https://picx.dev/ 2026-08-22 daily 1.0 https://picx.dev/gallery 2026-08-22 weekly 0.9 https://picx.dev/news hourly 0.8 https://picx.dev/gallery/archive 2026-08-22 daily 0.6 https://picx.dev/gallery/c/llm 2026-08-22 daily 0.7 https://picx.dev/gallery/c/nlp 2026-08-22 daily 0.7 https://picx.dev/gallery/c/multimodal 2026-08-22 daily 0.7 https://picx.dev/gallery/c/vision 2026-08-22 daily 0.7 https://picx.dev/gallery/c/generative 2026-08-22 daily 0.7 https://picx.dev/gallery/c/speech-audio 2026-08-22 daily 0.7 https://picx.dev/gallery/c/reinforcement-learning 2026-08-22 daily 0.7 https://picx.dev/gallery/c/agents 2026-08-22 daily 0.7 https://picx.dev/gallery/c/reasoning-planning 2026-08-22 daily 0.7 https://picx.dev/gallery/c/retrieval-rag 2026-08-22 daily 0.7 https://picx.dev/gallery/c/robotics-3d 2026-08-22 daily 0.7 https://picx.dev/gallery/c/ml-theory 2026-08-22 daily 0.7 https://picx.dev/gallery/c/efficiency 2026-08-22 daily 0.7 https://picx.dev/gallery/c/data-benchmark 2026-08-22 daily 0.7 https://picx.dev/gallery/c/alignment-safety 2026-08-22 daily 0.7 https://picx.dev/gallery/c/ai-for-science 2026-08-22 daily 0.7 https://picx.dev/gallery/d/formal-math 2026-08-22 weekly 0.7 https://picx.dev/gallery/d/pretrain-data 2026-08-22 weekly 0.7 https://picx.dev/gallery/d/moe 2026-08-22 weekly 0.7 https://picx.dev/gallery/d/efficient-attention 2026-08-22 weekly 0.7 https://picx.dev/gallery/d/scaling-training 2026-08-22 weekly 0.7 https://picx.dev/gallery/d/coding-agent 2026-08-22 weekly 0.7 https://picx.dev/gallery/d/self-improvement 2026-08-22 weekly 0.7 https://picx.dev/gallery/w/2026-08-22 2026-08-22 weekly 0.7 https://picx.dev/gallery/w/2026-08-15 2026-08-18 yearly 0.7 https://picx.dev/p/NkqbtS 2026-08-22 never 0.7 https://picx.dev/p/NkqbtS/image Harness Continual Learning: Continual Adaptation Beyond Model Parameters https://picx.dev/p/63a00p 2026-08-22 never 0.7 https://picx.dev/p/63a00p/image Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines? https://picx.dev/p/wgIzZ7 2026-08-22 never 0.7 https://picx.dev/p/wgIzZ7/image EvoMem: Memory-Augmented Evolution for Code Optimization https://picx.dev/p/tAFHIW 2026-08-22 never 0.7 https://picx.dev/p/tAFHIW/image SPADE: Self-Play in Adaptive Synthetic Executable Environments https://picx.dev/p/PEvnmA 2026-08-22 never 0.7 https://picx.dev/p/PEvnmA/image More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges https://picx.dev/p/hdg20S 2026-08-22 never 0.7 https://picx.dev/p/hdg20S/image Rollout Cards: A Reproducibility Standard for Agent Research https://picx.dev/p/r7iA0U 2026-08-22 never 0.7 https://picx.dev/p/r7iA0U/image AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement https://picx.dev/p/Inam8u 2026-08-22 never 0.7 https://picx.dev/p/Inam8u/image Phantom Gains: Auditing Self-Improvement Against a Measured Null https://picx.dev/p/ugT3eP 2026-08-22 never 0.7 https://picx.dev/p/ugT3eP/image Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench https://picx.dev/p/cccHxl 2026-08-22 never 0.7 https://picx.dev/p/cccHxl/image RestoreKV: Recovering Full-Cache Behavior Under Aggressive Query-Agnostic KV Cache Eviction https://picx.dev/p/70Hb5c 2026-08-22 never 0.7 https://picx.dev/p/70Hb5c/image Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs https://picx.dev/p/cuQl3f 2026-08-22 never 0.7 https://picx.dev/p/cuQl3f/image Training Transformers for KV Cache Compressibility (KV-CAT) https://picx.dev/p/Kt71Qi 2026-08-22 never 0.7 https://picx.dev/p/Kt71Qi/image OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching https://picx.dev/p/qxVV7R 2026-08-22 never 0.7 https://picx.dev/p/qxVV7R/image Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families https://picx.dev/p/ZEvoGQ 2026-08-22 never 0.7 https://picx.dev/p/ZEvoGQ/image Priming: Hybrid State Space Models From Pre-trained Transformers https://picx.dev/p/M6UsdR 2026-08-22 never 0.7 https://picx.dev/p/M6UsdR/image COBS: Cumulant Order Block Sparse Attention https://picx.dev/p/0lid0N 2026-08-22 never 0.7 https://picx.dev/p/0lid0N/image Auditing Reward Hackability in Code RL Training Environments https://picx.dev/p/L2OmH2 2026-08-22 never 0.7 https://picx.dev/p/L2OmH2/image HarnessOpt-Bench: Evaluating LLMs at Harness Optimization https://picx.dev/p/MgICR8 2026-08-22 never 0.7 https://picx.dev/p/MgICR8/image Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops https://picx.dev/p/3QMCRC 2026-08-22 never 0.7 https://picx.dev/p/3QMCRC/image The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks https://picx.dev/p/jBNH9m 2026-08-22 never 0.7 https://picx.dev/p/jBNH9m/image LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents https://picx.dev/p/qyHb7W 2026-08-22 never 0.7 https://picx.dev/p/qyHb7W/image Agent Lightning v1.0: Towards Harnessed Agentic RL https://picx.dev/p/R06uw3 2026-08-22 never 0.7 https://picx.dev/p/R06uw3/image The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation https://picx.dev/p/iETSYd 2026-08-22 never 0.7 https://picx.dev/p/iETSYd/image On the Nonlinearity of Learning Rate Scaling for LLM Training https://picx.dev/p/HZpmDd 2026-08-22 never 0.7 https://picx.dev/p/HZpmDd/image Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate https://picx.dev/p/1RM1ox 2026-08-22 never 0.7 https://picx.dev/p/1RM1ox/image Unified Neural Scaling Laws https://picx.dev/p/a7fifj 2026-08-22 never 0.7 https://picx.dev/p/a7fifj/image Abra: Scaling Diffusion Image Training https://picx.dev/p/IsG1aY 2026-08-22 never 0.7 https://picx.dev/p/IsG1aY/image Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World https://picx.dev/p/nnA6xQ 2026-08-22 never 0.7 https://picx.dev/p/nnA6xQ/image Towards Joint Scaling Laws with Optimal Batch Size Schedules https://picx.dev/p/YtXrCT 2026-08-22 never 0.7 https://picx.dev/p/YtXrCT/image Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization https://picx.dev/p/Un91AC 2026-08-22 never 0.7 https://picx.dev/p/Un91AC/image ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels https://picx.dev/p/BrYNX3 2026-08-22 never 0.7 https://picx.dev/p/BrYNX3/image MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving https://picx.dev/p/RLS011 2026-08-22 never 0.7 https://picx.dev/p/RLS011/image Diagnosing Training Inference Mismatch in LLM Reinforcement Learning (VeXact) https://picx.dev/p/vUWmrq 2026-08-22 never 0.7 https://picx.dev/p/vUWmrq/image Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing https://picx.dev/p/1TL5DI 2026-08-22 never 0.7 https://picx.dev/p/1TL5DI/image ReLibra: Routing-Replay-Guided Load Balancing for MoE Training in Reinforcement Learning https://picx.dev/p/5Pt6Rt 2026-08-22 never 0.7 https://picx.dev/p/5Pt6Rt/image Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training https://picx.dev/p/0Jv0ss 2026-08-22 never 0.7 https://picx.dev/p/0Jv0ss/image MidTool: Mid-training Data Synthesis for Agentic Tool Use https://picx.dev/p/xHfD3k 2026-08-22 never 0.7 https://picx.dev/p/xHfD3k/image The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora https://picx.dev/p/2Myrfj 2026-08-22 never 0.7 https://picx.dev/p/2Myrfj/image Scaling Domain Data Repetition in LLM Pretraining https://picx.dev/p/2yo0c5 2026-08-22 never 0.7 https://picx.dev/p/2yo0c5/image Explaining Data Mixing Scaling Laws https://picx.dev/p/0F9mM1 2026-08-22 never 0.7 https://picx.dev/p/0F9mM1/image Does the Proof Prove It That Way? Faithful Formalization of Elements Proofs https://picx.dev/p/vP8iCu 2026-08-22 never 0.7 https://picx.dev/p/vP8iCu/image Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization https://picx.dev/p/0egBJE 2026-08-22 never 0.7 https://picx.dev/p/0egBJE/image LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization https://picx.dev/p/plsrZn 2026-08-22 never 0.7 https://picx.dev/p/plsrZn/image Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement https://picx.dev/p/4vm4LX 2026-08-22 never 0.7 https://picx.dev/p/4vm4LX/image OProver: A Unified Framework for Agentic Formal Theorem Proving https://picx.dev/p/Uzn1P1 2026-08-22 never 0.7 https://picx.dev/p/Uzn1P1/image FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models https://picx.dev/p/eIM6cJ 2026-08-22 never 0.7 https://picx.dev/p/eIM6cJ/image LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks https://picx.dev/p/yUth75 2026-08-22 never 0.7 https://picx.dev/p/yUth75/image FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis https://picx.dev/p/Q5MumR 2026-08-22 never 0.7 https://picx.dev/p/Q5MumR/image EnvHarness: Awakening Static Worlds for Agent Learning https://picx.dev/p/xxNgxc 2026-08-21 never 0.7 https://picx.dev/p/xxNgxc/image SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation https://picx.dev/p/EA5MqG 2026-08-21 never 0.7 https://picx.dev/p/EA5MqG/image Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence https://picx.dev/p/qkfB3H 2026-08-21 never 0.7 https://picx.dev/p/qkfB3H/image SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation https://picx.dev/p/whkUoq 2026-08-20 never 0.7 https://picx.dev/p/whkUoq/image Demystifying Agent Skills: Why They Work-Until They Don't https://picx.dev/p/R5jC88 2026-08-19 never 0.7 https://picx.dev/p/R5jC88/image HarnessEval-W: Agentifying the Evaluation of Visual Worlds https://picx.dev/p/z3vsE3 2026-08-19 never 0.7 https://picx.dev/p/z3vsE3/image StateM: Reaching 95.3% Raw Accuracy, or a $15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling https://picx.dev/p/J50qCn 2026-08-18 never 0.7 https://picx.dev/p/J50qCn/image VERDI: RETRIEVAL IS NOT TRANSFER FOR CONTINUAL WORLD MODEL OPTIMIZATION https://picx.dev/p/DWY5bM 2026-08-18 never 0.7 https://picx.dev/p/DWY5bM/image Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection Pressure https://picx.dev/p/e8QzQK 2026-08-18 never 0.7 https://picx.dev/p/e8QzQK/image Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training https://picx.dev/p/pibb9F 2026-08-18 never 0.7 https://picx.dev/p/pibb9F/image Memory Reward Inflation in Self-Improving LLM Agents https://picx.dev/p/nd67r5 2026-08-18 never 0.7 https://picx.dev/p/nd67r5/image Data-Constrained Language Model Pretraining: Improved Regularization and Scaling Laws https://picx.dev/p/6pdG96 2026-08-18 never 0.7 https://picx.dev/p/6pdG96/image The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data https://picx.dev/p/XMAEVn 2026-08-18 never 0.7 https://picx.dev/p/XMAEVn/image How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings https://picx.dev/p/n7C2Cq 2026-08-18 never 0.7 https://picx.dev/p/n7C2Cq/image Generating Pretraining Tokens from Organic Data for Data-Bound Scaling https://picx.dev/p/XxxrQK 2026-08-18 never 0.7 https://picx.dev/p/XxxrQK/image Bridging Compute- and Data-Optimal Pretraining https://picx.dev/p/EETT3k 2026-08-18 never 0.7 https://picx.dev/p/EETT3k/image Internal Data Repetition Destroys Language Models https://picx.dev/p/4MwF44 2026-08-18 never 0.7 https://picx.dev/p/4MwF44/image Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models https://picx.dev/p/xrSXnn 2026-08-18 never 0.7 https://picx.dev/p/xrSXnn/image The Efficiency Gap in Byte Modeling https://picx.dev/p/2SbyCt 2026-08-18 never 0.7 https://picx.dev/p/2SbyCt/image UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing https://picx.dev/p/xyTam6 2026-08-18 never 0.7 https://picx.dev/p/xyTam6/image Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory https://picx.dev/p/b8iqVt 2026-08-18 never 0.7 https://picx.dev/p/b8iqVt/image PR²: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning https://picx.dev/p/tvYIqU 2026-08-18 never 0.7 https://picx.dev/p/tvYIqU/image Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression https://picx.dev/p/bZdTWU 2026-08-18 never 0.7 https://picx.dev/p/bZdTWU/image SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference https://picx.dev/p/S0E5DV 2026-08-18 never 0.7 https://picx.dev/p/S0E5DV/image Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms https://picx.dev/p/mjecui 2026-08-18 never 0.7 https://picx.dev/p/mjecui/image SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work? https://picx.dev/p/YT7O5G 2026-08-18 never 0.7 https://picx.dev/p/YT7O5G/image Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack https://picx.dev/p/XG8qga 2026-08-18 never 0.7 https://picx.dev/p/XG8qga/image Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows https://picx.dev/p/KxfmZJ 2026-08-18 never 0.7 https://picx.dev/p/KxfmZJ/image Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization https://picx.dev/p/pVtDfk 2026-08-18 never 0.7 https://picx.dev/p/pVtDfk/image The Faithfulness Gap: Certifying Semantic Equivalence Between Natural-Language and Formal Mathematical Statements https://picx.dev/p/MJHk5D 2026-08-18 never 0.7 https://picx.dev/p/MJHk5D/image MechGeo: Autoformalizing and Proving Euclidean Geometry in Lean 4 https://picx.dev/p/enaLEb 2026-08-18 never 0.7 https://picx.dev/p/enaLEb/image Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning https://picx.dev/p/ALTEB9 2026-08-18 never 0.7 https://picx.dev/p/ALTEB9/image Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development https://picx.dev/p/AhNtHC 2026-08-18 never 0.7 https://picx.dev/p/AhNtHC/image Self-Supervised Visual On-Policy Distillation https://picx.dev/p/N8nJJ2 2026-08-18 never 0.7 https://picx.dev/p/N8nJJ2/image Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination https://picx.dev/p/jnkmPQ 2026-08-17 never 0.7 https://picx.dev/p/jnkmPQ/image ε-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution https://picx.dev/p/YWPzDm 2026-08-17 never 0.7 https://picx.dev/p/YWPzDm/image PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents https://picx.dev/p/oGJ5xP 2026-08-17 never 0.7 https://picx.dev/p/oGJ5xP/image When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops https://picx.dev/p/77192p 2026-08-17 never 0.7 https://picx.dev/p/77192p/image Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents https://picx.dev/p/yRPcBQ 2026-08-17 never 0.7 https://picx.dev/p/yRPcBQ/image Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL https://picx.dev/p/twKveT 2026-08-17 never 0.7 https://picx.dev/p/twKveT/image Structured Scaling of AI Discovery Across Diverse Scientific Domains https://picx.dev/p/UsUzlm 2026-08-17 never 0.7 https://picx.dev/p/UsUzlm/image Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics https://picx.dev/p/RIZkTk 2026-08-17 never 0.7 https://picx.dev/p/RIZkTk/image Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics https://picx.dev/p/23YNki 2026-08-17 never 0.7 https://picx.dev/p/23YNki/image Multi-agent Autoformalization of Tensor Network Theory https://picx.dev/p/UQ23ax 2026-08-17 never 0.7 https://picx.dev/p/UQ23ax/image FormaTheoria: Constructing Large-Scale Lean Theories from Mathematical Literature - Toward the Formalization of the Classification of Finite Simple Groups https://picx.dev/p/ZOJb9Q 2026-08-17 never 0.7 https://picx.dev/p/ZOJb9Q/image MathAtlas: A Benchmark for Autoformalization in the Wild https://picx.dev/p/jG3uEe 2026-08-17 never 0.7 https://picx.dev/p/jG3uEe/image Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving https://picx.dev/p/1W29zP 2026-08-17 never 0.7 https://picx.dev/p/1W29zP/image A SAT Attack on Tarski’s High School Algebra Problem https://picx.dev/p/fXod2x 2026-08-17 never 0.7 https://picx.dev/p/fXod2x/image Advancing Mathematics Research with AI-Driven Formal Proof Search https://picx.dev/p/FyDUWn 2026-08-17 never 0.7 https://picx.dev/p/FyDUWn/image Rethinking Language Model Scaling under Transferable Hypersphere Optimization https://picx.dev/p/0QVKjG 2026-08-17 never 0.7 https://picx.dev/p/0QVKjG/image Dion3: Full-stack orthogonal updates https://picx.dev/p/D7cTAI 2026-08-17 never 0.7 https://picx.dev/p/D7cTAI/image Small-Scale Experiments: Are We There Yet? https://picx.dev/p/Fk1zpP 2026-08-17 never 0.7 https://picx.dev/p/Fk1zpP/image Skaling: Chinchilla’s Exponents Meet Kaplan’s Coupling https://picx.dev/p/ngVQEw 2026-08-17 never 0.7 https://picx.dev/p/ngVQEw/image Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits https://picx.dev/p/xqiFHS 2026-08-17 never 0.7 https://picx.dev/p/xqiFHS/image Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation https://picx.dev/p/iX3crF 2026-08-17 never 0.7 https://picx.dev/p/iX3crF/image How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization https://picx.dev/p/fbbSgs 2026-08-17 never 0.7 https://picx.dev/p/fbbSgs/image When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models https://picx.dev/p/WwS461 2026-08-17 never 0.7 https://picx.dev/p/WwS461/image Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-Experts https://picx.dev/p/dbV39w 2026-08-17 never 0.7 https://picx.dev/p/dbV39w/image Probing RLVR Training Instability through the Lens of Objective-Level Hacking https://picx.dev/p/YCH40Q 2026-08-17 never 0.7 https://picx.dev/p/YCH40Q/image TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes https://picx.dev/p/CpsmbX 2026-08-17 never 0.7 https://picx.dev/p/CpsmbX/image Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts https://picx.dev/p/8VuYT5 2026-08-17 never 0.7 https://picx.dev/p/8VuYT5/image How Modular Is a Frontier Mixture-of-Experts? A Pre-registered Causal Test in Which Apparent Expert Modularity Mostly Dissolves https://picx.dev/p/6vvmyr 2026-08-17 never 0.7 https://picx.dev/p/6vvmyr/image The Finetuner’s Fallacy When to Pretrain with Your Finetuning Data https://picx.dev/p/GiafjZ 2026-08-17 never 0.7 https://picx.dev/p/GiafjZ/image Repetition Mismatch: Why Data Mixture Experiments Don’t Scale and How to Fix Them https://picx.dev/p/dHgQ0Z 2026-08-17 never 0.7 https://picx.dev/p/dHgQ0Z/image PRISM: Demystifying Retention and Interaction in Mid-Training https://picx.dev/p/Xtt9iH 2026-08-17 never 0.7 https://picx.dev/p/Xtt9iH/image InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition https://picx.dev/p/eALen5 2026-08-17 never 0.7 https://picx.dev/p/eALen5/image Scaling Laws for Mixture Pretraining Under Data Constraints https://picx.dev/p/vB2BqW 2026-08-17 never 0.7 https://picx.dev/p/vB2BqW/image A Bitter Lesson for Data Filtering https://picx.dev/p/o8rY3b 2026-08-17 never 0.7 https://picx.dev/p/o8rY3b/image How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data https://picx.dev/p/lHtyVs 2026-08-17 never 0.7 https://picx.dev/p/lHtyVs/image MARCH: Scaling Recurrent Memory with Content-Routed State Anchors https://picx.dev/p/MmJeX9 2026-08-17 never 0.7 https://picx.dev/p/MmJeX9/image You Only Index Once: Cross-Layer Sparse Attention with Shared Routing https://picx.dev/p/QPMgD7 2026-08-17 never 0.7 https://picx.dev/p/QPMgD7/image MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference https://picx.dev/p/RxY43P 2026-08-17 never 0.7 https://picx.dev/p/RxY43P/image How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit https://picx.dev/p/7KD3Bi 2026-08-17 never 0.7 https://picx.dev/p/7KD3Bi/image LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing https://picx.dev/p/oAAZ43 2026-08-17 never 0.7 https://picx.dev/p/oAAZ43/image Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge https://picx.dev/p/z6NIX8 2026-08-17 never 0.7 https://picx.dev/p/z6NIX8/image Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension https://picx.dev/p/I6p9xF 2026-08-17 never 0.7 https://picx.dev/p/I6p9xF/image SWE-Touch: Benchmarking Coding Agents When Users Touch the Code https://picx.dev/p/fPa0ks 2026-08-17 never 0.7 https://picx.dev/p/fPa0ks/image Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents https://picx.dev/p/4Mg2zv 2026-08-17 never 0.7 https://picx.dev/p/4Mg2zv/image SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents https://picx.dev/p/E0FEZg 2026-08-17 never 0.7 https://picx.dev/p/E0FEZg/image Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI https://picx.dev/p/XjV02V 2026-08-17 never 0.7 https://picx.dev/p/XjV02V/image One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models https://picx.dev/p/4gfsEG 2026-08-17 never 0.7 https://picx.dev/p/4gfsEG/image EVO-BENCH: CAN LANGUAGE MODELS IMPROVE AGENT HARNESS? https://picx.dev/p/9wH5KI 2026-08-17 never 0.7 https://picx.dev/p/9wH5KI/image Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents https://picx.dev/p/pfX4Qf 2026-08-15 never 0.7 https://picx.dev/p/pfX4Qf/image HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses https://picx.dev/p/f5hlW9 2026-08-15 never 0.7 https://picx.dev/p/f5hlW9/image One Run Is Not an Idea: The Implementation Lottery in Automated Research https://picx.dev/p/jb1hbm 2026-08-15 never 0.7 https://picx.dev/p/jb1hbm/image Replaying pre-training data improves fine-tuning https://picx.dev/p/fZmmSS 2026-08-15 never 0.7 https://picx.dev/p/fZmmSS/image Prescriptive Scaling Laws for Data Constrained Training https://picx.dev/p/swvAfv 2026-08-15 never 0.7 https://picx.dev/p/swvAfv/image Self-Distillation for Multi-Token Prediction https://picx.dev/p/UtGNZI 2026-08-15 never 0.7 https://picx.dev/p/UtGNZI/image Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay https://picx.dev/p/3yNTi4 2026-08-15 never 0.7 https://picx.dev/p/3yNTi4/image SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales https://picx.dev/p/p7vJoN 2026-08-15 never 0.7 https://picx.dev/p/p7vJoN/image ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving https://picx.dev/p/SzCAwV 2026-08-15 never 0.7 https://picx.dev/p/SzCAwV/image From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models https://picx.dev/p/zKK3jH 2026-08-15 never 0.7 https://picx.dev/p/zKK3jH/image LINEARKV: ONE CACHED STATE SUFFICES FORPOSITION-INDEPENDENT CACHING IN HYBRID LLMS https://picx.dev/p/xbLDV9 2026-08-15 never 0.7 https://picx.dev/p/xbLDV9/image Rethinking the Role of Efficient Attention in Hybrid Architectures https://picx.dev/p/BoGzdv 2026-08-15 never 0.7 https://picx.dev/p/BoGzdv/image DevIntent: How Much Does LLM-Generated Code Violate Developer Intent? https://picx.dev/p/nNsgCt 2026-08-15 never 0.7 https://picx.dev/p/nNsgCt/image Rethinking the Evaluation of Harness Evolution for Agents https://picx.dev/p/bg4Q16 2026-08-15 never 0.7 https://picx.dev/p/bg4Q16/image How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions https://picx.dev/p/nyL7PI 2026-08-15 never 0.7 https://picx.dev/p/nyL7PI/image Don’t Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality https://picx.dev/p/5M5L1t 2026-08-15 never 0.7 https://picx.dev/p/5M5L1t/image Learned Interventions in Lean 4 grind https://picx.dev/p/zo852T 2026-08-15 never 0.7 https://picx.dev/p/zo852T/image The Banach lattice Lean library https://picx.dev/p/z2ZaEO 2026-08-15 never 0.7 https://picx.dev/p/z2ZaEO/image DO LLMS GAME FORMALIZATION? EVALUATING FAITHFULNESS IN LOGICAL REASONING https://picx.dev/p/KnJfBf 2026-08-15 never 0.7 https://picx.dev/p/KnJfBf/image AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design https://picx.dev/p/PcOtrb 2026-08-15 never 0.7 https://picx.dev/p/PcOtrb/image PLAYWORLD: BENCHMARKING WORLD MODELS WITH AGENT PLAYERS OVER LONG-HORIZON OBJECTIVES https://picx.dev/p/f7Doz0 2026-08-15 never 0.7 https://picx.dev/p/f7Doz0/image How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review https://picx.dev/p/mG8p19 2026-08-15 never 0.7 https://picx.dev/p/mG8p19/image Intern-S2-Preview: Scientific Agentic Foundation Model https://picx.dev/p/NnhFYG 2026-08-15 never 0.7 https://picx.dev/p/NnhFYG/image DarwinX: Evolving Agent Harnesses Through Natural Selection https://picx.dev/p/P0d3Ei 2026-08-15 never 0.7 https://picx.dev/p/P0d3Ei/image LLMROUTER: UNIFIED INFRASTRUCTURE FOR DEVELOPING, EVALUATING, AND DEPLOYING LLM ROUTERS https://picx.dev/p/gEoAIt 2026-08-14 never 0.7 https://picx.dev/p/gEoAIt/image SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries https://picx.dev/p/ktXxa9 2026-08-14 never 0.7 https://picx.dev/p/ktXxa9/image Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence https://picx.dev/p/Rruz4J 2026-08-14 never 0.7 https://picx.dev/p/Rruz4J/image AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses https://picx.dev/p/SLbCAp 2026-08-14 never 0.7 https://picx.dev/p/SLbCAp/image Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill https://picx.dev/p/Ld0o52 2026-08-14 never 0.7 https://picx.dev/p/Ld0o52/image OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution https://picx.dev/p/sBSbvF 2026-08-13 never 0.7 https://picx.dev/p/sBSbvF/image Articulated Object Reconstruction from Rest-State Observation https://picx.dev/p/m9PmqN 2026-08-13 never 0.7 https://picx.dev/p/m9PmqN/image Beyond Pixels: From Video Priors to 4D Worlds https://picx.dev/p/ss3I1x 2026-08-13 never 0.7 https://picx.dev/p/ss3I1x/image Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design https://picx.dev/p/A7f2AC 2026-08-12 never 0.7 https://picx.dev/p/A7f2AC/image Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory https://picx.dev/p/1D30Mn 2026-08-12 never 0.7 https://picx.dev/p/1D30Mn/image Stealing Reasoning Traces from Proprietary LLM APIs https://picx.dev/p/ZLy6La 2026-08-12 never 0.7 https://picx.dev/p/ZLy6La/image Motif 3: Technical Report https://picx.dev/p/gKNiJP 2026-08-12 never 0.7 https://picx.dev/p/gKNiJP/image On-Policy Self-Distillation without Any Supervision https://picx.dev/p/UYhd6L 2026-08-12 never 0.7 https://picx.dev/p/UYhd6L/image Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution https://picx.dev/p/o3LZSK 2026-08-12 never 0.7 https://picx.dev/p/o3LZSK/image SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring https://picx.dev/p/h76Pwv 2026-08-12 never 0.7 https://picx.dev/p/h76Pwv/image Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA https://picx.dev/p/tJT3x0 2026-08-11 never 0.7 https://picx.dev/p/tJT3x0/image SimWAM: A Simple World Action Model for End-to-End Autonomous Driving https://picx.dev/p/77K7Ie 2026-08-11 never 0.7 https://picx.dev/p/77K7Ie/image Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning https://picx.dev/p/eBG0Py 2026-08-11 never 0.7 https://picx.dev/p/eBG0Py/image SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs https://picx.dev/p/DDhxkr 2026-08-08 never 0.7 https://picx.dev/p/5qadmD 2026-08-08 never 0.7 https://picx.dev/p/5qadmD/image INTERPRETABLE MEG DECODING OF PERCEIVED SPEECH: CORTICAL SOURCES AND THE STIMULUS FEATURES THAT DRIVE RETRIEVAL https://picx.dev/p/4nIoDN 2026-08-08 never 0.7 https://picx.dev/p/4nIoDN/image WorldClaw: Agentic 3D Open-World Generation at Scale https://picx.dev/p/lfAQBy 2026-08-08 never 0.7 https://picx.dev/p/7WLkGI 2026-08-08 never 0.7 https://picx.dev/p/W8U5Vs 2026-08-07 never 0.7 https://picx.dev/p/12bbbP 2026-08-07 never 0.7 https://picx.dev/p/z0MUbK 2026-08-07 never 0.7 https://picx.dev/p/z0MUbK/image ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation https://picx.dev/p/Pz5QzK 2026-08-07 never 0.7 https://picx.dev/p/0TQ6yq 2026-08-06 never 0.7 https://picx.dev/p/0TQ6yq/image PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning https://picx.dev/p/n4eRsD 2026-08-06 never 0.7 https://picx.dev/p/n4eRsD/image Knowledge–Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation https://picx.dev/p/I0NEeE 2026-08-06 never 0.7 https://picx.dev/p/I0NEeE/image Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent https://picx.dev/p/oJldMy 2026-08-06 never 0.7 https://picx.dev/p/LJkeTS 2026-08-06 never 0.7 https://picx.dev/p/LJkeTS/image AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling https://picx.dev/p/iOTTwa 2026-08-06 never 0.7 https://picx.dev/p/iOTTwa/image JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion https://picx.dev/p/z2KSzI 2026-08-06 never 0.7 https://picx.dev/p/z2KSzI/image MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations https://picx.dev/p/oKQ3uz 2026-08-05 never 0.7 https://picx.dev/p/oKQ3uz/image CADENA: Stepwise CAD Reverse Engineering https://picx.dev/p/F1KIsS 2026-08-05 never 0.7 https://picx.dev/p/F1KIsS/image WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity https://picx.dev/p/hJEozU 2026-08-05 never 0.7 https://picx.dev/p/hJEozU/image UEmbed: Unified Sparse and Dense Multimodal Embeddings https://picx.dev/p/0caM3t 2026-08-05 never 0.7 https://picx.dev/p/s4hUjj 2026-08-05 never 0.7 https://picx.dev/p/s4hUjj/image Progressive Agent Skill Generation via Reinforcement Learning https://picx.dev/p/Y13IMA 2026-08-05 never 0.7 https://picx.dev/p/Y13IMA/image DAPD: Dual-Anchored Policy Distillation https://picx.dev/p/5G5Kuh 2026-08-05 never 0.7 https://picx.dev/p/5G5Kuh/image LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks https://picx.dev/p/GKb3xZ 2026-08-05 never 0.7 https://picx.dev/p/GKb3xZ/image SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks https://picx.dev/p/1PrYux 2026-08-04 never 0.7 https://picx.dev/p/1PrYux/image AISPA: User-Centric System Prompt Auditing for Large Language Model Applications https://picx.dev/p/GmVldH 2026-08-04 never 0.7 https://picx.dev/p/8lIKV4 2026-08-04 never 0.7 https://picx.dev/p/8lIKV4/image N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens https://picx.dev/p/NwAwDF 2026-08-04 never 0.7 https://picx.dev/p/NwAwDF/image Mental World Modeling https://picx.dev/p/AxBP49 2026-08-04 never 0.7 https://picx.dev/p/AxBP49/image From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement https://picx.dev/p/3t5c7C 2026-08-01 never 0.7 https://picx.dev/p/3t5c7C/image Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation https://picx.dev/p/JuGyYE 2026-08-01 never 0.7 https://picx.dev/p/qLn2E3 2026-08-01 never 0.7 https://picx.dev/p/qLn2E3/image MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing https://picx.dev/p/DRyKXl 2026-08-01 never 0.7 https://picx.dev/p/DRyKXl/image Flux-OPD: On-Policy Distillation with Evolving Contexts https://picx.dev/p/CP2jT2 2026-08-01 never 0.7 https://picx.dev/p/CP2jT2/image BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms https://picx.dev/p/fwZ0m9 2026-08-01 never 0.7 https://picx.dev/p/fwZ0m9/image Beacon: Knowing When and How to Perform Agentic Visual Reasoning https://picx.dev/p/p2ZSmM 2026-08-01 never 0.7 https://picx.dev/p/p2ZSmM/image Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory https://picx.dev/p/DedoDn 2026-08-01 never 0.7 https://picx.dev/p/DedoDn/image VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System https://picx.dev/p/d1mFT4 2026-08-01 never 0.7 https://picx.dev/p/d1mFT4/image Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering https://picx.dev/p/tKHGyr 2026-08-01 never 0.7 https://picx.dev/p/tKHGyr/image PhiZero: A World Model Built Around Physical Language https://picx.dev/p/Pwp8Fd 2026-08-01 never 0.7 https://picx.dev/p/Pwp8Fd/image Metis: Memory Foundation Model https://picx.dev/p/5xnDqo 2026-08-01 never 0.7 https://picx.dev/p/5xnDqo/image Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents https://picx.dev/p/1jxDR7 2026-08-01 never 0.7 https://picx.dev/p/1jxDR7/image AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis https://picx.dev/p/8MuH3Y 2026-07-31 never 0.7 https://picx.dev/p/8MuH3Y/image CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition https://picx.dev/p/ByGcAp 2026-07-31 never 0.7 https://picx.dev/p/ByGcAp/image DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space https://picx.dev/p/OV3aqY 2026-07-31 never 0.7 https://picx.dev/p/OV3aqY/image HumanCLAW: Can Vision-Language Models Act Through a Body? https://picx.dev/p/15gUZ4 2026-07-31 never 0.7 https://picx.dev/p/15gUZ4/image CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization https://picx.dev/p/E9Y8yt 2026-07-31 never 0.7 https://picx.dev/p/E9Y8yt/image TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM https://picx.dev/p/pWRP1l 2026-07-30 never 0.7 https://picx.dev/p/pWRP1l/image CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents https://picx.dev/p/0xf6mh 2026-07-30 never 0.7 https://picx.dev/p/0xf6mh/image ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition https://picx.dev/p/ZIoiZE 2026-07-30 never 0.7 https://picx.dev/p/ZIoiZE/image A New Role for Relevance: Guiding Corpus Interaction in Agentic Search https://picx.dev/p/3gnTFs 2026-07-29 never 0.7 https://picx.dev/p/3gnTFs/image Data Pyramid for Embodied Manipulation https://picx.dev/p/TdLQoX 2026-07-29 never 0.7 https://picx.dev/p/TdLQoX/image StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents https://picx.dev/p/dQLCvu 2026-07-29 never 0.7 https://picx.dev/p/dQLCvu/image Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation https://picx.dev/p/MlZ6z3 2026-07-29 never 0.7 https://picx.dev/p/MlZ6z3/image Progress Reward Modeling for Robotic Learning: A Comprehensive Survey https://picx.dev/p/NdazTg 2026-07-29 never 0.7 https://picx.dev/p/NdazTg/image From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search https://picx.dev/p/Nx5965 2026-07-29 never 0.7 https://picx.dev/p/Nx5965/image JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents https://picx.dev/p/048q6D 2026-07-29 never 0.7 https://picx.dev/p/8CyDxL 2026-07-28 never 0.7 https://picx.dev/p/RNW5s2 2026-07-28 never 0.7 https://picx.dev/p/RNW5s2/image Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills https://picx.dev/p/Zz2DfH 2026-07-28 never 0.7 https://picx.dev/p/Zz2DfH/image DataPrep-Bench: Benchmarking LLMs as Training Data Preparators https://picx.dev/p/kDmUaz 2026-07-25 never 0.7 https://picx.dev/p/kDmUaz/image Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text https://picx.dev/p/qwvySU 2026-07-25 never 0.7 https://picx.dev/p/qwvySU/image Visual Contrastive Self-Distillation https://picx.dev/p/smAVs7 2026-07-25 never 0.7 https://picx.dev/p/smAVs7/image K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs https://picx.dev/p/30isza 2026-07-25 never 0.7 https://picx.dev/p/30isza/image ReferTrack: Referring Then Tracking for Embodied Visual Tracking https://picx.dev/p/G4lEVu 2026-07-25 never 0.7 https://picx.dev/p/G4lEVu/image AREX: Towards a Recursively Self-Improving Agent for Deep Research https://picx.dev/p/zcTd3J 2026-07-24 never 0.7 https://picx.dev/p/zcTd3J/image Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking https://picx.dev/p/dzzHds 2026-07-24 never 0.7 https://picx.dev/p/dzzHds/image Self Gradient Forcing: Native Long Video Extrapolation https://picx.dev/p/Z2dTSJ 2026-07-24 never 0.7 https://picx.dev/p/Z2dTSJ/image SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD https://picx.dev/p/VyokBo 2026-07-23 never 0.7 https://picx.dev/p/VyokBo/image Subliminal Clocks: Latent Time Modelling in Diffusion Language Models https://picx.dev/p/b5Xs2s 2026-07-23 never 0.7 https://picx.dev/p/b5Xs2s/image AlayaWorld: Interactive Long-Horizon World Modeling – Full Technical Report https://picx.dev/p/zAkWa8 2026-07-23 never 0.7 https://picx.dev/p/zAkWa8/image Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing https://picx.dev/p/J7LquC 2026-07-23 never 0.7 https://picx.dev/p/J7LquC/image Generative World Renderer at the Speed of Play https://picx.dev/p/bZruum 2026-07-23 never 0.7 https://picx.dev/p/bZruum/image Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers https://picx.dev/p/kCmf8s 2026-07-23 never 0.7 https://picx.dev/p/kCmf8s/image DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines https://picx.dev/p/GodKH0 2026-07-23 never 0.7 https://picx.dev/p/GodKH0/image ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU https://picx.dev/p/0y0r4u 2026-07-22 never 0.7 https://picx.dev/p/0y0r4u/image GigaChat Audio: Time-aware Large Audio Language Model https://picx.dev/p/5DyRnD 2026-07-22 never 0.7 https://picx.dev/p/tKWpgw 2026-07-22 never 0.7 https://picx.dev/p/kkfX6M 2026-07-22 never 0.7 https://picx.dev/p/kkfX6M/image TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs https://picx.dev/p/AFbgub 2026-07-21 never 0.7 https://picx.dev/p/AFbgub/image Cura 1T: Specialized Model for Agentic Healthcare https://picx.dev/p/37GlhA 2026-07-21 never 0.7 https://picx.dev/p/37GlhA/image xHC: Expanded Hyper-Connections https://picx.dev/p/eehUMO 2026-07-21 never 0.7 https://picx.dev/p/eehUMO/image Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories https://picx.dev/p/CeOa7Z 2026-07-21 never 0.7 https://picx.dev/p/CeOa7Z/image Loop the Loopies! https://picx.dev/p/PBY7DM 2026-07-21 never 0.7 https://picx.dev/p/PBY7DM/image RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM https://picx.dev/p/swZJcJ 2026-07-21 never 0.7 https://picx.dev/p/swZJcJ/image RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources https://picx.dev/p/HQbP63 2026-07-18 never 0.7 https://picx.dev/p/HQbP63/image KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation https://picx.dev/p/xmxc61 2026-07-18 never 0.7 https://picx.dev/p/xmxc61/image BadWAM: When World-Action Models Dream Right but Act Wrong https://picx.dev/p/745msU 2026-07-18 never 0.7 https://picx.dev/p/745msU/image LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget https://picx.dev/p/gsDUiv 2026-07-18 never 0.7 https://picx.dev/p/gsDUiv/image SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration https://picx.dev/p/uhzsl4 2026-07-18 never 0.7 https://picx.dev/p/uhzsl4/image SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning https://picx.dev/p/0Njlvp 2026-07-18 never 0.7 https://picx.dev/p/0Njlvp/image VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding https://picx.dev/p/aghpmB 2026-07-17 never 0.7 https://picx.dev/p/aghpmB/image PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails https://picx.dev/p/troaBQ 2026-07-17 never 0.7 https://picx.dev/p/troaBQ/image OvisOCR2 Technical Report https://picx.dev/p/CFXbVN 2026-07-17 never 0.7 https://picx.dev/p/CFXbVN/image KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill https://picx.dev/p/WcqeEb 2026-07-17 never 0.7 https://picx.dev/p/UgfbtF 2026-07-17 never 0.7 https://picx.dev/p/UgfbtF/image Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation https://picx.dev/p/G9H8Ma 2026-07-17 never 0.7 https://picx.dev/p/G9H8Ma/image Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable https://picx.dev/p/kRPU03 2026-07-16 never 0.7 https://picx.dev/p/kRPU03/image Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation https://picx.dev/p/azaI2S 2026-07-16 never 0.7 https://picx.dev/p/azaI2S/image SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding https://picx.dev/p/QCAwQB 2026-07-15 never 0.7 https://picx.dev/p/QCAwQB/image LightMem-Ego: Your AI Memory for Everyday Life https://picx.dev/p/9GlVLZ 2026-07-15 never 0.7 https://picx.dev/p/9GlVLZ/image 4D Human-Scene Reconstruction from Low-Overlap Captures https://picx.dev/p/mmBNvc 2026-07-15 never 0.7 https://picx.dev/p/mmBNvc/image ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory https://picx.dev/p/43X4js 2026-07-15 never 0.7 https://picx.dev/p/43X4js/image ABot-N1: Toward a General Visual Language Navigation Foundation Model https://picx.dev/p/HZefSZ 2026-07-15 never 0.7 https://picx.dev/p/HZefSZ/image Weak-to-Strong Generalization via Direct On-Policy Distillation https://picx.dev/p/nJG15A 2026-07-14 never 0.7 https://picx.dev/p/nJG15A/image Video Generation Models are General-Purpose Vision Learners https://picx.dev/p/0L1czI 2026-07-14 never 0.7 https://picx.dev/p/0L1czI/image Scalable Visual Pretraining for Language Intelligence https://picx.dev/p/vwqt8Z 2026-07-14 never 0.7 https://picx.dev/p/vwqt8Z/image Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading https://picx.dev/p/HK96dk 2026-07-11 never 0.7 https://picx.dev/p/aQXEAk 2026-07-11 never 0.7 https://picx.dev/p/aQXEAk/image Video-Oasis: Rethinking Evaluation of Video Understanding https://picx.dev/p/xV8U5P 2026-07-11 never 0.7 https://picx.dev/p/xV8U5P/image Vidu S1: A Real-Time Interactive Video Generation Model https://picx.dev/p/ydBeEB 2026-07-10 never 0.7 https://picx.dev/p/ydBeEB/image Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence https://picx.dev/p/fPG4Zi 2026-07-10 never 0.7 https://picx.dev/p/fPG4Zi/image Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation https://picx.dev/p/0qxnse 2026-07-10 never 0.7 https://picx.dev/p/0qxnse/image Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning https://picx.dev/p/cr9gjl 2026-07-09 never 0.7 https://picx.dev/p/i8mmMJ 2026-07-09 never 0.7 https://picx.dev/p/i8mmMJ/image Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling https://picx.dev/p/pZ2fOz 2026-07-09 never 0.7 https://picx.dev/p/pZ2fOz/image RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation https://picx.dev/p/B1hmNx 2026-07-09 never 0.7 https://picx.dev/p/B1hmNx/image AlayaWorld: Long-Horizon and Playable Video World Generation https://picx.dev/p/OsaXaY 2026-07-09 never 0.7 https://picx.dev/p/OsaXaY/image RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation https://picx.dev/p/sygE2O 2026-07-08 never 0.7 https://picx.dev/p/sygE2O/image Vision Pretraining for Dense Spatial Perception https://picx.dev/p/QXd398 2026-07-08 never 0.7 https://picx.dev/p/QXd398/image GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation https://picx.dev/p/rScICU 2026-07-08 never 0.7 https://picx.dev/p/rScICU/image MANCE: Manifold Aware Concept Erasure https://picx.dev/p/JDQ11Z 2026-07-08 never 0.7 https://picx.dev/p/JDQ11Z/image ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes https://picx.dev/p/NUnw5e 2026-07-08 never 0.7 https://picx.dev/p/NUnw5e/image PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space https://picx.dev/p/caNPMZ 2026-07-08 never 0.7 https://picx.dev/p/caNPMZ/image ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog https://picx.dev/p/I4zBNo 2026-07-08 never 0.7 https://picx.dev/p/I4zBNo/image UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning https://picx.dev/p/IU1PkT 2026-07-08 never 0.7 https://picx.dev/p/IU1PkT/image OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers https://picx.dev/p/B0mkuh 2026-07-07 never 0.7 https://picx.dev/p/B0mkuh/image OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers https://picx.dev/p/3pMxi2 2026-07-07 never 0.7 https://picx.dev/p/3pMxi2/image Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots https://picx.dev/p/EV75Vd 2026-07-07 never 0.7 https://picx.dev/p/EV75Vd/image The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning https://picx.dev/p/H3DGRI 2026-07-04 never 0.7 https://picx.dev/p/qQbaHN 2026-07-04 never 0.7 https://picx.dev/p/qQbaHN/image AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents https://picx.dev/p/k2f6gQ 2026-07-04 never 0.7 https://picx.dev/p/k2f6gQ/image EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments https://picx.dev/p/UDQYDc 2026-07-04 never 0.7 https://picx.dev/p/UDQYDc/image Program-as-Weights: A Programming Paradigm for Fuzzy Functions https://picx.dev/p/nHgHob 2026-07-03 never 0.7 https://picx.dev/p/nHgHob/image TurboServe: Serving Streaming Video Generation Efficiently and Economically https://picx.dev/p/vpvWrV 2026-07-03 never 0.7 https://picx.dev/p/vpvWrV/image ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving https://picx.dev/p/p7Ez40 2026-07-03 never 0.7 https://picx.dev/p/p7Ez40/image PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception https://picx.dev/p/vsdFyK 2026-07-02 never 0.7 https://picx.dev/p/vsdFyK/image Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views https://picx.dev/p/H2Xp8d 2026-07-02 never 0.7 https://picx.dev/p/H2Xp8d/image Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models https://picx.dev/p/MouwNL 2026-07-02 never 0.7 https://picx.dev/p/MouwNL/image BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding https://picx.dev/p/1c5HeT 2026-07-02 never 0.7 https://picx.dev/p/1c5HeT/image DOPD: Dual On-policy Distillation https://picx.dev/p/PVRHDG 2026-07-02 never 0.7 https://picx.dev/p/PVRHDG/image Dockerless: Environment-Free Program Verifier for Coding Agents https://picx.dev/p/t1zh2K 2026-07-01 never 0.7 https://picx.dev/p/t1zh2K/image Trimming the Long-Tail of Visual World Modeling Evaluation https://picx.dev/p/EhGwFo 2026-07-01 never 0.7 https://picx.dev/p/EhGwFo/image Beyond IID: How General Are Tabular Foundation Models, Really? https://picx.dev/p/u1MqWG 2026-07-01 never 0.7 https://picx.dev/p/u1MqWG/image ReFreeKV: Towards Threshold-Free KV Cache Compression https://picx.dev/p/8ISXwp 2026-07-01 never 0.7 https://picx.dev/p/8ISXwp/image TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents https://picx.dev/p/2BUIZP 2026-07-01 never 0.7 https://picx.dev/p/2BUIZP/image Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent https://picx.dev/p/sj5s4w 2026-07-01 never 0.7 https://picx.dev/p/sj5s4w/image LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing https://picx.dev/p/L99Z3B 2026-07-01 never 0.7 https://picx.dev/p/L99Z3B/image Agentic Abstention: Do Agents Know When to Stop Instead of Act? https://picx.dev/p/Mn54sb 2026-06-30 never 0.7 https://picx.dev/p/Mn54sb/image Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots https://picx.dev/p/umBZGk 2026-06-30 never 0.7 https://picx.dev/p/umBZGk/image Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs https://picx.dev/p/1YP3e6 2026-06-30 never 0.7 https://picx.dev/p/1YP3e6/image PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation https://picx.dev/p/4mA5OF 2026-06-27 never 0.7 https://picx.dev/p/4mA5OF/image The Verification Horizon: No Silver Bullet for Coding Agent Rewards https://picx.dev/p/X0Pcag 2026-06-27 never 0.7 https://picx.dev/p/REHpgh 2026-06-27 never 0.7 https://picx.dev/p/REHpgh/image OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning https://picx.dev/p/f3cgDs 2026-06-27 never 0.7 https://picx.dev/p/f3cgDs/image ViQ: Text-Aligned Visual Quantized Representations at Any Resolution https://picx.dev/p/gq84gZ 2026-06-27 never 0.7 https://picx.dev/p/gq84gZ/image DanceOPD: On-Policy Generative Field Distillation https://picx.dev/p/AaCvBy 2026-06-26 never 0.7 https://picx.dev/p/AaCvBy/image Improved Large Language Diffusion Models https://picx.dev/p/tsoDfl 2026-06-26 never 0.7 https://picx.dev/p/tsoDfl/image ShutterMuse: Capture-Time Photography Guidance with MLLMs https://picx.dev/p/OK1QBP 2026-06-26 never 0.7 https://picx.dev/p/OK1QBP/image Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models https://picx.dev/p/h0OvBW 2026-06-26 never 0.7 https://picx.dev/p/h0OvBW/image DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation https://picx.dev/p/yjujMW 2026-06-26 never 0.7 https://picx.dev/p/yjujMW/image Are We Ready For An Agent-Native Memory System? https://picx.dev/p/mIwt7U 2026-06-25 never 0.7 https://picx.dev/p/mIwt7U/image MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management https://picx.dev/p/g53rfs 2026-06-25 never 0.7 https://picx.dev/p/g53rfs/image MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization https://picx.dev/p/fuFjtc 2026-06-25 never 0.7 https://picx.dev/p/fuFjtc/image NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers? https://picx.dev/p/QVnrsq 2026-06-25 never 0.7 https://picx.dev/p/QVnrsq/image Qwen-AgentWorld: Language World Models for General Agents https://picx.dev/p/iPGPs1 2026-06-24 never 0.7 https://picx.dev/p/iPGPs1/image World Action Models: A Survey https://picx.dev/p/1PgpkB 2026-06-24 never 0.7 https://picx.dev/p/1PgpkB/image KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking https://picx.dev/p/LuXu9J 2026-06-24 never 0.7 https://picx.dev/p/LuXu9J/image Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention https://picx.dev/p/zCKnQc 2026-06-24 never 0.7 https://picx.dev/p/zCKnQc/image EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions https://picx.dev/p/e6D28X 2026-06-24 never 0.7 https://picx.dev/p/e6D28X/image DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams https://picx.dev/p/m23mUu 2026-06-24 never 0.7 https://picx.dev/p/m23mUu/image OpenRath: Session-Centered Runtime State for Agent Systems https://picx.dev/p/Kz7hcE 2026-06-24 never 0.7 https://picx.dev/p/Kz7hcE/image PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems https://picx.dev/p/okfleI 2026-06-23 never 0.7 https://picx.dev/p/okfleI/image GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents https://picx.dev/p/lTaV9g 2026-06-23 never 0.7 https://picx.dev/p/lTaV9g/image MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision https://picx.dev/p/NvafIj 2026-06-23 never 0.7 https://picx.dev/p/NvafIj/image PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models https://picx.dev/p/BJ8QML 2026-06-20 never 0.7 https://picx.dev/p/BJ8QML/image Playful Agentic Robot Learning https://picx.dev/p/xA5q96 2026-06-20 never 0.7 https://picx.dev/p/xA5q96/image DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects https://picx.dev/p/nHYYy2 2026-06-20 never 0.7 https://picx.dev/p/nHYYy2/image Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance https://picx.dev/p/Fw36ML 2026-06-19 never 0.7 https://picx.dev/p/Fw36ML/image Kairos: A Native World Model Stack for Physical AI https://picx.dev/p/uRJkOA 2026-06-19 never 0.7 https://picx.dev/p/uRJkOA/image MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction https://picx.dev/p/66IC4G 2026-06-19 never 0.7 https://picx.dev/p/66IC4G/image Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games https://picx.dev/p/PlXZnO 2026-06-18 never 0.7 https://picx.dev/p/PlXZnO/image LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching https://picx.dev/p/DKJUNY 2026-06-18 never 0.7 https://picx.dev/p/DKJUNY/image Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients https://picx.dev/p/X032bD 2026-06-18 never 0.7 https://picx.dev/p/X032bD/image LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling https://picx.dev/p/tFHsWH 2026-06-17 never 0.7 https://picx.dev/p/tFHsWH/image VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models https://picx.dev/p/XxO7Wq 2026-06-17 never 0.7 https://picx.dev/p/XxO7Wq/image FastContext: Training Efficient Repository Explorer for Coding Agents https://picx.dev/p/hMMQnj 2026-06-17 never 0.7 https://picx.dev/p/hMMQnj/image DreamX-World 1.0: A General-Purpose Interactive World Model https://picx.dev/p/SGTUrO 2026-06-17 never 0.7 https://picx.dev/p/SGTUrO/image Geometric Action Model for Robot Policy Learning https://picx.dev/p/8fd3Y5 2026-06-17 never 0.7 https://picx.dev/p/8fd3Y5/image Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories https://picx.dev/p/4gaI78 2026-06-17 never 0.7 https://picx.dev/p/lsdUbq 2026-06-16 never 0.7 https://picx.dev/p/lsdUbq/image Rethinking RAG in Long Videos: What to Retrieve and How to Use It? https://picx.dev/p/00m7IM 2026-06-16 never 0.7 https://picx.dev/p/00m7IM/image HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry https://picx.dev/p/nJIGk4 2026-06-16 never 0.7 https://picx.dev/p/nJIGk4/image Orchestra-o1: Omnimodal Agent Orchestration https://picx.dev/p/ZL2lmL 2026-06-16 never 0.7 https://picx.dev/p/ZL2lmL/image From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI https://picx.dev/p/6TIfTm 2026-06-16 never 0.7 https://picx.dev/p/6TIfTm/image Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents https://picx.dev/p/lQ63yn 2026-06-16 never 0.7 https://picx.dev/p/lQ63yn/image APPO: Agentic Procedural Policy Optimization https://picx.dev/p/OtVz9E 2026-06-16 never 0.7 https://picx.dev/p/OtVz9E/image OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data https://picx.dev/p/fSepxc 2026-06-13 never 0.7 https://picx.dev/p/fSepxc/image LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories https://picx.dev/p/dTLhV9 2026-06-13 never 0.7 https://picx.dev/p/dTLhV9/image WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces https://picx.dev/p/jQTYaq 2026-06-13 never 0.7 https://picx.dev/p/jQTYaq/image MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling https://picx.dev/p/H41geU 2026-06-13 never 0.7 https://picx.dev/p/H41geU/image Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? https://picx.dev/p/820tML 2026-06-13 never 0.7 https://picx.dev/p/820tML/image FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents https://picx.dev/p/lE4y4J 2026-06-13 never 0.7 https://picx.dev/p/lE4y4J/image InterleaveThinker: Reinforcing Agentic Interleaved Generation https://picx.dev/p/uC7Rna 2026-06-13 never 0.7 https://picx.dev/p/uC7Rna/image MiniMax Sparse Attention https://picx.dev/p/O4Jah9 2026-06-13 never 0.7 https://picx.dev/p/O4Jah9/image SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning https://picx.dev/p/9C7QqQ 2026-06-13 never 0.7 https://picx.dev/p/9C7QqQ/image EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments https://picx.dev/p/zScBvE 2026-06-12 never 0.7 https://picx.dev/p/zScBvE/image TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders https://picx.dev/p/w8aY56 2026-06-12 never 0.7 https://picx.dev/p/w8aY56/image Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions https://picx.dev/p/xr83Ku 2026-06-12 never 0.7 https://picx.dev/p/N6hho4 2026-06-12 never 0.7 https://picx.dev/p/YxhwL0 2026-06-12 never 0.7 https://picx.dev/p/YxhwL0/image Toward Generalist Autonomous Research via Hypothesis-Tree Refinement https://picx.dev/p/leCPAG 2026-06-12 never 0.7 https://picx.dev/p/leCPAG/image Redesign Mixture-of-Experts Routers with Manifold Power Iteration https://picx.dev/p/yW29jv 2026-06-11 never 0.7 https://picx.dev/p/yW29jv/image SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning https://picx.dev/p/Z2gk0a 2026-06-11 never 0.7 https://picx.dev/p/Z2gk0a/image Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models https://picx.dev/p/sQDXZZ 2026-06-11 never 0.7 https://picx.dev/p/sQDXZZ/image MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism https://picx.dev/p/wEkgGz 2026-06-11 never 0.7 https://picx.dev/p/wEkgGz/image Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning https://picx.dev/p/aFopgw 2026-06-11 never 0.7 https://picx.dev/p/aFopgw/image SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research https://picx.dev/p/dD5Nlo 2026-06-11 never 0.7 https://picx.dev/p/dD5Nlo/image Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts https://picx.dev/p/1zruZL 2026-06-11 never 0.7 https://picx.dev/p/1zruZL/image Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution https://picx.dev/p/r5JNLR 2026-06-11 never 0.7 https://picx.dev/p/r5JNLR/image Kwai Keye-VL-2.0 Technical Report https://picx.dev/p/n3hp3C 2026-06-11 never 0.7 https://picx.dev/p/n3hp3C/image ABot-Earth 0.5: Generative 3D Earth Model https://picx.dev/p/TgZ67v 2026-06-10 never 0.7 https://picx.dev/p/TgZ67v/image Human Psychometric Questionnaires Mischaracterize LLM Behavior https://picx.dev/p/mIBc4g 2026-06-10 never 0.7 https://picx.dev/p/mIBc4g/image Latent Spatial Memory for Video World Models https://picx.dev/p/q6d00h 2026-06-10 never 0.7 https://picx.dev/p/q6d00h/image On the Geometry of On-Policy Distillation https://picx.dev/p/1rxyDH 2026-06-10 never 0.7 https://picx.dev/p/1rxyDH/image Agents' Last Exam https://picx.dev/p/MvFdES 2026-06-10 never 0.7 https://picx.dev/p/MvFdES/image SWE-Explore: Benchmarking How Coding Agents Explore Repositories https://picx.dev/p/jsi1mM 2026-06-09 never 0.7 https://picx.dev/p/jsi1mM/image MMAE: A Massive Multitask Audio Editing Benchmark https://picx.dev/p/3kbvgf 2026-06-09 never 0.7 https://picx.dev/p/3kbvgf/image GENEB: Why Genomic Models Are Hard to Compare https://picx.dev/p/0cc720 2026-06-09 never 0.7 https://picx.dev/p/0cc720/image SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations https://picx.dev/p/DOV2f2 2026-06-09 never 0.7 https://picx.dev/p/DOV2f2/image Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings https://picx.dev/p/tefQLH 2026-06-06 never 0.7 https://picx.dev/p/tefQLH/image VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding https://picx.dev/p/Dosxe1 2026-06-06 never 0.7 https://picx.dev/p/Dosxe1/image AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints https://picx.dev/p/tZMaHK 2026-06-06 never 0.7 https://picx.dev/p/tZMaHK/image TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration https://picx.dev/p/JKnpki 2026-06-06 never 0.7 https://picx.dev/p/JKnpki/image ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? https://picx.dev/p/Th4nbG 2026-06-06 never 0.7 https://picx.dev/p/Th4nbG/image Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution https://picx.dev/p/Q4VhEf 2026-06-05 never 0.7 https://picx.dev/p/Q4VhEf/image Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning https://picx.dev/p/fh0Jks 2026-06-05 never 0.7 https://picx.dev/p/fh0Jks/image Audio Interaction Model https://picx.dev/p/PvGXJ3 2026-06-04 never 0.7 https://picx.dev/p/PvGXJ3/image Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking https://picx.dev/p/LM5K4D 2026-06-04 never 0.7 https://picx.dev/p/LM5K4D/image Trust Region On-Policy Distillation https://picx.dev/p/QDxUcx 2026-06-04 never 0.7 https://picx.dev/p/QDxUcx/image From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain https://picx.dev/p/fFFqK6 2026-06-04 never 0.7 https://picx.dev/p/fFFqK6/image OCC-RAG: Optimal Cognitive Core for Faithful Question Answering https://picx.dev/p/hEFFBn 2026-06-03 never 0.7 https://picx.dev/p/hEFFBn/image Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses https://picx.dev/p/7kT8Mh 2026-06-03 never 0.7 https://picx.dev/p/7kT8Mh/image K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts https://picx.dev/p/Oh7v9F 2026-06-03 never 0.7 https://picx.dev/p/Oh7v9F/image A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks https://picx.dev/p/Fvs5rW 2026-06-03 never 0.7 https://picx.dev/p/Fvs5rW/image On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters https://picx.dev/p/1QkNH0 2026-06-03 never 0.7 https://picx.dev/p/1QkNH0/image Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs https://picx.dev/p/Af3c5y 2026-06-02 never 0.7 https://picx.dev/p/Af3c5y/image GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration https://picx.dev/p/hq54Fr 2026-06-02 never 0.7 https://picx.dev/p/hq54Fr/image Function2Scene: 3D Indoor Scene Layout from Functional Specifications https://picx.dev/p/OFpUe0 2026-06-02 never 0.7 https://picx.dev/p/OFpUe0/image LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards https://picx.dev/p/K4SKZk 2026-06-02 never 0.7 https://picx.dev/p/K4SKZk/image Mellum2 Technical Report https://picx.dev/p/CGOUjv 2026-06-02 never 0.7 https://picx.dev/p/CGOUjv/image SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue https://picx.dev/p/RTC7qE 2026-06-02 never 0.7 https://picx.dev/p/RTC7qE/image Representation Forcing for Bottleneck-Free Unified Multimodal Models https://picx.dev/p/4ppBup 2026-06-02 never 0.7 https://picx.dev/p/4ppBup/image Trust-Region Behavior Blending for On-Policy Distillation https://picx.dev/p/60C3tX 2026-06-02 never 0.7 https://picx.dev/p/60C3tX/image COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation https://picx.dev/p/S71Ugv 2026-06-02 never 0.7 https://picx.dev/p/S71Ugv/image GrepSeek: Training Search Agents for Direct Corpus Interaction https://picx.dev/p/v9JGPh 2026-05-30 never 0.7 https://picx.dev/p/v9JGPh/image YoCausal: How Far is Video Generation from World Model? A Causality Perspective https://picx.dev/p/LbSMNB 2026-05-30 never 0.7 https://picx.dev/p/LbSMNB/image minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models https://picx.dev/p/RsY4ur 2026-05-30 never 0.7 https://picx.dev/p/RsY4ur/image CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation https://picx.dev/p/6d4Ot0 2026-05-30 never 0.7 https://picx.dev/p/6d4Ot0/image OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources https://picx.dev/p/3VhQo0 2026-05-30 never 0.7 https://picx.dev/p/3VhQo0/image Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments https://picx.dev/p/oFi4Z3 2026-05-30 never 0.7 https://picx.dev/p/oFi4Z3/image AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security https://picx.dev/p/jOcZU0 2026-05-29 never 0.7 https://picx.dev/p/jOcZU0/image Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents https://picx.dev/p/NByKN6 2026-05-29 never 0.7 https://picx.dev/p/NByKN6/image MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems https://picx.dev/p/JTC0iO 2026-05-29 never 0.7 https://picx.dev/p/JTC0iO/image GEM: Generative Supervision Helps Embodied Intelligence https://picx.dev/p/ZCaXax 2026-05-29 never 0.7 https://picx.dev/p/ZCaXax/image DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes https://picx.dev/p/SYEyUO 2026-05-29 never 0.7 https://picx.dev/p/SYEyUO/image ResearchMath-14K: Scaling Research-Level Mathematics via Agents https://picx.dev/p/MI4xp5 2026-05-29 never 0.7 https://picx.dev/p/MI4xp5/image Self-Improving Language Models with Bidirectional Evolutionary Search https://picx.dev/p/tdni88 2026-05-29 never 0.7 https://picx.dev/p/tdni88/image From Pixels to Words – Towards Native One-Vision Models at Scale https://picx.dev/p/WiTJx2 2026-05-29 never 0.7 https://picx.dev/p/WiTJx2/image Agent Explorative Policy Optimization for Multimodal Agentic Reasoning https://picx.dev/p/MQP1Jl 2026-05-29 never 0.7 https://picx.dev/p/MQP1Jl/image ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation https://picx.dev/p/JtKaGD 2026-05-29 never 0.7 https://picx.dev/p/JtKaGD/image Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players https://picx.dev/p/Q15j91 2026-05-28 never 0.7 https://picx.dev/p/Q15j91/image D^2-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing https://picx.dev/p/eaacWz 2026-05-28 never 0.7 https://picx.dev/p/eaacWz/image LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV https://picx.dev/p/kTVxXu 2026-05-28 never 0.7 https://picx.dev/p/kTVxXu/image Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction https://picx.dev/p/QlC7RW 2026-05-28 never 0.7 https://picx.dev/p/QlC7RW/image MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research https://picx.dev/p/3hP1Zy 2026-05-28 never 0.7 https://picx.dev/p/3hP1Zy/image SpatialBench: Is Your Spatial Foundation Model an All-Round Player? https://picx.dev/p/cF72Dm 2026-05-28 never 0.7 https://picx.dev/p/cF72Dm/image EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation https://picx.dev/p/9Gh56k 2026-05-28 never 0.7 https://picx.dev/p/9Gh56k/image LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding https://picx.dev/p/uFkqWi 2026-05-27 never 0.7 https://picx.dev/p/uFkqWi/image Toward Native Multimodal Modeling: A Roadmap https://picx.dev/p/AXuQed 2026-05-27 never 0.7 https://picx.dev/p/AXuQed/image TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction https://picx.dev/p/uUxdDJ 2026-05-27 never 0.7 https://picx.dev/p/uUxdDJ/image Foundation Protocol: A Coordination Layer for Agentic Society https://picx.dev/p/UZ13Lj 2026-05-27 never 0.7 https://picx.dev/p/UZ13Lj/image Macaron-A2UI: A Model for Generative UI in Personal Agents https://picx.dev/p/5G7Me4 2026-05-27 never 0.7 https://picx.dev/p/5G7Me4/image WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation https://picx.dev/p/0I0xqK 2026-05-27 never 0.7 https://picx.dev/p/0I0xqK/image DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning https://picx.dev/p/UIQul2 2026-05-26 never 0.7 https://picx.dev/p/UIQul2/image StepAudio 2.5 Technical Report https://picx.dev/p/37AOru 2026-05-26 never 0.7 https://picx.dev/p/37AOru/image SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research https://picx.dev/p/7T54aH 2026-05-26 never 0.7 https://picx.dev/p/7T54aH/image Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models https://picx.dev/p/8eN0Q4 2026-05-26 never 0.7 https://picx.dev/p/8eN0Q4/image Rethinking Cross-Layer Information Routing in Diffusion Transformers https://picx.dev/p/pUAERe 2026-05-26 never 0.7 https://picx.dev/p/pUAERe/image SkillOpt: Executive Strategy for Self-Evolving Agent Skills https://picx.dev/p/kolEKr 2026-05-22 never 0.7 https://picx.dev/p/kolEKr/image Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos https://picx.dev/p/RZPdPG 2026-05-22 never 0.7 https://picx.dev/p/RZPdPG/image Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining https://picx.dev/p/7tRiuP 2026-05-22 never 0.7 https://picx.dev/p/7tRiuP/image Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation https://picx.dev/p/Ss36kd 2026-05-21 never 0.7 https://picx.dev/p/Ss36kd/image CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition https://picx.dev/p/zzIFLz 2026-05-21 never 0.7 https://picx.dev/p/zzIFLz/image EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL https://picx.dev/p/Pzlmwc 2026-05-21 never 0.7 https://picx.dev/p/Pzlmwc/image Process Rewards with Learned Reliability https://picx.dev/p/AAfOO5 2026-05-21 never 0.7 https://picx.dev/p/AAfOO5/image AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration https://picx.dev/p/2ygHum 2026-05-21 never 0.7 https://picx.dev/p/2ygHum/image OpenComputer: Verifiable Software Worlds for Computer-Use Agents https://picx.dev/p/2Wnv5s 2026-05-21 never 0.7 https://picx.dev/p/2Wnv5s/image GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment https://picx.dev/p/51xwcx 2026-05-21 never 0.7 https://picx.dev/p/51xwcx/image Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information https://picx.dev/p/HT21wH 2026-05-21 never 0.7 https://picx.dev/p/HT21wH/image Active Learners as Efficient PRP Rerankers https://picx.dev/p/RG6ESG 2026-05-21 never 0.7 https://picx.dev/p/RG6ESG/image When Vision Speaks for Sound https://picx.dev/p/fXE8EZ 2026-05-20 never 0.7 https://picx.dev/p/fXE8EZ/image KVPO: ODE-Native GRPO for Autoregressive Video Alignment via KV Semantic Exploration https://picx.dev/p/fMpWUW 2026-05-20 never 0.7 https://picx.dev/p/fMpWUW/image Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis https://picx.dev/p/S5euJl 2026-05-20 never 0.7 https://picx.dev/p/S5euJl/image CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows? https://picx.dev/p/SrcGIf 2026-05-20 never 0.7 https://picx.dev/p/SrcGIf/image AI for Auto-Research: Roadmap User Guide https://picx.dev/p/FYBIdL 2026-05-20 never 0.7 https://picx.dev/p/FYBIdL/image Lance: Unified Multimodal Modeling by Multi-Task Synergy https://picx.dev/p/l0SHvu 2026-05-20 never 0.7 https://picx.dev/p/l0SHvu/image LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation https://picx.dev/p/LVSdFd 2026-05-20 never 0.7 https://picx.dev/p/LVSdFd/image SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution https://picx.dev/p/wcR3p2 2026-05-20 never 0.7 https://picx.dev/p/wcR3p2/image Code as Agent Harness https://picx.dev/p/pKNI6t 2026-05-19 never 0.7 https://picx.dev/p/pKNI6t/image InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation https://picx.dev/p/Qls4MU 2026-05-19 never 0.7 https://picx.dev/p/Qls4MU/image Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding https://picx.dev/p/bR2f20 2026-05-19 never 0.7 https://picx.dev/p/bR2f20/image DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo https://picx.dev/p/Ys9QeQ 2026-05-19 never 0.7 https://picx.dev/p/Ys9QeQ/image Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation https://picx.dev/p/Xkxh2j 2026-05-19 never 0.7 https://picx.dev/p/Xkxh2j/image FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization https://picx.dev/p/R7xs3T 2026-05-19 never 0.7 https://picx.dev/p/R7xs3T/image MMSkills: Towards Multimodal Skills for General Visual Agents https://picx.dev/p/NQbxs1 2026-05-19 never 0.7 https://picx.dev/p/NQbxs1/image PhysBrain 1.0 Technical Report https://picx.dev/p/E2QCMi 2026-05-19 never 0.7 https://picx.dev/p/E2QCMi/image CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence https://picx.dev/p/zvUtLQ 2026-05-16 never 0.7 https://picx.dev/p/zvUtLQ/image Self-Distilled Agentic Reinforcement Learning https://picx.dev/p/viK3nz 2026-05-16 never 0.7 https://picx.dev/p/viK3nz/image Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation https://picx.dev/p/hVhxN9 2026-05-16 never 0.7 https://picx.dev/p/hVhxN9/image Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling https://picx.dev/p/qdKwc6 2026-05-15 never 0.7 https://picx.dev/p/qdKwc6/image Edit-Compass EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling https://picx.dev/p/eObMI7 2026-05-15 never 0.7 https://picx.dev/p/eObMI7/image Qwen-Image-VAE-2.0 Technical Report https://picx.dev/p/PL3DEs 2026-05-15 never 0.7 https://picx.dev/p/PL3DEs/image Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling https://picx.dev/p/JHlcH9 2026-05-15 never 0.7 https://picx.dev/p/JHlcH9/image Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context https://picx.dev/p/74SAAF 2026-05-15 never 0.7 https://picx.dev/p/74SAAF/image AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation https://picx.dev/p/Un2IP2 2026-05-15 never 0.7 https://picx.dev/p/Un2IP2/image MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image https://picx.dev/p/kRLtjl 2026-05-15 never 0.7 https://picx.dev/p/kRLtjl/image MinT: Managed Infrastructure for Training and Serving Millions of LLMs https://picx.dev/p/JHC970 2026-05-14 never 0.7 https://picx.dev/p/JHC970/image World Action Models: The Next Frontier in Embodied AI https://picx.dev/p/3yg2yo 2026-05-14 never 0.7 https://picx.dev/p/UZqgjW 2026-05-14 never 0.7 https://picx.dev/p/UZqgjW/image RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards https://picx.dev/p/uk5K4a 2026-05-14 never 0.7 https://picx.dev/p/uk5K4a/image δ-mem: Efficient Online Memory for Large Language Models https://picx.dev/p/5LUZuj 2026-05-14 never 0.7 https://picx.dev/p/5LUZuj/image SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture https://picx.dev/p/m7wbyl 2026-05-14 never 0.7 https://picx.dev/p/m7wbyl/image MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents https://picx.dev/p/8pdSu9 2026-05-13 never 0.7 https://picx.dev/p/8pdSu9/image TMAS: Scaling Test-Time Compute via Multi-Agent Synergy https://picx.dev/p/4jW4rO 2026-05-13 never 0.7 https://picx.dev/p/4jW4rO/image CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models https://picx.dev/p/iZlrfz 2026-05-13 never 0.7 https://picx.dev/p/iZlrfz/image Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs https://picx.dev/p/6WrV4D 2026-05-13 never 0.7 https://picx.dev/p/6WrV4D/image Qwen-Image-2.0 Technical Report https://picx.dev/p/1cRHex 2026-05-12 never 0.7 https://picx.dev/p/1cRHex/image Flow-OPD: On-Policy Distillation for Flow Matching Models https://picx.dev/p/rZzfeY 2026-05-12 never 0.7 https://picx.dev/p/rZzfeY/image MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation https://picx.dev/p/xhlqCV 2026-05-12 never 0.7 https://picx.dev/p/xhlqCV/image Mean Mode Screaming: Mean–Variance Split Residuals for 1000-Layer Diffusion Transformers https://picx.dev/p/GJDDle 2026-05-09 never 0.7 https://picx.dev/p/hnsXXL 2026-05-09 never 0.7 https://picx.dev/p/BXusLc 2026-05-09 never 0.7 https://picx.dev/p/BXusLc/image RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation https://picx.dev/p/i41zJY 2026-05-09 never 0.7 https://picx.dev/p/i41zJY/image MiA-Signature: Approximating Global Activation for Long-Context Understanding https://picx.dev/p/4o6F0G 2026-05-09 never 0.7 https://picx.dev/p/4o6F0G/image Continuous Latent Diffusion Language Model https://picx.dev/p/9wJ5C9 2026-05-09 never 0.7 https://picx.dev/p/9wJ5C9/image Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction https://picx.dev/p/xHgSUy 2026-05-09 never 0.7 https://picx.dev/p/xHgSUy/image Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning https://picx.dev/p/yeqYmk 2026-05-08 never 0.7 https://picx.dev/p/yeqYmk/image PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World https://picx.dev/p/bXahf0 2026-05-08 never 0.7 https://picx.dev/p/bXahf0/image HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation https://picx.dev/p/GpQ3lz 2026-05-08 never 0.7 https://picx.dev/p/GpQ3lz/image OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents https://picx.dev/p/qn6FuE 2026-05-08 never 0.7 https://picx.dev/p/qn6FuE/image RLDX-1 Technical Report https://picx.dev/p/0KMZhc 2026-05-08 never 0.7 https://picx.dev/p/0KMZhc/image Stream-T1: Test-Time Scaling for Streaming Video Generation https://picx.dev/p/HJ65Nn 2026-05-08 never 0.7 https://picx.dev/p/HJ65Nn/image Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation https://picx.dev/p/jKiYlA 2026-05-07 never 0.7 https://picx.dev/p/jKiYlA/image Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL https://picx.dev/p/2BDwRu 2026-05-07 never 0.7 https://picx.dev/p/2BDwRu/image OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories https://picx.dev/p/9eeqst 2026-05-07 never 0.7 https://picx.dev/p/9eeqst/image ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration https://picx.dev/p/UMUlA9 2026-05-06 never 0.7 https://picx.dev/p/UMUlA9/image Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling https://picx.dev/p/7aRz0g 2026-05-06 never 0.7 https://picx.dev/p/7aRz0g/image From Context to Skills: Can Language Models Learn from Context Skillfully? https://picx.dev/p/EoZhlX 2026-05-06 never 0.7 https://picx.dev/p/EoZhlX/image MolmoAct2: Action Reasoning Models for Real-world Deployment https://picx.dev/p/DQSCI6 2026-05-05 never 0.7 https://picx.dev/p/DQSCI6/image Map2World: Segment Map Conditioned Text to 3D World Generation https://picx.dev/p/cqLikg 2026-05-05 never 0.7 https://picx.dev/p/cqLikg/image Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction https://picx.dev/p/CUUih8 2026-05-05 never 0.7 https://picx.dev/p/CUUih8/image UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors https://picx.dev/p/GoG2z2 2026-05-02 never 0.7 https://picx.dev/p/GoG2z2/image ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control https://picx.dev/p/ZgM3Uh 2026-05-02 never 0.7 https://picx.dev/p/ZgM3Uh/image Co-Evolving Policy Distillation https://picx.dev/p/iF5ID2 2026-05-02 never 0.7 https://picx.dev/p/iF5ID2/image Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling https://picx.dev/p/DZDopI 2026-05-02 never 0.7 https://picx.dev/p/DZDopI/image Heterogeneous Scientific Foundation Model Collaboration https://picx.dev/p/Zjln2g 2026-05-01 never 0.7 https://picx.dev/p/Zjln2g/image Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models https://picx.dev/p/D2DTJA 2026-05-01 never 0.7 https://picx.dev/p/D2DTJA/image ClawGym: A Scalable Framework for Building Effective Claw Agents https://picx.dev/p/805fLk 2026-05-01 never 0.7 https://picx.dev/p/805fLk/image RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments https://picx.dev/p/KpOCLC 2026-05-01 never 0.7 https://picx.dev/p/KpOCLC/image Large Language Models Explore by Latent Distilling https://picx.dev/p/7cOZ8W 2026-05-01 never 0.7 https://picx.dev/p/7cOZ8W/image GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents https://picx.dev/p/wcII9c 2026-04-30 never 0.7 https://picx.dev/p/wcII9c/image DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios https://picx.dev/p/Cseww3 2026-04-30 never 0.7 https://picx.dev/p/Cseww3/image Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora https://picx.dev/p/qxP2k7 2026-04-30 never 0.7 https://picx.dev/p/qxP2k7/image Recursive Multi-Agent Systems https://picx.dev/p/OBZbDo 2026-04-29 never 0.7 https://picx.dev/p/OBZbDo/image Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms https://picx.dev/p/Yu3zRv 2026-04-29 never 0.7 https://picx.dev/p/Yu3zRv/image Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation https://picx.dev/p/6V2xDQ 2026-04-29 never 0.7 https://picx.dev/p/6V2xDQ/image ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning https://picx.dev/p/TETr2N 2026-04-29 never 0.7 https://picx.dev/p/TETr2N/image World-R1: Reinforcing 3D Constraints for Text-to-Video Generation https://picx.dev/p/9UBSLx 2026-04-29 never 0.7 https://picx.dev/p/9UBSLx/image From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company https://picx.dev/p/18w6ac 2026-04-28 never 0.7 https://picx.dev/p/18w6ac/image DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction https://picx.dev/p/YvzKtg 2026-04-28 never 0.7 https://picx.dev/p/YvzKtg/image Video Analysis and Generation via a Semantic Progress Function https://picx.dev/p/sivzb4 2026-04-28 never 0.7 https://picx.dev/p/sivzb4/image Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond https://picx.dev/p/SabpM3 2026-04-25 never 0.7 https://picx.dev/p/SabpM3/image UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling https://picx.dev/p/sopctd 2026-04-25 never 0.7 https://picx.dev/p/sopctd/image WorldMark: A Unified Benchmark Suite for Interactive Video World Models https://picx.dev/p/Z8f7WW 2026-04-25 never 0.7 https://picx.dev/p/Z8f7WW/image LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics https://picx.dev/p/dywuTg 2026-04-24 never 0.7 https://picx.dev/p/dywuTg/image DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data https://picx.dev/p/BJ5kEH 2026-04-24 never 0.7 https://picx.dev/p/BJ5kEH/image Near-Future Policy Optimization https://picx.dev/p/D5leQk 2026-04-24 never 0.7 https://picx.dev/p/D5leQk/image LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model https://picx.dev/p/npjj0F 2026-04-23 never 0.7 https://picx.dev/p/npjj0F/image AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model https://picx.dev/p/2oOdWI 2026-04-23 never 0.7 https://picx.dev/p/2oOdWI/image AgentSPEX: An Agent SPecification and EXecution Language https://picx.dev/p/31uKmc 2026-04-23 never 0.7 https://picx.dev/p/31uKmc/image CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation https://picx.dev/p/IC9FMq 2026-04-23 never 0.7 https://picx.dev/p/IC9FMq/image Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items https://picx.dev/p/YR8OVg 2026-04-22 never 0.7 https://picx.dev/p/YR8OVg/image EasyVideoR1: Easier RL for Video Understanding https://picx.dev/p/UFJpA8 2026-04-22 never 0.7 https://picx.dev/p/UFJpA8/image MultiWorld: Scalable Multi-Agent Multi-View Video World Models https://picx.dev/p/SFZENs 2026-04-22 never 0.7 https://picx.dev/p/SFZENs/image OpenGame: Open Agentic Coding for Games https://picx.dev/p/iKbI5Y 2026-04-22 never 0.7 https://picx.dev/p/iKbI5Y/image Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation https://picx.dev/p/qCp0G6 2026-04-21 never 0.7 https://picx.dev/p/qCp0G6/image Elucidating the SNR-t Bias of Diffusion Probabilistic Models https://picx.dev/p/EVWC2p 2026-04-18 never 0.7 https://picx.dev/p/EVWC2p/image DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation https://picx.dev/p/aEtb28 2026-04-18 never 0.7 https://picx.dev/p/aEtb28/image RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework https://picx.dev/p/KdRwLR 2026-04-18 never 0.7 https://picx.dev/p/KdRwLR/image HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds https://picx.dev/p/V2U3kD 2026-04-17 never 0.7 https://picx.dev/p/V2U3kD/image OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models https://picx.dev/p/Go4fuT 2026-04-17 never 0.7 https://picx.dev/p/Go4fuT/image SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments https://picx.dev/p/w19jO0 2026-04-17 never 0.7 https://picx.dev/p/w19jO0/image RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time https://picx.dev/p/ogOnLh 2026-04-17 never 0.7 https://picx.dev/p/ogOnLh/image GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents https://picx.dev/p/eEqW50 2026-04-17 never 0.7 https://picx.dev/p/eEqW50/image Seedance 2.0: Advancing Video Generation for World Complexity https://picx.dev/p/d473RJ 2026-04-16 never 0.7 https://picx.dev/p/d473RJ/image Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe https://picx.dev/p/bGjar7 2026-04-16 never 0.7 https://picx.dev/p/bGjar7/image KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance https://picx.dev/p/DLH63Y 2026-04-16 never 0.7 https://picx.dev/p/DLH63Y/image ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents https://picx.dev/p/GIpUP0 2026-04-15 never 0.7 https://picx.dev/p/GIpUP0/image The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping https://picx.dev/p/RCC6hL 2026-04-15 never 0.7 https://picx.dev/p/RCC6hL/image QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation https://picx.dev/p/9baz2Q 2026-04-14 never 0.7 https://picx.dev/p/9baz2Q/image EXAONE 4.5 Technical Report https://picx.dev/p/SAog55 2026-04-14 never 0.7 https://picx.dev/p/SAog55/image Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory https://picx.dev/p/tgv26P 2026-04-14 never 0.7 https://picx.dev/p/tgv26P/image RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details https://picx.dev/p/7qzHO5 2026-04-14 never 0.7 https://picx.dev/p/7qzHO5/image FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios https://picx.dev/p/xqPVhI 2026-04-14 never 0.7 https://picx.dev/p/xqPVhI/image WildDet3D: Scaling Promptable 3D Detection in the Wild https://picx.dev/p/QZZwEg 2026-04-11 never 0.7 https://picx.dev/p/QZZwEg/image ClawBench: Can AI Agents Complete Everyday Online Tasks? https://picx.dev/p/XFnuMQ 2026-04-11 never 0.7 https://picx.dev/p/XFnuMQ/image HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents https://picx.dev/p/INEX4H 2026-04-11 never 0.7 https://picx.dev/p/INEX4H/image SkillClaw: Let Skills Evolve Collectively with Agentic Evolver https://picx.dev/p/sGCJSb 2026-04-10 never 0.7 https://picx.dev/p/sGCJSb/image MARS: Enabling Autoregressive Models Multi-Token Generation https://picx.dev/p/n7MRUx 2026-04-10 never 0.7 https://picx.dev/p/n7MRUx/image RAGEN-2: Reasoning Collapse in Agentic RL https://picx.dev/p/LiWyrW 2026-04-10 never 0.7 https://picx.dev/p/LiWyrW/image Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning https://picx.dev/p/9RuTOH 2026-04-09 never 0.7 https://picx.dev/p/9YZvYR 2026-04-09 never 0.7 https://picx.dev/p/9YZvYR/image GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers https://picx.dev/p/6j7jtQ 2026-04-09 never 0.7 https://picx.dev/p/6j7jtQ/image ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation https://picx.dev/p/hKyM0L 2026-04-09 never 0.7 https://picx.dev/p/hKyM0L/image Learning to Retrieve from Agent Trajectories https://picx.dev/p/Ahl14c 2026-04-09 never 0.7 https://picx.dev/p/Ahl14c/image Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents https://picx.dev/p/haUC9M 2026-04-09 never 0.7 https://picx.dev/p/haUC9M/image Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding https://picx.dev/p/C44hOy 2026-04-08 never 0.7 https://picx.dev/p/C44hOy/image OpenWorldLib: A Unified Codebase and Definition of Advanced World Models https://picx.dev/p/55E32j 2026-04-07 never 0.7 https://picx.dev/p/55E32j/image Token Warping Helps MLLMs Look from Nearby Viewpoints https://picx.dev/p/OJ1g5p 2026-04-07 never 0.7 https://picx.dev/p/OJ1g5p/image A Simple Baseline for Streaming Video Understanding https://picx.dev/p/gZiSWy 2026-04-07 never 0.7 https://picx.dev/p/gZiSWy/image Self-Distilled RLVR https://picx.dev/p/Pl4me1 2026-04-04 never 0.7 https://picx.dev/p/Pl4me1/image DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models https://picx.dev/p/dVW7CX 2026-04-03 never 0.7 https://picx.dev/p/dVW7CX/image Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification https://picx.dev/p/hLWgXD 2026-04-03 never 0.7 https://picx.dev/p/hLWgXD/image ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? https://picx.dev/p/W3aXxu 2026-04-03 never 0.7 https://picx.dev/p/W3aXxu/image MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome https://picx.dev/p/G0Dol7 2026-04-03 never 0.7 https://picx.dev/p/G0Dol7/image Terminal Agents Suffice for Enterprise Automation https://picx.dev/p/tX6lE3 2026-04-03 never 0.7 https://picx.dev/p/tX6lE3/image ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers https://picx.dev/p/QfS53U 2026-04-02 never 0.7 https://picx.dev/p/QfS53U/image Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis https://picx.dev/p/fmvA4y 2026-04-02 never 0.7 https://picx.dev/p/fmvA4y/image VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward https://picx.dev/p/0VsTZH 2026-04-02 never 0.7 https://picx.dev/p/0VsTZH/image GEMS: Agent-Native Multimodal Generation with Memory and Skills https://picx.dev/p/lFw6B6 2026-04-02 never 0.7 https://picx.dev/p/lFw6B6/image Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells https://picx.dev/p/IXOA73 2026-04-02 never 0.7 https://picx.dev/p/IXOA73/image LongCat-Next: Lexicalizing Modalities as Discrete Tokens https://picx.dev/p/91ETu5 2026-04-02 never 0.7 https://picx.dev/p/91ETu5/image CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence https://picx.dev/p/JMTLfB 2026-04-02 never 0.7 https://picx.dev/p/JMTLfB/image FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization https://picx.dev/p/jUlxyZ 2026-04-01 never 0.7 https://picx.dev/p/jUlxyZ/image EpochX: Building the Infrastructure for an Emergent Agent Civilization https://picx.dev/p/G07pwG 2026-04-01 never 0.7 https://picx.dev/p/G07pwG/image Emergent Social Intelligence Risks in Generative Multi-Agent Systems https://picx.dev/p/6nnvNK 2026-04-01 never 0.7 https://picx.dev/p/6nnvNK/image Gen-Searcher: Reinforcing Agentic Search for Image Generation https://picx.dev/p/Is7My2 2026-04-01 never 0.7 https://picx.dev/p/Is7My2/image Towards a Medical AI Scientist https://picx.dev/p/ECxOvh 2026-04-01 never 0.7 https://picx.dev/p/ECxOvh/image TAPS: Task Aware Proposal Distributions for Speculative Sampling https://picx.dev/p/GWktTM 2026-03-31 never 0.7 https://picx.dev/p/GWktTM/image Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills https://picx.dev/p/zGmQhg 2026-03-31 never 0.7 https://picx.dev/p/zGmQhg/image PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference https://picx.dev/p/o0rHL2 2026-03-31 never 0.7 https://picx.dev/p/o0rHL2/image ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling https://picx.dev/p/Tzf6wb 2026-03-31 never 0.7 https://picx.dev/p/Tzf6wb/image Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models https://picx.dev/p/DAlihE 2026-03-27 never 0.7 https://picx.dev/p/DAlihE/image T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search https://picx.dev/p/O077aW 2026-03-27 never 0.7 https://picx.dev/p/O077aW/image EVA: Efficient Reinforcement Learning for End-to-End Video Agent https://picx.dev/p/w0KlWY 2026-03-27 never 0.7 https://picx.dev/p/w0KlWY/image CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents https://picx.dev/p/hDzPUF 2026-03-26 never 0.7 https://picx.dev/p/hDzPUF/image SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM https://picx.dev/p/N27KcW 2026-03-26 never 0.7 https://picx.dev/p/N27KcW/image DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models https://picx.dev/p/LNL2gG 2026-03-26 never 0.7 https://picx.dev/p/oq0RNK 2026-03-26 never 0.7 https://picx.dev/p/oq0RNK/image From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents https://picx.dev/p/Wd2THa 2026-03-26 never 0.7 https://picx.dev/p/Wd2THa/image SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning https://picx.dev/p/ddhwlj 2026-03-26 never 0.7 https://picx.dev/p/ddhwlj/image WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG https://picx.dev/p/X2gOIC 2026-03-26 never 0.7 https://picx.dev/p/X2gOIC/image MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding https://picx.dev/p/4G14qx 2026-03-25 never 0.7 https://picx.dev/p/4G14qx/image F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting https://picx.dev/p/rowoAZ 2026-03-25 never 0.7 https://picx.dev/p/rowoAZ/image Manifold-Aware Exploration for Reinforcement Learning in Video Generation https://picx.dev/p/4qBBJi 2026-03-25 never 0.7 https://picx.dev/p/4qBBJi/image SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning https://picx.dev/p/qFw9aB 2026-03-25 never 0.7 https://picx.dev/p/qFw9aB/image VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding https://picx.dev/p/gKc5EV 2026-03-25 never 0.7 https://picx.dev/p/gKc5EV/image OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis https://picx.dev/p/kJJOVr 2026-03-25 never 0.7 https://picx.dev/p/kJJOVr/image Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs https://picx.dev/p/vGA6be 2026-03-25 never 0.7 https://picx.dev/p/vGA6be/image LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning https://picx.dev/p/IBVfvE 2026-03-25 never 0.7 https://picx.dev/p/IBVfvE/image Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model https://picx.dev/p/aO5bWy 2026-03-25 never 0.7 https://picx.dev/p/JdnaaU 2026-03-24 never 0.7 https://picx.dev/p/JdnaaU/image TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation https://picx.dev/p/lzUWw4 2026-03-24 never 0.7 https://picx.dev/p/lzUWw4/image Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models https://picx.dev/p/5x7KYR 2026-03-24 never 0.7 https://picx.dev/p/5x7KYR/image HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning https://picx.dev/p/IXtC9Y 2026-03-21 never 0.7 https://picx.dev/p/IXtC9Y/image Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer https://picx.dev/p/kMV8T3 2026-03-21 never 0.7 https://picx.dev/p/kMV8T3/image 3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model https://picx.dev/p/0jiBGu 2026-03-21 never 0.7 https://picx.dev/p/0jiBGu/image FASTER: Rethinking Real-Time Flow VLAs https://picx.dev/p/tp7q3m 2026-03-21 never 0.7 https://picx.dev/p/tp7q3m/image SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing https://picx.dev/p/h04hxp 2026-03-21 never 0.7 https://picx.dev/p/h04hxp/image Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding https://picx.dev/p/TpCN66 2026-03-20 never 0.7 https://picx.dev/p/TpCN66/image Alignment Makes Language Models Normative, Not Descriptive https://picx.dev/p/gGZktc 2026-03-20 never 0.7 https://picx.dev/p/gGZktc/image MosaicMem: Hybrid Spatial Memory for Controllable Video World Models https://picx.dev/p/IX5sV5 2026-03-20 never 0.7 https://picx.dev/p/IX5sV5/image Video-CoE: Reinforcing Video Event Prediction via Chain of Events https://picx.dev/p/XJq8uS 2026-03-20 never 0.7 https://picx.dev/p/XJq8uS/image MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild https://picx.dev/p/WBprxB 2026-03-19 never 0.7 https://picx.dev/p/WBprxB/image FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use https://picx.dev/p/vJjlgH 2026-03-19 never 0.7 https://picx.dev/p/vJjlgH/image Online Experiential Learning for Language Models https://picx.dev/p/EWB5ah 2026-03-19 never 0.7 https://picx.dev/p/EWB5ah/image TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas https://picx.dev/p/PDQ9KY 2026-03-19 never 0.7 https://picx.dev/p/PDQ9KY/image WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation https://picx.dev/p/peUlSS 2026-03-19 never 0.7 https://picx.dev/p/peUlSS/image Demystifing Video Reasoning https://picx.dev/p/SaGMN3 2026-03-19 never 0.7 https://picx.dev/p/SaGMN3/image Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation https://picx.dev/p/H9hb20 2026-03-19 never 0.7 https://picx.dev/p/H9hb20/image Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding https://picx.dev/p/JMwJT1 2026-03-19 never 0.7 https://picx.dev/p/JMwJT1/image Qianfan-OCR: A Unified End-to-End Model for Document Intelligence https://picx.dev/p/rF7JoK 2026-03-19 never 0.7 https://picx.dev/p/rF7JoK/image MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification https://picx.dev/p/yJHFpA 2026-03-19 never 0.7 https://picx.dev/p/nFr1nY 2026-03-18 never 0.7 https://picx.dev/p/nFr1nY/image Effective Distillation to Hybrid xLSTM Architectures https://picx.dev/p/7k53tv 2026-03-18 never 0.7 https://picx.dev/p/7k53tv/image Mixture-of-Depths Attention https://picx.dev/p/2znetu 2026-03-18 never 0.7 https://picx.dev/p/2znetu/image Attention Residuals https://picx.dev/p/59ASct 2026-03-18 never 0.7 https://picx.dev/p/59ASct/image HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions https://picx.dev/p/9N6DpJ 2026-03-18 never 0.7 https://picx.dev/p/9N6DpJ/image Grounding World Simulation Models in a Real-World Metropolis https://picx.dev/p/VOPVDD 2026-03-18 never 0.7 https://picx.dev/p/VOPVDD/image EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings https://picx.dev/p/e2EAIc 2026-03-18 never 0.7 https://picx.dev/p/e2EAIc/image OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data https://picx.dev/p/lH0SlD 2026-03-18 never 0.7 https://picx.dev/p/lH0SlD/image AI Can Learn Scientific Taste https://picx.dev/p/WKlmjU 2026-03-17 never 0.7 https://picx.dev/p/WKlmjU/image Can Vision-Language Models Solve the Shell Game? https://picx.dev/p/65lo3w 2026-03-17 never 0.7 https://picx.dev/p/65lo3w/image Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation https://picx.dev/p/zhyxGY 2026-03-17 never 0.7 https://picx.dev/p/zhyxGY/image LMEB: Long-horizon Memory Embedding Benchmark https://picx.dev/p/XEKSPC 2026-03-14 never 0.7 https://picx.dev/p/XEKSPC/image Video-Based Reward Modeling for Computer-Use Agents https://picx.dev/p/N7CvSB 2026-03-14 never 0.7 https://picx.dev/p/N7CvSB/image IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse https://picx.dev/p/LqDjFh 2026-03-14 never 0.7 https://picx.dev/p/LqDjFh/image Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections https://picx.dev/p/iPOrt6 2026-03-14 never 0.7 https://picx.dev/p/iPOrt6/image Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training https://picx.dev/p/KPCD70 2026-03-13 never 0.7 https://picx.dev/p/KPCD70/image LLM2Vec-Gen: Generative Embeddings from Large Language Models https://picx.dev/p/D4Do4z 2026-03-13 never 0.7 https://picx.dev/p/D4Do4z/image Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning https://picx.dev/p/bhLoFu 2026-03-13 never 0.7 https://picx.dev/p/bhLoFu/image Flash-KMeans: Fast and Memory-Efficient Exact K-Means https://picx.dev/p/DIAVmN 2026-03-13 never 0.7 https://picx.dev/p/DIAVmN/image OpenClaw-RL: Train Any Agent Simply by Talking https://picx.dev/p/R71d9g 2026-03-11 never 0.7 https://picx.dev/p/R71d9g/image CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation https://picx.dev/p/04P8EM 2026-03-11 never 0.7 https://picx.dev/p/04P8EM/image CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing https://picx.dev/p/lNKJat 2026-03-11 never 0.7 https://picx.dev/p/lNKJat/image Believe Your Model: Distribution-Guided Confidence Calibration https://picx.dev/p/ylogZK 2026-03-11 never 0.7 https://picx.dev/p/ylogZK/image How Far Can Unsupervised RLVR Scale LLM Training? https://picx.dev/p/jJmbNY 2026-03-11 never 0.7 https://picx.dev/p/jJmbNY/image LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory https://picx.dev/p/yhZFOZ 2026-03-11 never 0.7 https://picx.dev/p/yhZFOZ/image Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence https://picx.dev/p/zjiwxd 2026-03-11 never 0.7 https://picx.dev/p/zjiwxd/image Lost in Stories: Consistency Bugs in Long Story Generation by LLMs https://picx.dev/p/88HQe9 2026-03-10 never 0.7 https://picx.dev/p/88HQe9/image WildActor: Unconstrained Identity-Preserving Video Generation https://picx.dev/p/lTghMa 2026-03-10 never 0.7 https://picx.dev/p/lTghMa/image Progressive Residual Warmup for Language Model Pretraining https://picx.dev/p/AnZY8h 2026-03-10 never 0.7 https://picx.dev/p/AnZY8h/image Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model https://picx.dev/p/FX89FO 2026-03-10 never 0.7 https://picx.dev/p/FX89FO/image BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning https://picx.dev/p/TbL4AE 2026-03-10 never 0.7 https://picx.dev/p/TbL4AE/image Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders https://picx.dev/p/OJrD9p 2026-03-09 never 0.7 https://picx.dev/p/OJrD9p/image RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies https://picx.dev/p/AjIgTc 2026-03-09 never 0.7 https://picx.dev/p/AjIgTc/image Reasoning Models Struggle to Control their Chains of Thought https://picx.dev/p/Yrcy64 2026-03-07 never 0.7 https://picx.dev/p/Yrcy64/image Training language models to follow instructions with human feedback https://picx.dev/p/nBoBhO 2026-03-07 never 0.7 https://picx.dev/p/nBoBhO/image Deep Residual Learning for Image Recognition https://picx.dev/p/7rYbgf 2026-03-07 never 0.7 https://picx.dev/p/7rYbgf/image DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning https://picx.dev/p/A89PJ4 2026-03-07 never 0.7 https://picx.dev/p/A89PJ4/image Scaling Laws for Neural Language Models https://picx.dev/p/0gc36Q 2026-03-07 never 0.7 https://picx.dev/p/0gc36Q/image An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale https://picx.dev/p/1pZt28 2026-03-07 never 0.7 https://picx.dev/p/1pZt28/image Language Models are Few-Shot Learners https://picx.dev/p/YHaWrF 2026-03-07 never 0.7 https://picx.dev/p/YHaWrF/image BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding https://picx.dev/p/X7eYGU 2026-03-07 never 0.7 https://picx.dev/p/X7eYGU/image Attention Is All You Need https://picx.dev/gallery/d/scaling-training/2 2026-08-22 monthly 0.6 https://picx.dev/gallery/d/moe/2 2026-08-22 monthly 0.6 https://picx.dev/gallery/d/efficient-attention/2 2026-08-22 monthly 0.6 https://picx.dev/gallery/d/self-improvement/2 2026-08-22 monthly 0.6 https://picx.dev/gallery/d/coding-agent/2 2026-08-22 monthly 0.6 https://picx.dev/gallery/d/pretrain-data/2 2026-08-22 monthly 0.6 https://picx.dev/gallery/d/formal-math/2 2026-08-22 monthly 0.6 https://picx.dev/gallery/d/self-improvement/1 2026-08-18 monthly 0.6 https://picx.dev/gallery/d/pretrain-data/1 2026-08-18 monthly 0.6 https://picx.dev/gallery/d/scaling-training/1 2026-08-18 monthly 0.6 https://picx.dev/gallery/d/moe/1 2026-08-18 monthly 0.6 https://picx.dev/gallery/d/efficient-attention/1 2026-08-18 monthly 0.6 https://picx.dev/gallery/d/formal-math/1 2026-08-18 monthly 0.6 https://picx.dev/gallery/d/coding-agent/1 2026-08-18 monthly 0.6 https://picx.dev/news/e2ZogF 2026-08-24 daily 0.6 https://picx.dev/news/J1No4e 2026-08-24 daily 0.6 https://picx.dev/news/rXYjGF 2026-08-24 daily 0.6 https://picx.dev/news/ECtblx 2026-08-24 daily 0.6 https://picx.dev/news/cYfSG2 2026-08-24 daily 0.6 https://picx.dev/news/oL6VkO 2026-08-24 daily 0.6 https://picx.dev/news/OFeY5d 2026-08-24 daily 0.6 https://picx.dev/news/ytVLeX 2026-08-24 daily 0.6 https://picx.dev/news/lIQbFK 2026-08-24 daily 0.6 https://picx.dev/news/aoGfH2 2026-08-24 daily 0.6 https://picx.dev/news/KcbRj7 2026-08-24 daily 0.6 https://picx.dev/news/6V2ier 2026-08-24 daily 0.6 https://picx.dev/news/hd7sB4 2026-08-24 daily 0.6 https://picx.dev/news/WCs5q3 2026-08-23 daily 0.6 https://picx.dev/news/1zQ1yz 2026-08-23 daily 0.6 https://picx.dev/news/7DS60Z 2026-08-24 daily 0.6 https://picx.dev/news/IePGs1 2026-08-23 daily 0.6 https://picx.dev/news/jt3VZj 2026-08-23 daily 0.6 https://picx.dev/news/lpQFRG 2026-08-23 daily 0.6 https://picx.dev/news/1ni4JE 2026-08-23 daily 0.6 https://picx.dev/news/dIeYJ5 2026-08-23 daily 0.6 https://picx.dev/news/H5UO5k 2026-08-23 daily 0.6 https://picx.dev/news/xzIQpX 2026-08-23 daily 0.6 https://picx.dev/news/sy9aRc 2026-08-22 daily 0.6 https://picx.dev/news/H3Y6yG 2026-08-24 daily 0.6 https://picx.dev/news/qnNm7u 2026-08-23 daily 0.6 https://picx.dev/news/KGFqgN 2026-08-23 daily 0.6 https://picx.dev/news/Qyr8J6 2026-08-23 daily 0.6 https://picx.dev/news/B8pKYU 2026-08-22 daily 0.6 https://picx.dev/news/GeNAi2 2026-08-22 daily 0.6 https://picx.dev/news/qqZ3PX 2026-08-23 daily 0.6 https://picx.dev/news/616T89 2026-08-22 daily 0.6 https://picx.dev/news/M7mTuJ 2026-08-22 daily 0.6 https://picx.dev/news/PMGhnu 2026-08-22 daily 0.6 https://picx.dev/news/N8RWo2 2026-08-21 daily 0.6 https://picx.dev/news/zfBekF 2026-08-22 daily 0.6 https://picx.dev/news/I0NqJU 2026-08-21 daily 0.6 https://picx.dev/news/hetkcP 2026-08-22 daily 0.6 https://picx.dev/news/dqpC03 2026-08-21 daily 0.6 https://picx.dev/news/5dXzBZ 2026-08-21 daily 0.6 https://picx.dev/news/Fid1AD 2026-08-21 daily 0.6 https://picx.dev/news/2rrcWK 2026-08-21 daily 0.6 https://picx.dev/news/LLjaXk 2026-08-21 daily 0.6 https://picx.dev/news/QtQpPI 2026-08-21 daily 0.6 https://picx.dev/news/2wfme2 2026-08-21 daily 0.6 https://picx.dev/news/sloFD8 2026-08-20 daily 0.6 https://picx.dev/news/CE9CBo 2026-08-23 daily 0.6 https://picx.dev/news/siZ0fd 2026-08-22 daily 0.6 https://picx.dev/news/UER4dW 2026-08-20 daily 0.6 https://picx.dev/news/YPTdD8 2026-08-20 daily 0.6 https://picx.dev/news/acJhvD 2026-08-21 daily 0.6 https://picx.dev/news/DPYBld 2026-08-22 daily 0.6 https://picx.dev/news/vijtVJ 2026-08-20 daily 0.6 https://picx.dev/news/o7qjzj 2026-08-20 daily 0.6 https://picx.dev/news/TV8wj5 2026-08-20 daily 0.6 https://picx.dev/news/7z4tKe 2026-08-20 daily 0.6 https://picx.dev/news/6aqWna 2026-08-20 daily 0.6 https://picx.dev/news/ItS7Em 2026-08-20 daily 0.6 https://picx.dev/news/2weM9c 2026-08-21 daily 0.6 https://picx.dev/news/pqe2jJ 2026-08-20 daily 0.6 https://picx.dev/news/ov7MQT 2026-08-21 daily 0.6 https://picx.dev/news/uuxKAX 2026-08-20 daily 0.6 https://picx.dev/news/0yQKZQ 2026-08-20 daily 0.6 https://picx.dev/news/zk6Pfu 2026-08-19 daily 0.6 https://picx.dev/news/62waxJ 2026-08-20 daily 0.6 https://picx.dev/news/IZZPOj 2026-08-20 daily 0.6 https://picx.dev/news/AIMOrH 2026-08-20 daily 0.6 https://picx.dev/news/m6kWTS 2026-08-20 daily 0.6 https://picx.dev/news/hPZ5Oq 2026-08-20 daily 0.6 https://picx.dev/news/5LP9E1 2026-08-20 daily 0.6 https://picx.dev/news/0hK27u 2026-08-20 daily 0.6 https://picx.dev/news/Rht87a 2026-08-20 daily 0.6 https://picx.dev/news/H0fAKT 2026-08-19 daily 0.6 https://picx.dev/news/xUw2fH 2026-08-19 daily 0.6 https://picx.dev/news/xvX2dD 2026-08-20 daily 0.6 https://picx.dev/news/2wHjrE 2026-08-19 daily 0.6 https://picx.dev/news/59jE8y 2026-08-19 daily 0.6 https://picx.dev/news/gygbEV 2026-08-19 daily 0.6 https://picx.dev/news/NY1kDF 2026-08-19 daily 0.6 https://picx.dev/news/WSrXxE 2026-08-20 daily 0.6 https://picx.dev/news/fxVCF2 2026-08-19 daily 0.6 https://picx.dev/news/b0VhHu 2026-08-19 daily 0.6 https://picx.dev/news/zPRbKA 2026-08-19 daily 0.6 https://picx.dev/news/48lTYO 2026-08-19 daily 0.6 https://picx.dev/news/OxzkGy 2026-08-19 daily 0.6 https://picx.dev/news/4FUoHM 2026-08-21 daily 0.6 https://picx.dev/news/kV3uTx 2026-08-21 daily 0.6 https://picx.dev/news/uSlURZ 2026-08-20 daily 0.6 https://picx.dev/news/YgQ2Qk 2026-08-18 daily 0.6 https://picx.dev/news/DpOiKS 2026-08-18 daily 0.6 https://picx.dev/news/zGS67A 2026-08-21 daily 0.6 https://picx.dev/news/zA5xze 2026-08-20 daily 0.6 https://picx.dev/news/7ZUJyw 2026-08-18 daily 0.6 https://picx.dev/news/i3Qkkl 2026-08-19 daily 0.6 https://picx.dev/news/zSUgY0 2026-08-20 daily 0.6 https://picx.dev/news/0V7ZoM 2026-08-18 daily 0.6 https://picx.dev/news/ISEadP 2026-08-18 daily 0.6 https://picx.dev/news/q3nFHh 2026-08-20 daily 0.6 https://picx.dev/news/pI5gWs 2026-08-20 daily 0.6 https://picx.dev/news/T2PZ7J 2026-08-20 daily 0.6 https://picx.dev/news/u3x8V6 2026-08-20 daily 0.6 https://picx.dev/news/fwJMFn 2026-08-20 daily 0.6 https://picx.dev/news/MhW1s4 2026-08-18 daily 0.6 https://picx.dev/news/Yi4vZI 2026-08-21 daily 0.6 https://picx.dev/news/jmPJjn 2026-08-18 daily 0.6 https://picx.dev/news/KHKvWI 2026-08-20 daily 0.6 https://picx.dev/news/vQzfo0 2026-08-20 daily 0.6 https://picx.dev/news/5agSHD 2026-08-18 daily 0.6 https://picx.dev/news/6yHYgT 2026-08-18 daily 0.6 https://picx.dev/news/hgzOPw 2026-08-20 daily 0.6 https://picx.dev/news/m6MtzM 2026-08-20 daily 0.6 https://picx.dev/news/waeJ7b 2026-08-20 daily 0.6 https://picx.dev/news/6QjyoP 2026-08-19 daily 0.6 https://picx.dev/news/Qk9B7f 2026-08-22 daily 0.6 https://picx.dev/news/bnqubi 2026-08-18 daily 0.6 https://picx.dev/news/MYnhXC 2026-08-18 daily 0.6 https://picx.dev/news/pedhIA 2026-08-19 daily 0.6 https://picx.dev/news/wI4N1I 2026-08-17 daily 0.6 https://picx.dev/news/ELwVrF 2026-08-17 daily 0.6 https://picx.dev/news/wfIfzU 2026-08-20 daily 0.6 https://picx.dev/news/qs11lK 2026-08-18 daily 0.6 https://picx.dev/news/u4itbn 2026-08-17 daily 0.6 https://picx.dev/news/zup9Ng 2026-08-17 daily 0.6 https://picx.dev/news/DDWh1C 2026-08-17 daily 0.6 https://picx.dev/news/HGPLlc 2026-08-17 daily 0.6 https://picx.dev/news/z5LJwt 2026-08-17 daily 0.6 https://picx.dev/news/NBmTxb 2026-08-17 daily 0.6 https://picx.dev/news/YZMXVs 2026-08-18 daily 0.6 https://picx.dev/news/oa7cyA 2026-08-20 daily 0.6 https://picx.dev/news/xEkr9m 2026-08-20 daily 0.6 https://picx.dev/news/OYCHKo 2026-08-17 daily 0.6 https://picx.dev/news/QPf2av 2026-08-17 daily 0.6 https://picx.dev/news/AI2fcI 2026-08-17 daily 0.6 https://picx.dev/news/6gFLgm 2026-08-17 daily 0.6 https://picx.dev/news/PEuwvH 2026-08-20 daily 0.6 https://picx.dev/news/47gp0Z 2026-08-17 daily 0.6 https://picx.dev/news/JeLDVe 2026-08-17 daily 0.6 https://picx.dev/news/hmZpCU 2026-08-16 daily 0.6 https://picx.dev/news/XKVQw8 2026-08-16 daily 0.6 https://picx.dev/news/XlPd9Y 2026-08-19 daily 0.6 https://picx.dev/news/sNcugv 2026-08-16 daily 0.6 https://picx.dev/news/S65aer 2026-08-16 daily 0.6 https://picx.dev/news/4rUd0C 2026-08-16 daily 0.6 https://picx.dev/news/lQjGZi 2026-08-16 daily 0.6 https://picx.dev/news/XUzD3u 2026-08-16 daily 0.6 https://picx.dev/news/ZD33xN 2026-08-16 daily 0.6 https://picx.dev/news/GWG43L 2026-08-16 daily 0.6 https://picx.dev/news/GHOPv1 2026-08-16 daily 0.6 https://picx.dev/news/vHBxAO 2026-08-16 daily 0.6 https://picx.dev/news/vRRTKc 2026-08-16 daily 0.6 https://picx.dev/news/GH9Clk 2026-08-17 daily 0.6 https://picx.dev/news/7oz34q 2026-08-18 daily 0.6 https://picx.dev/news/PsrQHh 2026-08-15 daily 0.6 https://picx.dev/news/12JuDW 2026-08-15 daily 0.6 https://picx.dev/news/Ont4Bw 2026-08-16 daily 0.6 https://picx.dev/news/RwFlGT 2026-08-15 daily 0.6 https://picx.dev/news/7G18Qi 2026-08-15 daily 0.6 https://picx.dev/news/OHnQGn 2026-08-15 daily 0.6 https://picx.dev/news/9NH17q 2026-08-15 daily 0.6 https://picx.dev/news/KyLGiV 2026-08-14 daily 0.6 https://picx.dev/news/P5pKfm 2026-08-15 daily 0.6 https://picx.dev/news/5qXQ72 2026-08-15 daily 0.6 https://picx.dev/news/1cDUgE 2026-08-14 daily 0.6 https://picx.dev/news/cXynnQ 2026-08-19 daily 0.6 https://picx.dev/news/4Ig3zU 2026-08-14 daily 0.6 https://picx.dev/news/II9Icu 2026-08-18 daily 0.6 https://picx.dev/news/MXamIb 2026-08-14 daily 0.6 https://picx.dev/news/QW7FUm 2026-08-24 daily 0.6 https://picx.dev/news/xGd6zm 2026-08-14 daily 0.6 https://picx.dev/news/x4uXSl 2026-08-19 daily 0.6 https://picx.dev/news/o3Z5oc 2026-08-14 daily 0.6 https://picx.dev/news/43R7sH 2026-08-14 daily 0.6 https://picx.dev/news/RUxswh 2026-08-13 daily 0.6 https://picx.dev/news/JxLFcn 2026-08-13 daily 0.6 https://picx.dev/news/nJTFtg 2026-08-15 daily 0.6 https://picx.dev/news/MGJXxs 2026-08-13 daily 0.6 https://picx.dev/news/jkSV38 2026-08-14 daily 0.6 https://picx.dev/news/IMS7Kg 2026-08-13 daily 0.6 https://picx.dev/news/ErTZfo 2026-08-13 daily 0.6 https://picx.dev/news/NjPwS5 2026-08-13 daily 0.6 https://picx.dev/news/qwZVQ3 2026-08-13 daily 0.6 https://picx.dev/news/gQdCUT 2026-08-13 daily 0.6 https://picx.dev/news/ipGv8D 2026-08-13 daily 0.6 https://picx.dev/news/tRCVBB 2026-08-14 daily 0.6 https://picx.dev/news/OXDCC2 2026-08-13 daily 0.6 https://picx.dev/news/7kNubX 2026-08-12 daily 0.6 https://picx.dev/news/ALgsbg 2026-08-12 daily 0.6 https://picx.dev/news/G52tQ2 2026-08-12 daily 0.6 https://picx.dev/news/Qpfu7h 2026-08-13 daily 0.6 https://picx.dev/news/TXX15n 2026-08-13 daily 0.6 https://picx.dev/news/IMYIph 2026-08-12 daily 0.6 https://picx.dev/news/9K1K57 2026-08-12 daily 0.6 https://picx.dev/news/L2MTe3 2026-08-12 daily 0.6 https://picx.dev/news/algwnM 2026-08-13 daily 0.6 https://picx.dev/news/2WlC0Q 2026-08-12 daily 0.6 https://picx.dev/news/LIC1oI 2026-08-12 daily 0.6 https://picx.dev/news/bI8gvT 2026-08-12 daily 0.6 https://picx.dev/news/nzfcLV 2026-08-12 daily 0.6 https://picx.dev/news/Ij2RSl 2026-08-12 daily 0.6 https://picx.dev/news/CG7Bdn 2026-08-12 daily 0.6 https://picx.dev/news/nEEUdH 2026-08-12 daily 0.6 https://picx.dev/news/eK2Omf 2026-08-13 daily 0.6 https://picx.dev/news/4DW1NE 2026-08-12 daily 0.6 https://picx.dev/news/S9hK5i 2026-08-12 daily 0.6 https://picx.dev/news/ZBuRhz 2026-08-12 daily 0.6 https://picx.dev/news/lJQ8NN 2026-08-11 daily 0.6 https://picx.dev/news/JsvoOv 2026-08-12 daily 0.6 https://picx.dev/news/W9ccoR 2026-08-12 daily 0.6 https://picx.dev/news/jn4Z92 2026-08-11 daily 0.6 https://picx.dev/news/IwSB4W 2026-08-11 daily 0.6 https://picx.dev/news/Uk3qVX 2026-08-12 daily 0.6 https://picx.dev/news/cUO6xH 2026-08-12 daily 0.6 https://picx.dev/news/ulucJg 2026-08-11 daily 0.6 https://picx.dev/news/abEtur 2026-08-12 daily 0.6 https://picx.dev/news/psmwlZ 2026-08-12 daily 0.6 https://picx.dev/news/TUyNcO 2026-08-11 daily 0.6 https://picx.dev/news/LjwrSf 2026-08-11 daily 0.6 https://picx.dev/news/MxAzwp 2026-08-11 daily 0.6 https://picx.dev/news/heJ4xs 2026-08-11 daily 0.6 https://picx.dev/news/vnFKdy 2026-08-11 daily 0.6 https://picx.dev/news/AAGPVk 2026-08-18 daily 0.6 https://picx.dev/news/OeOwei 2026-08-17 daily 0.6 https://picx.dev/news/GZxZUh 2026-08-11 daily 0.6 https://picx.dev/news/vxvpd6 2026-08-12 daily 0.6 https://picx.dev/news/76lN0R 2026-08-11 daily 0.6 https://picx.dev/news/18btnW 2026-08-10 daily 0.6 https://picx.dev/news/2gXZbl 2026-08-13 daily 0.6 https://picx.dev/news/EbR95x 2026-08-12 daily 0.6 https://picx.dev/news/3Rl0cu 2026-08-10 daily 0.6 https://picx.dev/news/kF3gSm 2026-08-10 daily 0.6 https://picx.dev/news/QZknj4 2026-08-10 daily 0.6 https://picx.dev/news/UtlCN0 2026-08-10 daily 0.6 https://picx.dev/news/qzhOQk 2026-08-10 daily 0.6 https://picx.dev/news/Mm0XFb 2026-08-10 daily 0.6 https://picx.dev/news/xX0euS 2026-08-11 daily 0.6 https://picx.dev/news/izRqw4 2026-08-10 daily 0.6 https://picx.dev/news/7Vu2JB 2026-08-10 daily 0.6 https://picx.dev/news/JdW7hC 2026-08-11 daily 0.6 https://picx.dev/news/kVECox 2026-08-10 daily 0.6 https://picx.dev/news/vUx735 2026-08-10 daily 0.6 https://picx.dev/news/k9Z0Uw 2026-08-10 daily 0.6 https://picx.dev/news/AXgxF3 2026-08-10 daily 0.6 https://picx.dev/news/Lz30pX 2026-08-10 daily 0.6 https://picx.dev/news/ER1kMD 2026-08-10 daily 0.6 https://picx.dev/news/nVzCs7 2026-08-10 daily 0.6 https://picx.dev/news/ChwZHU 2026-08-11 daily 0.6 https://picx.dev/news/1Phvxk 2026-08-11 daily 0.6 https://picx.dev/news/i72be0 2026-08-09 daily 0.6 https://picx.dev/news/VQWcQQ 2026-08-10 daily 0.6 https://picx.dev/news/q7Sea5 2026-08-10 daily 0.6 https://picx.dev/news/aUOxVx 2026-08-11 daily 0.6 https://picx.dev/news/FbXtwW 2026-08-09 daily 0.6 https://picx.dev/news/tdWYRM 2026-08-09 daily 0.6 https://picx.dev/news/KnJVNS 2026-08-09 daily 0.6 https://picx.dev/news/TyC07G 2026-08-09 daily 0.6 https://picx.dev/news/SmffEG 2026-08-09 daily 0.6 https://picx.dev/news/7wPR0d 2026-08-09 daily 0.6 https://picx.dev/news/O6EDWT 2026-08-09 daily 0.6 https://picx.dev/news/W7lxch 2026-08-09 daily 0.6 https://picx.dev/news/FZh6S8 2026-08-09 daily 0.6 https://picx.dev/news/5qqpm7 2026-08-08 daily 0.6 https://picx.dev/news/uSJnHx 2026-08-08 daily 0.6 https://picx.dev/news/5bRH3Y 2026-08-08 daily 0.6 https://picx.dev/news/zUvPvQ 2026-08-08 daily 0.6 https://picx.dev/news/MxGQsY 2026-08-08 daily 0.6 https://picx.dev/news/6tAkwx 2026-08-08 daily 0.6 https://picx.dev/news/jDiF0b 2026-08-07 daily 0.6 https://picx.dev/news/f1Ezlh 2026-08-07 daily 0.6 https://picx.dev/news/tko0xn 2026-08-09 daily 0.6 https://picx.dev/news/HSyXkE 2026-08-07 daily 0.6 https://picx.dev/news/dLWy1S 2026-08-07 daily 0.6 https://picx.dev/news/0tQ1UP 2026-08-14 daily 0.6 https://picx.dev/news/7738Oy 2026-08-07 daily 0.6 https://picx.dev/news/wywg8W 2026-08-07 daily 0.6 https://picx.dev/news/NeBqfy 2026-08-07 daily 0.6 https://picx.dev/news/XbxjoX 2026-08-07 daily 0.6 https://picx.dev/news/wdlX2g 2026-08-07 daily 0.6 https://picx.dev/news/19tZd3 2026-08-07 daily 0.6 https://picx.dev/news/JRoq3g 2026-08-07 daily 0.6 https://picx.dev/news/5NheTI 2026-08-07 daily 0.6 https://picx.dev/news/cXfGbl 2026-08-09 daily 0.6 https://picx.dev/news/XVdeQk 2026-08-07 daily 0.6 https://picx.dev/news/Si4tar 2026-08-07 daily 0.6 https://picx.dev/news/UXiZ0W 2026-08-06 daily 0.6 https://picx.dev/news/0jgUjs 2026-08-06 daily 0.6 https://picx.dev/news/IEvJGP 2026-08-06 daily 0.6 https://picx.dev/news/y41I47 2026-08-06 daily 0.6 https://picx.dev/news/24oDsN 2026-08-07 daily 0.6 https://picx.dev/news/eMybhe 2026-08-05 daily 0.6 https://picx.dev/news/IlttQD 2026-08-08 daily 0.6 https://picx.dev/news/q5ekzF 2026-08-09 daily 0.6 https://picx.dev/news/N2qrv1 2026-08-07 daily 0.6 https://picx.dev/news/1tZZjv 2026-08-05 daily 0.6 https://picx.dev/news/ogGuLG 2026-08-05 daily 0.6 https://picx.dev/news/54tfKW 2026-08-05 daily 0.6 https://picx.dev/news/tlIi7C 2026-08-05 daily 0.6 https://picx.dev/news/GAVC5H 2026-08-05 daily 0.6 https://picx.dev/news/PTXKe7 2026-08-05 daily 0.6 https://picx.dev/news/biv7pq 2026-08-07 daily 0.6 https://picx.dev/news/l1Eo17 2026-08-05 daily 0.6 https://picx.dev/news/IofaY7 2026-08-05 daily 0.6 https://picx.dev/news/rnqsjM 2026-08-04 daily 0.6 https://picx.dev/news/I3iAeH 2026-08-04 daily 0.6 https://picx.dev/news/hKaa7Q 2026-08-04 daily 0.6 https://picx.dev/news/k6tBnl 2026-08-04 daily 0.6 https://picx.dev/news/4VdEg7 2026-08-04 daily 0.6 https://picx.dev/news/Ky4KHt 2026-08-04 daily 0.6 https://picx.dev/news/5ntkzC 2026-08-04 daily 0.6 https://picx.dev/news/qVTqog 2026-08-04 daily 0.6 https://picx.dev/news/R9V8NX 2026-08-04 daily 0.6 https://picx.dev/news/AGxpdb 2026-08-04 daily 0.6 https://picx.dev/news/kufv1L 2026-08-07 daily 0.6 https://picx.dev/news/UoSMfx 2026-08-04 daily 0.6 https://picx.dev/news/FGnT4O 2026-08-06 daily 0.6 https://picx.dev/news/83tKzu 2026-08-04 daily 0.6 https://picx.dev/news/6aG3Io 2026-08-04 daily 0.6 https://picx.dev/news/rabbK1 2026-08-04 daily 0.6 https://picx.dev/news/1IxPgr 2026-08-04 daily 0.6 https://picx.dev/news/gJ195L 2026-08-06 daily 0.6 https://picx.dev/news/w3VoDw 2026-08-04 daily 0.6 https://picx.dev/news/hg1M1c 2026-08-04 daily 0.6 https://picx.dev/news/a1SBNP 2026-08-06 daily 0.6 https://picx.dev/news/KTJEDW 2026-08-04 daily 0.6 https://picx.dev/news/2hw5ai 2026-08-05 daily 0.6 https://picx.dev/news/lX22q4 2026-08-04 daily 0.6 https://picx.dev/news/lUcQmq 2026-08-04 daily 0.6 https://picx.dev/news/4wNxr7 2026-08-04 daily 0.6 https://picx.dev/news/t59ch0 2026-08-04 daily 0.6 https://picx.dev/news/NONKZp 2026-08-04 daily 0.6 https://picx.dev/news/94J8MD 2026-08-04 daily 0.6 https://picx.dev/news/S7hB8j 2026-08-04 daily 0.6 https://picx.dev/news/YRdR27 2026-08-04 daily 0.6 https://picx.dev/news/rlmOhN 2026-08-04 daily 0.6 https://picx.dev/news/W2CIPP 2026-08-04 daily 0.6 https://picx.dev/news/C4n5zo 2026-08-04 daily 0.6 https://picx.dev/news/kd5lFB 2026-08-07 daily 0.6 https://picx.dev/news/LecbwC 2026-08-06 daily 0.6 https://picx.dev/news/lFjOIz 2026-08-04 daily 0.6 https://picx.dev/news/iFHywm 2026-08-04 daily 0.6 https://picx.dev/news/d6VGGr 2026-08-04 daily 0.6 https://picx.dev/news/Pj84QL 2026-08-04 daily 0.6