https://picx.dev/ 2026-06-03 weekly 1.0 https://picx.dev/gallery 2026-06-03 daily 0.9 https://picx.dev/about monthly 0.5 https://picx.dev/gallery/c/llm 2026-06-03 daily 0.7 https://picx.dev/gallery/c/nlp 2026-06-03 daily 0.7 https://picx.dev/gallery/c/multimodal 2026-06-03 daily 0.7 https://picx.dev/gallery/c/vision 2026-06-03 daily 0.7 https://picx.dev/gallery/c/generative 2026-06-03 daily 0.7 https://picx.dev/gallery/c/speech-audio 2026-06-03 daily 0.7 https://picx.dev/gallery/c/reinforcement-learning 2026-06-03 daily 0.7 https://picx.dev/gallery/c/agents 2026-06-03 daily 0.7 https://picx.dev/gallery/c/reasoning-planning 2026-06-03 daily 0.7 https://picx.dev/gallery/c/retrieval-rag 2026-06-03 daily 0.7 https://picx.dev/gallery/c/robotics-3d 2026-06-03 daily 0.7 https://picx.dev/gallery/c/ml-theory 2026-06-03 daily 0.7 https://picx.dev/gallery/c/efficiency 2026-06-03 daily 0.7 https://picx.dev/gallery/c/data-benchmark 2026-06-03 daily 0.7 https://picx.dev/gallery/c/alignment-safety 2026-06-03 daily 0.7 https://picx.dev/gallery/c/ai-for-science 2026-06-03 daily 0.7 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/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/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/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/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/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/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