SimpleVLN: Native MLLM Method Achieves SOTA in Vision-Language Navigation
Researchers from Fudan University and Nanyang Technological University propose SimpleVLN, a method that achieves state-of-the-art results in vision-language navigation without adding specialized modules, by leveraging the native capabilities of multimodal large language models (MLLMs). The approach treats each model call as an independent decision, using a global-plus-local strategy for historical observations, and demonstrates through ablation studies that uniform sampling of global history outperforms feeding all historical images.
Coverage timeline
机器之心机器之心
设想这样一个场景：给机器人下达一句自然语言指令，让它穿过走廊、接连转弯，最终走进指定房间。视觉语言导航（VLN），需要让机器人结合沿途看到的画面，把人类的语言指令转化为一连串连续行动。 现有多数 VLN 方法会引入专门的空间推理模块、图结构建模或分层决策系统来增强导航能力，但多模态大模型本身自带的导航潜力，究竟能不能被充分激活，还有待深入探索。复旦大学与新加坡南洋理工大学团队开辟了新的研究思路：能不能不改动多模态大模型的核心结构，也不新增专门的导航模块，仅靠巧妙的决策设计与训练流程，充分发挥模型原生能力，完成导航任务？ 论文标题：SimpleVLN: Towards Simple and Frontier Vision-Language Navigation With Native MLLMs 作者：Lingyi Hong, Weiren Cai, Jiayu Chen, Xinyu Zhou, Bailin He, Yunfei Guo, Qiao Sun, Xiang Liu, Boyu Ma, Jianfei Yang, Wenqiang Zhang 机构：复旦大学，新加坡南洋理工大学，联想研究院 论文链接：https://arxiv.org/pdf/2610.23203v1 项目主页：https://simplevln.github.io/ 代码仓库：https://github.com/simplevln/SimpleVLN 图 1｜SimpleVLN 的研究问题与两项导航基准上的表现。 给机器人看什么，又该让它怎么走？ 机器人转过一个弯后，眼前的画面可能已经与之前截然不同。此时，它既需要判断自己当下的位置，还要结合之前看到的画面，规划后续行进路线。 不过历史画面并非存得越多越好：全部保存会不断拉长输入；只保留最近几帧，又容易丢失早前的路线信息。 SimpleVLN 把每一次模型调用都当作一次独立决策，输入包含导航指令、当前画面以及筛选后的历史观测，不会持续累积过往对话与动作。针对历史图像，团队采用全局 + 局部的组合策略：从早期观测里均匀采样，同时保留最新一帧画面。 消融实验证明，把所有历史图像全部输入并不会提升效果；对全局历史做均匀采样反而效果更佳，继续增加局部帧也无法继续提高导航成功率。 图2｜历史帧和局部帧数对导航性能的影响。 由此可见，重点不在于
Related stories
LoopVL open-source VLM shows data efficiency with 260x less training data
Researchers from Renmin University, Baidu, and others released LoopVL, an open-source vision-language model based on the Loop Transformer. Despite using only 0.14T training tokens versus about 36T for Qwen3.5-2B and InternVL3.5-2B, LoopVL matches or exceeds them on benchmarks like LogicVista, MMMU-Pro, and MathVision, demonstrating high data efficiency. The team also observed cross-loop visual attention reorganization, termed 'Visual Aha Moment'.
1 reports · 1 sources
RAVEL: Training-Free Method Improves Vision Encoder Evaluation for Multimodal LLMs
Researchers proposed RAVEL, a training-free evaluation method with two improvements—stabilized PCA whitening and patch-level similarity scoring—to predict how well vision encoders perform in multimodal LLMs. Experiments on 210 multimodal LLMs showed existing cross-modal methods degrade as candidate pools grow, while RAVEL achieved an average Spearman correlation of 0.85, outperforming prior methods by up to 101.1%.
Fudan, Tencent Hunyuan, Tsinghua Release ExplorationBench to Test AI Rule Discovery
Fudan University, Tencent Hunyuan, and Tsinghua University released ExplorationBench, a benchmark measuring how AI systems discover rules in unfamiliar environments. It includes two altered 'alien worlds'—the programming language AlienCode and the logic proof system AlienLogic—where models must learn rules through trial and error. Results showed that without environment feedback, scores remained low (max 11.0%), while autonomous exploration led to high scores (up to 89.0%).
NV-CoT: Multimodal LLMs Predict Continuous Coordinates for Visual Chain-of-Thought, NeurIPS 2026 Oral
Researchers from NTU, USTC, NUS, and Microsoft propose NV-CoT (Numerical Visual Chain-of-Thought), a method that lets multimodal LLMs directly predict continuous numerical coordinates for region selection instead of generating bounding boxes as text tokens. The work, accepted as a NeurIPS 2026 Oral (top 0.4%), supports supervised fine-tuning and reinforcement learning, addressing mismatches between token-level training and spatial error.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe