2025.11.05 | 向量草图测代码；先画后想补视觉
"视觉推理" 相关文章
A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics
Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
Evaluating ChatGPT's Performance in Classifying Pneumonia from Chest X-Ray Images
RewardMap: 通过多阶段强化学习解决细粒度视觉推理的Sparse Reward
ZeST: an LLM-based Zero-Shot Traversability Navigation for Unknown Environments
SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
RECODE: Reasoning Through Code Generation for Visual Question Answering
CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts
1万亿参数Ling-1T开源，国产LLM牛了~
To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering
ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
Can World Models Benefit VLMs for World Dynamics?
NeurIPS 2025 | UniPixel：首个统一对象指代与分割的像素级推理框架，让大模型看懂每一个像素
NeurIPS 2025 Spotlight | FSDrive统一VLA和世界模型，推动自动驾驶迈向视觉推理
