1
VRPRM: Process Reward Modeling via Visual Reasoning
通过视觉推理提升过程奖励建模精度，为复杂任务训练提供新思路。
arXiv:2508.03556v3 Announce Type: replace Abstract: Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) becau…
2
What is Holding Back Latent Visual Reasoning?
探究视觉语言模型中潜在视觉推理的瓶颈，揭示人类式中间视觉步骤的模拟障碍
arXiv:2605.18445v1 Announce Type: cross Abstract: Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather…
3
Leveraging Latent Visual Reasoning in Silence
论文揭示多模态推理中潜伏视觉令牌的非必需性，随机噪声替代不影响性能，挑战现有认知。
arXiv:2605.18641v1 Announce Type: new Abstract: Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting co…
4
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
提出ATLAS方法，用单个词统一智能体和潜在视觉推理，突破中间状态计算瓶颈
arXiv:2605.15198v1 Announce Type: cross Abstract: Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising dire…
5
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
多模态大模型在空间智能上的突破，赋予AI更强的视觉感知与推理能力。
arXiv:2505.23747v2 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced …
6
Grounded Reinforcement Learning for Visual Reasoning
视觉推理遇上强化学习，链式思考突破复杂场景，脑洞与硬核并存。
arXiv:2505.23678v3 Announce Type: replace Abstract: While reinforcement learning (RL) over chains of thought has significantly advanced language model…