paper-with-me

Papers

Think Proprioceptively: State-Grounded Visual Token Selection for VLA Policies

2026-02-06 · Fangyuan Wang, Peng Zhou, Jiaming Qi, Shipeng Lyu, Chengyang He, David Navarro-Alarcon, Guodong Guo arxiv

Vision-language-action (VLA) models typically inject proprioception only as a late conditioning signal, preventing robot state from grounding instruction understanding or directing visual attention. We introduce ThinkProprio, which discretizes proprioception into VLM-vocabulary tokens and uses them jointly with the instruction to gate visual patches before VLM computation, steering the model toward action-relevant evidence while discarding redundant tokens early. We find that proprioception added as a passive conditioning signal leaves performance essentially unchanged; its value emerges when token-form state acts as an active query that, with the instruction, selects which visual patches the VLM processes. Systematic ablations show that VLM-vocabulary tokens outperform learned projectors as the state encoding, and that retaining only about \SI{12}{\percent} of the visual tokens surpasses on CALVIN ABC$\to$D. Across CALVIN, LIBERO, and real-world manipulation, ThinkProprio reduces end-to-end inference latency while improving the matched full-token baseline.

📄 PDF Abstract BibTeX arXiv:2602.06575

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs

2025-12-18 · Jintao Tong, Jiaqi Gu, Yujing Lou, Lubin Fan 외 arxiv

While Multimodal Large Language Models (MLLMs) excel at visual understanding tasks through text reasoning, they often fall short in scenarios requiring visual imagination. Unlike current works that take predefined extern…

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs

2026-03-05 · Yiwei Li, Zihao Wu, Yanjun Lv, Hanqi Jiang 외 arxiv

Vision--language models (VLMs) process images as visual tokens, yet their intermediate reasoning is often carried out in text, which can be suboptimal for visually grounded radiology tasks. Radiologists instead diagnose …

Visual Reasoning

VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models

2026-02-27 · Soumya Suvra Ghosal, Youngeun Kim, Zhuowei Li, Ritwick Chaudhry 외 arxiv

Advances in large reasoning models have shown strong performance on complex reasoning tasks by scaling test-time compute through extended reasoning. However, recent studies observe that in vision-dependent tasks, extende…

Reinforcement LearningVisual Reasoning

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

2025-11-24 · Yiming Qin, Bomin Wei, Jiaxin Ge, Konstantinos Kallidromitis 외 arxiv

Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stem…

Spatial Reasoning

GLaQ: Grounding Latent Queries in Visual Evidence for Multimodal Reasoning

2026-08-16 · Zesheng Yang, Lingling Zhang, Xinyu Zhang, Cheng Zhang 외 arxiv

Chain-of-thought reasoning has substantially improved the problem-solving capabilities of multimodal large language models. Fine-grained visual evidence, however, remains difficult to preserve and reuse across text-based…

Reinforcement LearningMultimodal ReasoningAnswer Generation