paper-with-me

홈 › Papers

Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models

2025-09-28 · Rokas Bendikas, Daniel Dijkman, Markus Peschl, Sanjay Haresh, Pietro Mazzaglia arxiv

Vision-Language-Action (VLA) models offer a pivotal approach to learning robotic manipulation at scale by repurposing large pre-trained Vision-Language-Models (VLM) to output robotic actions. However, adapting VLMs for robotic domains comes with an unnecessarily high computational cost, which we attribute to the tokenization scheme of visual inputs. In this work, we aim to enable efficient VLA training by proposing Oat-VLA, an Object-Agent-centric Tokenization for VLAs. Building on the insights of object-centric representation learning, our method introduces an inductive bias towards scene objects and the agent's own visual information. As a result, we find that Oat-VLA can drastically reduce the number of visual tokens to just a few tokens without sacrificing performance. We reveal that Oat-VLA converges at least twice as fast as OpenVLA on the LIBERO suite, as well as outperform OpenVLA in diverse real-world pick and place tasks.

📄 PDF Abstract BibTeX arXiv:2509.23655

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents

2026-02-07 · Sai Puppala, Ismail Hossain, Md Jahangir Alam, Yoonpyo Lee 외 arxiv

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFe…

Mask What Matters: Mitigating Object Hallucinations in Multimodal Large Language Models with Object-Aligned Visual Contrastive Decoding

2026-02-12 · Boqi Chen, Xudong Liu, Jianing Qiu arxiv

We study object hallucination in Multimodal Large Language Models (MLLMs) and improve visual contrastive decoding (VCD) by constructing an object-aligned auxiliary view. We leverage object-centric attention in self-super…

Relevant Action Matters : Motivating agent with action usefulness

2021-03-09 · ICLR Workshop SSL-RL 2021 5 · Mathieu Seurin, Florian Strub, Philippe Preux, Olivier Pietquin

Sparse rewards are double-edged training signals in reinforcement learning: easy to design but hard to optimize. Intrinsic motivation guidances have thus been developed toward alleviating the resulting exploration proble…

StoryTR: Narrative-Centric Video Temporal Retrieval with Theory of Mind Reasoning

2026-04-25 · Xuanyue Zhong, Yuqiang Xie, Guanqun Bi, Jiangping Yang 외 arxiv

Current video moment retrieval excels at action-centric tasks but struggles with narrative content. Models can see \textit{what is happening} but fail to reason \textit{why it matters}. This semantic gap stems from the l…

Moment Retrieval

Agent-centric learning: from external reward maximization to internal knowledge curation

2025-07-29 · Hanqi Zhou, Fryderyk Mantiuk, David G. Nagy, Charley M. Wu arxiv

The pursuit of general intelligence has traditionally centered on external objectives: an agent's control over its environments or mastery of specific tasks. This external focus, however, can produce specialized agents t…