{"ID":6620451,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12287","arxiv_id":"2607.12287","title":"Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference","abstract":"Vision-Language-Action (VLA) models exhibit strong generalization for robotic manipulation, yet their high inference latency limits real time deployment. We identify two primary sources of temporal redundancy in existing VLA pipelines: repeated visual encoding of highly similar consecutive frames and multi step iterative sampling in diffusion based policies. To address this, we propose a system level acceleration strategy that reduces computation in both perception and action generation. On the perception side, we incrementally update only tokens corresponding to dynamic scene regions instead of re-encoding entire frames. On the policy side, we compress diffusion sampling into a compact 2-step schedule through efficiency oriented training while preserving action precision. Experiments on Libero, RobotWin, and Real Robot Platforms demonstrate over 2 times speedup while maintaining high performance, achieving up to 98% success rate on general manipulation benchmarks. Our codes will be released on Github.","short_abstract":"Vision-Language-Action (VLA) models exhibit strong generalization for robotic manipulation, yet their high inference latency limits real time deployment. We identify two primary sources of temporal redundancy in existing VLA pipelines: repeated visual encoding of highly similar consecutive frames and multi step iterati...","url_abs":"https://arxiv.org/abs/2607.12287","url_pdf":"https://arxiv.org/pdf/2607.12287v1","authors":"[\"Yuzhou Wu\",\"Yuxin Zheng\",\"Muchun Niu\",\"Yishan Yang\",\"Tianhao Liu\",\"hanwen kang\",\"Jiajian Jing\",\"Linfeng Zhang\",\"Chuan Wen\"]","published":"2026-07-14T02:48:31Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Diffusion Model\"]","has_code":false}