{"ID":2850242,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22201","arxiv_id":"2510.22201","title":"ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models","abstract":"Diffusion and flow matching models have emerged as powerful robot policies, enabling Vision-Language-Action (VLA) models to generalize across diverse scenes and instructions. Yet, when trained via imitation learning, their high generative capacity makes them sensitive to noise in human demonstrations: jerks, pauses, and jitter which reduce action coherence. Reduced action coherence causes instability and trajectory drift during deployment, failures that are catastrophic in fine-grained manipulation where precision is crucial. In this paper, we present Action Coherence Guidance (ACG) for VLA models, a training-free test-time guidance algorithm that improves action coherence and thereby yields performance gains. Evaluated on RoboCasa, DexMimicGen, and real-world SO-101 tasks, ACG consistently improves action coherence and boosts success rates across diverse manipulation tasks. Code and project page are available at https://github.com/DAVIAN-Robotics/ACG and https://DAVIAN-Robotics.github.io/ACG , respectively.","short_abstract":"Diffusion and flow matching models have emerged as powerful robot policies, enabling Vision-Language-Action (VLA) models to generalize across diverse scenes and instructions. Yet, when trained via imitation learning, their high generative capacity makes them sensitive to noise in human demonstrations: jerks, pauses, an...","url_abs":"https://arxiv.org/abs/2510.22201","url_pdf":"https://arxiv.org/pdf/2510.22201v2","authors":"[\"Minho Park\",\"Kinam Kim\",\"Junha Hyung\",\"Hyojin Jang\",\"Hoiyeong Jin\",\"Jooyeol Yun\",\"Hojoon Lee\",\"Jaegul Choo\"]","published":"2025-10-25T07:44:33Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":607779,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2850242,"paper_url":"https://arxiv.org/abs/2510.22201","paper_title":"ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models","repo_url":"https://github.com/DAVIAN-Robotics/ACG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}