arXiv 2610.25043 · cs.AI · 2026-10-18
VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
Sicheng He, Yi Pan, Qiuting Yu, Jiaming Huang, Qi Lu, Shuyan Wu, Hongyan Feng, Xuanyu Liu 等 13 人
ZJU-OmniAI
在最新榜 #273 本站收录于 2026-10-22
一句话要点
VLA-Rolling 复用上一段未执行的动作尾巴作为去噪起点，用更少步数生成动作，冻结模型即可提速并提高成功率。
VLA-Rolling reuses the unexecuted action tail as the starting point for denoising, cutting steps for frozen flow-matching VLAs while often raising success.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：机器人与具身
- Has GPT-6-Astra Achieved Embodied Intelligence? ▲459
- In-Context Learning for Robots: Methods and Applications ▲388
- HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents ▲313
- GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives ▲310
- Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience ▲179
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。