{"ID":23474996,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19666","arxiv_id":"2609.19666","title":"Towards High-DoF Dexterous Manipulation through VLA Post-Training","abstract":"Imitation-learned vision--language--action (VLA) foundation models acquire broad manipulation capabilities by scaling robot data across tasks and embodiments, but reliable deployment on a specific downstream task and hardware platform still requires post-training. Dexterous hands make this adaptation particularly difficult: their broad behavioural repertoire and high degree of freedom create a large and structured action space. Three obstacles are central: open-source VLAs do not natively provide an action interface for high-DoF hands; gesture mismatch during human-gated DAgger takeover creates command discontinuities and contaminates corrective trajectories; and reinforcement learning in the raw joint space is sample-inefficient. We present a unified four-step post-training pipeline comprising a learned temporal hand-action codec, supervised fine-tuning, DAgger, and real-world residual reinforcement learning. The codec adapts a pretrained VLA to absolute dexterous-hand commands. Buffered rollback, pose alignment, and smooth command blending enable continuous, task-relevant DAgger corrections, while latent residual RL confines exploration to coordinated hand motions captured by the codec. We evaluate the pipeline on five diverse real-world tasks spanning bimanual transfer, in-hand reorientation, and tool use. Within the reported post-training budgets, the resulting policies achieve 100\\% success on every evaluated task over 20 trials per task. These results provide a practical path for adapting VLA foundation models to reliable real-world dexterous manipulation.","short_abstract":"Imitation-learned vision--language--action (VLA) foundation models acquire broad manipulation capabilities by scaling robot data across tasks and embodiments, but reliable deployment on a specific downstream task and hardware platform still requires post-training. Dexterous hands make this adaptation particularly diffi...","url_abs":"https://arxiv.org/abs/2609.19666","url_pdf":"https://arxiv.org/pdf/2609.19666v1","authors":"[\"Junlei Zhu\",\"Shenzhe Yao\",\"Chaogui Huang\",\"Wenkai Zhu\",\"Jingwei Peng\",\"Guanqi He\",\"Soren Schwertfeger\",\"Jiahao Chen\",\"Yide Liu\"]","published":"2026-09-17T04:12:21Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Reinforcement Learning\",\"LoRA\"]","has_code":false}