A unified four-step post-training pipeline comprising a learned temporal hand-action codec, supervised fine-tuning, DAgger, and real-world residual reinforcement learning provides a practical path for adapting VLA foundation models to reliable real-world dexterous manipulation.
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.
Simulation Pre-training for Dexterity (SPD) is introduced, a pre-training framework for dexterous manipulation that uses data entirely collected in simulation and outperforms training behavior cloning policies from scratch, showing that simulation teleoperation is a viable pre-training source for real-world dexterous m...
Sarthak Kamat, Adam Rashid, Satvik Sharma et al.· 0 citations
Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains challenging. Supervised fine-tuning (SFT) on task-specific demonstrations provides a step toward deployment, but faces two persistent limitations: static data provide limite...
We introduce Accelerating Dexterity via Pre-Training (ADEPT), a large-scale reinforcement learning (RL) framework for learning sim-to-real transferable dexterity across high degree-of-freedom (DoF) robot embodiments that can solve long-horizon tasks directly from raw visuo-tactile perception. ADEPT pretrains a dexterou...
Jayjun Lee, Jessica Yin, Asif Rana et al.· 2 citations
MotorMind is introduced, a robot manipulation harness that connects VLM-proposed mid-level actions to deterministic robot control and feedback, with asynchronous monitoring and background memory updates, and shows that a general-purpose VLM, when equipped with an appropriate mid-level action representation and asynchro...
ForceRFT is presented, a force-guided residual reinforcement learning framework that learns contact-dependent corrections from human supervision and autonomous task outcomes and shows higher autonomous success rates than the evaluated demonstration-trained and residual-imitation baselines.
Yi-Cheng Wang, Chao-Yang Zhang, Xu-Qi Su et al.· 0 citations
This work instantiates Real-Time EXPO-FT, an RL framework for finetuning real-time VLA policies that meets the real-time control requirements of dynamic real-world manipulation, demonstrating rapid, sample-efficient adaptation to challenging real-world dynamics.
Perry Dong, Kuo-Han Hung, D. Sadigh et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.