ReWeight is introduced, a framework that incorporates human data into VLA post-training through demonstration-level retrieval and sample-level weighting and learns a cross-embodiment visuomotor representation that combines visual observations with future actions to measure behavioral similarity between human and robot demonstrations.
Abstract
Post-training vision-language-action (VLA) models for specific robots and tasks requires in-domain demonstrations, yet collecting diverse robot data is costly. Egocentric human demonstrations provide a scalable alternative, but directly mixing human and robot data can introduce cross-embodiment discrepancies and degrade policy performance. To address this challenge, we introduce ReWeight, a framework that incorporates human data into VLA post-training through demonstration-level retrieval and sample-level weighting. ReWeight learns a cross-embodiment visuomotor representation that combines visual observations with future actions to measure behavioral similarity between human and robot demonstrations. Based on optimal transport, it retrieves human demonstrations relevant to the target robot data and assigns larger weights to samples with smaller cross-embodiment discrepancies. We evaluate ReWeight using $\pi_{0.5}$ across eight simulation tasks and four real-world tasks under both clean and randomized settings. In simulation, ReWeight improves the average success rate of post-trained $\pi_{0.5}$ from 39% with only robot data and 44% with randomly mixed human-robot data to 57%. In the physical experimental setting, it achieves an average success rate of 68.8%, outperforming the baselines by 28.8% and 13.8%, respectively. Overall, ReWeight provides an effective paradigm for transforming abundant egocentric human experience into transferable supervision for robot learning. (Project webpage: https://reweight-vla.github.io/)
The team reports highlight the importance of adapting to the deployment environment while retaining prior capabilities, treating demonstration quality at an appropriate temporal scale, and suppressing errors in inactive robot components, and expose the limitations of offline action-prediction metrics for forecasting cl...
Jiaming Wang, Ji-Zhuo Chen, Di-Wen Liu et al.· 0 citations
This report introduces Rho, a family of open-weights VLA models for bimanual manipulation designed for data-light task adaptation on 3 embodiments representative of dual-arm robots across research labs and the industry -- YAM Box, UR AI Trainer, and FR3 Duo.
Rho Team Simran Bagaria, Daphne Chen, Dean Fortier et al.· 0 citations
Vision--language--action (VLA) models acquire broad generalization through large-scale pretraining, yet adapting them to a new task and robot embodiment still requires post-training on newly collected data. Unlike pretraining, post-training targets task- and embodiment-specific adaptation, making it particularly sensit...
Run-Ze Xu, Yuan-Fan Xu, Cui-Jie Xu et al.· 0 citations
The performance of learned robot visuomotor policies depends heavily on the size and quality of their training data, yet collecting high-quality demonstrations remains costly for robots in the real world. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action spa...
Yi-Qin Wang, Mrinal Verghese, Jeff G. Schneider· 0 citations
This work proposes VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning, showing that representation-centric continued pre-training can deliver highly competitive performance under a modest compute budget and is an important independent axis of...
Sen-Qiao Yang, Cheng-Yao Wang, Yu-Xin Chen et al.· 8 citations
A robotization pipeline is developed that converts heterogeneous human videos into robot-aligned observations and action trajectories while inferring missing intermediate signals across annotation levels and constructs the HuRo dataset, comprising about 630K robotized episodes and 142M processed frames from five human-...
Jinho Jeong, Se June Joo, Jaehyun Kang et al.· 2 citations