8 papers
What Should Robot Policies Learn to Predict? Rethinking Supervision Targets in Vision-Language-Action Learning
Haitao Shen, Hanyu Liu, Yihan Lin +7
Vision-language-action (VLA) policies are typically trained with action prediction as the primary supervision signal, since robots ultimately execute actions. Auxiliary objectives…
MUCO: A Mani-Unit-Structured Manipulation Framework for Compositional Long-Horizon Robot Tasks
Xiangyi Wei, Hanzhe Yao, Jingwen Shang +3
Learning and executing long-horizon robot manipulation as complete task trajectories raises data-collection costs, lim?its capability reuse, and causes local failures to cascade in…
RoboRecover: Benchmarking Robot Policy Recovery under Execution Deviations
Yang Li, Chen Zhao, Zhuoran Wang +5
Robot-policy benchmarks increasingly cover diverse tasks and preset out-of-distribution conditions, but typically evaluate complete trajectories from predefined initial states. The…
JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
Yihan Lin, Jiawei He, Shifeng Bao +6
Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployment cost. Existing latent WAM…
Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision
Haoyang Li, Guanlin Li, Youhe Feng +9
Cross-embodiment transfer in vision-language-action (VLA) models remains challenging because low-level state and action spaces differ fundamentally across robot platforms. We obser…
From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
Yihan Lin, Haoyang Li, Yang Li +4
Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to…
TokenPB: Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
Chen Zhao, Zhuoran Wang, Haoyang Li +6
Test-time sampling can improve Vision-Language-Action (VLA) policies, but only if the model can efficiently select a good action from multiple candidates. Prior work often relies o…
Ovis-U1 Technical Report
Guo-Hua Wang, Shanshan Zhao, Xinjie Zhang +9
In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Buildi…