12 papers
Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
Chi Zhang, Penglin Cai, Ziheng Xi +6
As an essential modality for dexterous and contact-rich tasks, tactile sensing provides precise force feedback that cannot be reliably inferred from vision. However, limited by har…
Transport Discrepancy as a Reliability Signal for Vision-Language-Action Models
Wanpeng Zhang, Ye Wang, Hao Luo +6
Vision-language-action (VLA) models that generate continuous action chunks via flow matching lack an internal signal for judging whether a given prediction is reliable. Distributio…
Being-H0.7: A Latent World-Action Model from Egocentric Videos
Hao Luo, Wanpeng Zhang, Yicheng Feng +6
Visual-Language-Action models (VLAs) have advanced generalist robot control by mapping multimodal observations and language instructions directly to actions, but sparse action supe…
Diverse Skill Discovery for Quadruped Robots via Unsupervised Learning
Ruopeng Cui, Yifei Bi, Haojie Luo +1
Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast,…
Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization
Ye Wang, Sipeng Zheng, Hao Luo +9
While Vision-Language-Action (VLA) models show strong promise for generalist robot control, it remains unclear whether -- and under what conditions -- the standard "scale data" rec…
Accelerated Mirror Descent Method through Variable and Operator Splitting
Long Chen, Hao Luo, Jingrong Wei +2
Mirror descent uses the mirror function to encode geometry and constraints, improving convergence while preserving feasibility. Accelerated Mirror Descent Methods (Acc-MD) are deri…