21 citations · 27 across the 6 of their papers we have counts for
4 papers · 1 filter
OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
Xule Gao, Xi Wang, Zehua Zang +3
Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-level supervised imitation o…
Context-dependent agent evaluation with orthogonal equilibrium learning
Haorui Ma, Zehua Zang, Jiangmeng Li +3
Many applications require to evaluate agents under contextual information (e.g., a prompt, task, or user group). We study how to perform such context-dependent agent evaluation fro…
Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models
Zehua Zang, Xi Wang, Fuchun Sun +4
Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, such as small changes in object…
RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation
Kai Zhu, Zhenyu Cui, Zehua Zang +1
Recently, state space models have demonstrated efficient video segmentation through linear-complexity state space compression. However, Video Semantic Segmentation (VSS) requires p…