5 papers
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
Jindi Lv, Hao Li, Jie Li +11
Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due to partial observability and…
EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement
Zitong Xu, Huiyu Duan, Yifei Nie +9
Recent text-guided image editing (TIE) models have made remarkable progress, yet edited images still frequently suffer from fine-grained issues such as unnatural objects, lighting…
TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning
Zhenan Wang, Yanzhe Wang, Meixuan Ren +8
In visually ambiguous manipulation such as detecting button click tactile feedback is often the sole source of ground truth. However, fusing tactile data poses a significant challe…
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
GigaBrain Team, Boyuan Wang, Bohan Li +23
Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and we…
Task-Centric Policy Optimization from Misaligned Motion Priors
Ziang Zheng, Kai Feng, Yi Nie +1
Humanoid control often leverages motion priors from human demonstrations to encourage natural behaviors. However, such demonstrations are frequently suboptimal or misaligned with r…