4 papers
RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance
Dongchi Huang, Hongyin Zhang, Bohan Hou +12
General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from large-scale heterogeneous corp…
AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment
Weijie Kong, Zhian Su, Wei Yu +1
Recent advances in Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation. However, the visual representations of most VLA models…
SID: Sliding into Distribution for Robust Few-Demonstration Manipulation
Yicheng Ma, Wei Yu, Zhian Su +2
Generalizing robotic manipulation across object poses, viewpoints, and dynamic disturbances is difficult, especially with only a few demonstrations. End-to-end visuomotor policies…
IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation
Zhian Su, Weijie Kong, Haonan Dong +1
Vision-Language-Action (VLA) models have demonstrated significant potential for generalist robotic policies; however, they struggle to generalize to long-horizon complex tasks in n…