4 papers
Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
Anthony Liang, Yigit Korkmaz, Jiahui Zhang +14
General-purpose robot reward models are typically trained to predict absolute task progress from expert demonstrations, providing only local, frame-level supervision. While effecti…
Retrospex: Language Agent Meets Offline Reinforcement Learning Critic
Yufei Xiang, Yiqun Shen, Yeqin Zhang +1
Large Language Models (LLMs) possess extensive knowledge and commonsense reasoning capabilities, making them valuable for creating powerful agents. However, existing LLM agent fram…
Continual Distillation Learning for Rehearsal-Free Class-Incremental Learning via Decoupled Prompting
Qifan Zhang, Yunhui Guo, Yu Xiang
Prompt-based continual learning has shown strong performance in rehearsal-free class-incremental learning by adapting learnable prompts while freezing a pre-trained Vision Transfor…
HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction
Jikai Wang, Qifan Zhang, Yu-Wei Chao +3
We introduce a data capture system and a new dataset, HO-Cap, for 3D reconstruction and pose tracking of hands and objects in videos. The system leverages multiple RGBD cameras and…