9 papers
Authentic Multinational Federated Time-to-Event Analyses Among People with HIV in Latin America
Kaixing Liu, Zhuohui J. Liang, Fabio Paredes +12
Multinational HIV cohort studies face regulatory barriers to cross-border sharing of individual participant data, limiting centralized pooled analyses. Federated statistical method…
SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation
Nie Lin, Takehiko Ohkawa, Sijin Chen +10
Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually benefits dexterous manipulatio…
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
Zhuohang Li, Liqun Huang, Wei Xu +5
Vision-Language-Action (VLA) models are prone to compounding errors in dexterous manipulation, where high-dimensional action spaces and contact-rich dynamics amplify small policy d…
WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
Yu Shang, Yinzhou Tang, Yiding Ma +22
World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, ex…
Token-weighted Direct Preference Optimization with Attention
Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1
Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses e…
Judging with Confidence: Calibrating Autoraters to Preference Distributions
Zhuohang Li, Xiaowei Li, Chengyu Huang +11
The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limite…