5 papers
Progressively Learning Heterogeneous Skills in a Unified Latent Space
Yue-Yi Zhang, Ming Gong, Linpu He +2
We propose HetSkills, a novel framework designed to progressively learn heterogeneous skills within a unified latent space for physics-based character control. The core idea is to…
Bridging Domain Expertise and Generalization for Performance Estimation
Shuxuan Li, Zhilin Zhao, Quyu Kong +1
Performance estimation under distribution shift aims to predict how a model behaves on an unlabeled test set whose distribution differs from the training data, a scenario that requ…
UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference
Lang Zhou, Shuxuan Li, Zhuohao Li +3
Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates this limitation by a…
DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors
Yanqi Wu, Qichao Chen, Runhe Lai +5
Out-of-distribution (OOD) detection remains a fundamental challenge for deep neural networks, particularly due to overconfident predictions on unseen OOD samples during testing. We…
Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations
Wei-Jin Huang, Yue-Yi Zhang, Yi-Lin Wei +5
Enabling humanoid robots to physically interact with humans is a critical frontier, but progress is hindered by the scarcity of high-quality Human-Humanoid Interaction (HHoI) data.…