7 papers
Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels
Yaqi Zhao, Haoliang Sun, Yating Wang +2
Prompt learning has gained significant attention as a parameter-efficient approach for adapting large pre-trained vision-language models to downstream tasks. However, when only par…
EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp Generation
Yukun Zhao, Zichen Zhong, Yongshun Gong +2
Denoising generative models have recently become the dominant paradigm for dexterous grasp generation, owing to their ability to model complex grasp distributions from large-scale…
Riemannian MeanFlow for One-Step Generation on Manifolds
Zichen Zhong, Haoliang Sun, Yukun Zhao +2
Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE.…
TSRE: Channel-Aware Typical Set Refinement for Out-of-Distribution Detection
Weijun Gao, Rundong He, Jinyang Dong +1
Out-of-Distribution (OOD) detection is a critical capability for ensuring the safe deployment of machine learning models in open-world environments, where unexpected or anomalous i…
Diverse Teacher-Students for Deep Safe Semi-Supervised Learning under Class Mismatch
Qikai Wang, Rundong He, Yongshun Gong +4
Semi-supervised learning can significantly boost model performance by leveraging unlabeled data, particularly when labeled data is scarce. However, real-world unlabeled data often…
CLIP-driven Outliers Synthesis for few-shot OOD detection
Hao Sun, Rundong He, Zhongyi Han +3
Few-shot OOD detection focuses on recognizing out-of-distribution (OOD) images that belong to classes unseen during training, with the use of only a small number of labeled in-dist…