8 papers
Heterogeneous Complementary Distillation
Liuchi Xu, Hao Zheng, Lu Wang +2
Knowledge distillation (KD)transfers the dark knowledge from a complex teacher to a compact student. However, heterogeneous architecture distillation, such as Vision Transformer (V…
Label Smoothing Improves Gradient Ascent in LLM Unlearning
Zirui Pang, Hao Zheng, Zhijie Deng +3
LLM unlearning has emerged as a promising approach, aiming to enable models to forget hazardous/undesired knowledge at low cost while preserving as much model utility as possible.…
OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
Hao Zheng, Zirui Pang, Ling li +5
Advances in Multimodal Large Language Models (MLLMs) intensify concerns about data privacy, making Machine Unlearning (MU), the selective removal of learned information, a critical…
MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
Md Zubair, Hao Zheng, Grayson W. Armstrong +5
Medical decision systems increasingly rely on data from multiple sources to ensure reliable and unbiased diagnosis. However, existing multimodal learning models fail to achieve thi…
Personalized Federated Dictionary Learning for Modeling Heterogeneity in Multi-site fMRI Data
Yipu Zhang, Chengshuo Zhang, Ziyu Zhou +5
Data privacy constraints pose significant challenges for large-scale neuroimaging analysis, especially in multi-site functional magnetic resonance imaging (fMRI) studies, where sit…
Hierarchical Cross-modal Prompt Learning for Vision-Language Models
Hao Zheng, Shunzhi Yang, Zhuoxin He +2
Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preservin…
Density Discontinuity Regression
Surya T Tokdar, Rik Sen, Haoliang Zheng +1
Many policies hinge on a continuous variable exceeding a threshold, prompting strategic behavior by agents to stay on the favorable side. This creates density discontinuities at cu…
Towards Trustworthy Unsupervised Domain Adaptation: A Representation Learning Perspective for Enhancing Robustness, Discrimination, and Generalization
Jia-Li Yin, Haoyuan Zheng, Ximeng Liu
Robust Unsupervised Domain Adaptation (RoUDA) aims to achieve not only clean but also robust cross-domain knowledge transfer from a labeled source domain to an unlabeled target dom…