collaborators

6 papers

cs.LG2025

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment

Zhikang Chen, Sen Cui, Deheng Ye +5

Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstr…

cs.CL2025

Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective

Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai +8

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised seriou…

cs.CV2025

What Makes "Good" Distractors for Object Hallucination Evaluation in Large Vision-Language Models?

Ming-Kun Xie, Jia-Hao Xiao, Gang Niu +4

Large Vision-Language Models (LVLMs), empowered by the success of Large Language Models (LLMs), have achieved impressive performance across domains. Despite the great advances in L…

cs.CV2025

Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation

Jie Xu, Na Zhao, Gang Niu +2

Recently, multi-view learning (MVL) has garnered significant attention due to its ability to fuse discriminative information from multiple views. However, real-world multi-view dat…

cs.LG2025

Accurate Forgetting for Heterogeneous Federated Continual Learning

Abudukelimu Wuerkaixi, Sen Cui, Jingfeng Zhang +6

Recent years have witnessed a burgeoning interest in federated learning (FL). However, the contexts in which clients engage in sequential learning remain under-explored. Bridging F…

cs.LG2025

Label Distribution Learning with Biased Annotations by Learning Multi-Label Representation

Zhiqiang Kou, Si Qin, Hailin Wang +6

Multi-label learning (MLL) has gained attention for its ability to represent real-world data. Label Distribution Learning (LDL), an extension of MLL to learning from label distribu…