6 papers
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…
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…
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…
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…
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…
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…