10 papers
CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
Ao Sun, Xiaoyu Wang, Zhe Tan +4
As Large Language Models (LLMs) serve a global audience, alignment must transition from enforcing universal consensus to respecting cultural pluralism. We demonstrate that dense mo…
Refine and Purify: Orthogonal Basis Optimization with Null-Space Denoising for Conditional Representation Learning
Jiaquan Wang, Yan Lyu, Chen Li +1
Conditional representation learning aims to extract criterion-specific features for customized tasks. Recent studies project universal features onto the conditional feature subspac…
FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation
Muqing Liu, Chongjie Si, Yuheng Jia
Large pre-trained models achieve remarkable success across diverse domains, yet fully fine-tuning incurs prohibitive computational and memory costs. Parameter-efficient fine-tuning…
Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning
Yaxin Hou, Bo Han, Yuheng Jia +2
Current long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.…
DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning
Bo Han, Zhuoming Li, Xiaoyu Wang +4
Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data in multi-label learning (MLL) by leveraging unlabeled data to improve the model's…
ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering
Xinyue Wang, Yuheng Jia, Hui Liu +1
Typical deep clustering methods, while achieving notable progress, can only provide one clustering result per dataset. This limitation arises from their assumption of a fixed under…