activity
20242026
collaborators

15 papers

cs.LG2026

Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions

Wei Wang, Gang Niu, Masashi Sugiyama

Deep learning has achieved great success in recent years thanks to the availability of high-quality, well-annotated training data. However, this requirement is often not met in rea…

cs.LG2026

CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models

Ruijiang Dong, Zesheng Ye, Jianzhong Qi +4

Pre-trained vision-language models (VLMs) enable zero-shot image classification by computing the similarity score between an image and textual descriptions, typically formed by ins…

cs.LG2026

Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators

Tongtong Fang, Nan Lu, Gang Niu +2

Importance weighting (IW) is a golden solver for joint distribution shift, where the joint distributions differ between the training and test data. To solve this problem, IW estima…

cs.LG2026

Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes

Tan-Ha Mai, Chao-Kai Chiang, Han-Hwa Shih +3

Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain…

cs.LG2026

What Is Preference Optimization Doing, and Why?

Yue Wang, Qizhou Wang, Zizhuo Zhang +3

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) ach…

cs.CL2026

Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning

Bing Wang, Ximing Li, Changchun Li +3

Recently, the prominent performance of large language models (LLMs) has been largely driven by multi-task instruct-tuning. Unfortunately, this training paradigm suffers from a key…