activity
20242026
collaborators

5 papers

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…

cs.LG2025

Impact of Noisy Supervision in Foundation Model Learning

Hao Chen, Zihan Wang, Ran Tao +5

Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inacces…

cs.LG2025

Realistic Evaluation of Deep Partial-Label Learning Algorithms

Wei Wang, Dong-Dong Wu, Jindong Wang +3

Partial-label learning (PLL) is a weakly supervised learning problem in which each example is associated with multiple candidate labels and only one is the true label. In recent ye…

cs.CV2024

Slight Corruption in Pre-training Data Makes Better Diffusion Models

Hao Chen, Yujin Han, Diganta Misra +6

Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on…

cs.LG2024

A General Framework for Learning from Weak Supervision

Hao Chen, Jindong Wang, Lei Feng +6

Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algor…