Skip to content
conftrace_
2025 ICML ICML 2025

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Wenke Huang, Jian Liang, Guancheng Wan, Didi Zhu, He Li, Jiawei Shao, Mang Ye, Bo Du, Dacheng Tao

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Optimization & Theory > Optimization Artificial Intelligence > Core AI > Large Language Models

Keywords

multi-task fine-tuning gaussian perturbation confidence alignment overfitting open-response datasets visual behavioral cues
Download PDF