140 citations · 322 across the 13 of their papers we have counts for
14 papers
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
Yuwei Liang, Jian Liang, Dapeng Hu +2
Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance. Most existing calibration met…
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
Dong Yan, Jian Liang, Dapeng Hu +4
Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluati…
SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice
Tianfu Wang, Max Xiong, Jianxun Lian +9
Social skills such as negotiation and leadership are crucial for personal and professional success in today's interconnected world. However, scalable and effective training remains…
Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning
Yongcan Yu, Lingxiao He, Shuo Lu +10
Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away fro…
UMAD: Universal Model Adaptation under Domain and Category Shift
Jian Liang, Dapeng Hu, Jiashi Feng +1
Learning to reject unknown samples (not present in the source classes) in the target domain is fairly important for unsupervised domain adaptation (UDA). There exist two typical UD…
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Mi Luo, Fei Chen, Dapeng Hu +3
A central challenge in training classification models in the real-world federated system is learning with non-IID data. To cope with this, most of the existing works involve enforc…