Min Zhang

FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits

OmniEduBench: A Comprehensive Chinese Benchmark for Assessing Large Language Models in Education

From Coefficients to Directions: Rethinking Model Merging with Directional Alignment

T-POP: Test-Time Personalization with Online Preference Feedback

EduDial: Constructing a Large-scale Multi-turn Teacher–Student Dialogue Corpus

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport

Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge

ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models

CALM: Consensus-Aware Localized Merging for Multi-Task Learning

REMEDY: Recipe Merging Dynamics in Large Vision-Language Models

Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models