Didi Zhu

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

C-Flat Turbo: A Faster Path to Continual Learning

Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

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

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

REMEDY: Recipe Merging Dynamics in Large Vision-Language Models

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

Improving Group Connectivity for Generalization of Federated Deep Learning