Han Hu

From Coarse to Fine: Recursive Audio-Visual Semantic Enhancement for Speech Separation

H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learning

Branching Memory: Task-Specific Expansion for Continual Learning in Large Language Models

MixPrompt: Efficient Mixed Prompting for Multimodal Semantic Segmentation

Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs

Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging

Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision

Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients

FusionBench: A Comprehensive Benchmark of Deep Model Fusion

Empirical Study on Enhancing Efficiency in Masked Image Modeling Pre-training

Targeted Low-rank Refinement: Enhancing Sparse Neural Networks with Precision