Fei Zhu

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training

One Patch Doesn’t Fit All: Adaptive Patching for Native-Resolution Multimodal Large Language Models

MLLM-CL: Continual Learning for Multimodal Large Language Models

Routing-Deconstructed LoRA in Federated Fine-Tuning

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

Gradient-Guided Epsilon Constraint Method for Online Continual Learning

C-CLIP: Multimodal Continual Learning for Vision-Language Model

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

Towards Flexible and Controllable Unknown Rejection

DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning

Dual-Modality Guided Prompt for Continual Learning of Large Multimodal Models