Junwei Han

Cross-Architecture Knowledge Distillation via Information Alignment

Bidirectional Hierarchical Reasoning for Fine-grained Visual Recognition

Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers

3D-CT-GPT++: Enhancing 3D Radiology Report Generation with Direct Preference Optimization and Large Vision-Language Models

STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization

EpilepsyFM: Foundation Model for Learning Generalized Epileptic Representations from EEG and SEEG Signals

Brain-like Functional Organization within Large Language Models