Yongtao Wu

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

Linear Attention for Efficient Bidirectional Sequence Modeling

Quantum-PEFT: Ultra parameter-efficient fine-tuning

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Multi-Step Preference Optimization via Two-Player Markov Games

LION: A bidirectional framework that trains like a Transformer and infers like an RNN

Imbalance-Regularized LoRA: A Plug-and-Play Method for Improving Fine-Tuning of Foundation Models