Leilei Gan

Don't Just Fine-tune the Agent, Tune the Environment

V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking

Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning

Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers

Backdoor Attacks for LLMs with Weak-To-Strong Knowledge Distillation