AI.info

Yan Zhang

Explore Yan Zhang on AI.info.

• CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets
• Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
• Bilevel Layer-Positioning LoRA for Real Image Dehazing
• UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment
• LTD-Bench: Evaluating Large Language Models by Letting Them Draw
• Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding