Shilin Yan
- Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
- GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing
- MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
- T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
- UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens