AI.info

Hongyu Li

Explore Hongyu Li on AI.info.

• LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
• LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
• OneThinker: All-in-one Reasoning Model for Image and Video
• AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model
• Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation