AI.info

Zhe Li

Explore Zhe Li on AI.info.

• CoCo-IR: Contextual Composed Image Retrieval
• Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
• Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
• ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking
• MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model
• BLM$_1$: A Boundless Large Model for Cross-Space, Cross-Task, and Cross-Embodiment Learning