AI.info

Bin Li

Explore Bin Li on AI.info.

• Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
• Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
• InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
• Generative Latent Coding for Ultra-Low Bitrate Image Compression
• Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs
• Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
• CoD: A Diffusion Foundation Model for Image Compression
• OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and Understanding
• Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models
• Adaptive Morph-Patch Transformer for Aortic Vessel Segmentation
• KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls
• MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models