AI.info

Song Han

Explore Song Han on AI.info.

• Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing
• Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
• Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
• FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos
• VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
• Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
• ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
• OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
• QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
• StreamingVLM: Real-Time Understanding for Infinite Video Streams