Song

songhan

·

https://songhan.mit.edu

AI & ML interests

efficient AI computing

Recent Activity

authored a paper 11 days ago

SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video

authored a paper 11 days ago

Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge

authored a paper 23 days ago

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

View all activity

Organizations

upvoted a paper about 2 months ago

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published Aug 17 • 113

upvoted a collection 11 months ago

SANA-Video

🎬 SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer • 11 items • Updated Aug 20 • 12

upvoted a paper 12 months ago

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Paper • 2510.15870 • Published Oct 17, 2025 • 93

upvoted 2 papers about 1 year ago

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

Paper • 2509.24695 • Published Sep 29, 2025 • 56

Scaling RL to Long Videos

Paper • 2507.07966 • Published Jul 10, 2025 • 160

upvoted a paper almost 2 years ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 62