Efficient AI
Efficient AI
News
Blog
Publications
Light
Dark
Automatic
Wei Huang
Latest
Autoregressive Video Gen
Pushing Intelligence to 4-bit
KV Cache Compression and Its Infra Problems
Scaling Video Training with Parallelism
Why Video Gen Is an Infra Problem
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
LongLive: Real-time Interactive Long Video Generation
QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs
Scaling RL to Long Videos
Cite
×