Efficient Intelligence and Systems

AI & ML interests

Low-bit Quantization of Large Language Models (LLMs)

Recent Activity

AaronHuangWei  authored a paper 2 days ago

Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion

AaronHuangWei  authored a paper 2 days ago

SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

AaronHuangWei  authored a paper 2 days ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

View all activity

Team members 9