arxiv:2607.24027
Song
songhan
AI & ML interests
efficient AI computing
Recent Activity
authored a paper 4 days ago
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification authored a paper 4 days ago
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation authored a paper 11 days ago
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation DecodingOrganizations
models 0
None public yet
datasets 0
None public yet