Song
songhan
AI & ML interests
efficient AI computing
Recent Activity
upvoted a paper about 14 hours ago
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution authored a paper 22 days ago
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification authored a paper 22 days ago
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video GenerationOrganizations
