arxiv:2607.24027
Song
songhan
AI & ML interests
efficient AI computing
Recent Activity
authored a paper about 13 hours ago
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization upvoted a paper 3 days ago
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution authored a paper 25 days ago
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention SparsificationOrganizations
arxiv:2607.21553
arxiv:2607.05722
arxiv:2606.23743
arxiv:2606.02800
arxiv:2606.02553
arxiv:2605.30409
arxiv:2605.18739
arxiv:2605.15178
arxiv:2605.13724
arxiv:2602.02958
arxiv:2509.25182
arxiv:2509.24695
arxiv:2509.22622
arxiv:2508.00413
arxiv:2503.16428
arxiv:2503.09641
arxiv:2502.14866
arxiv:2501.18427
arxiv:2410.10733
arxiv:2410.10629
arxiv:2407.18908
arxiv:2407.17453
arxiv:2406.10774
arxiv:2402.10193
arxiv:2312.07533
arxiv:2310.17752
arxiv:2309.12307
arxiv:2204.10319
