Skip navigation
🚀 Introducing Sparse VideoGen2 (SVG2) — Pareto-frontier video generation acceleration with…
0:00 / 0:12

🚀 Introducing Sparse VideoGen2 (SVG2) — Pareto-frontier video generation acceleration with…

Haocheng Xi

@HaochengXiUCB1.6K followers

Visit on X

43,470 views #NeurIPS2025

🚀 Introducing Sparse VideoGen2 (SVG2) — Pareto-frontier video generation acceleration with semantic-aware sparse attention! 🏆Spotlight paper accepted by #NeurIPS2025 ✅ Training-free & plug-and-play ✅ Up to 2.5× faster on HunyuanVideo, 1.9× faster on Wan 2.1 ✅ SOTA quality preserved (no artifacts, no flickering, no distortion) 📚Paper: 💻Code: 🌐Website: ⚡Attention Kernel: Joint work with: @randwalk0 Yilong Zhao Muyang Li Jintao Zhang Han Cai Yujun Lin Xiuyu Li Chenfeng_X Kelly Peng Jianfei Chen Song Han Kurt Keutzer Ion Stoica See details below ⬇️ (1/6) NeurIPS Conference #NeurIPS #VideoGeneration #GenerativeAI #MachineLearning #EfficientAI #OpenSource

Comments

Comments from the original post on X (Twitter)

No comments yet