arXiv 2610.06801 · cs.CV · 2026-10-05
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Jiarui Chen, Zeqiang Lai, Jiangshan Wang, Ziheng Ouyang, Ye Huang, Xiangyu Yue, Cewu Lu, Chunchao Guo
Tencent Hunyuan
In latest · #179 Added on 2026-10-21
One-line takeaway
MC-Sparse is training-free sparse attention that selects individual KV tokens with cached compensation, closing the dense-sparse gap in DiTs.
MC-Sparse 免训练地逐个挑选 KV token 并缓存补偿，缩小扩散 Transformer 稀疏与稠密注意力的质量差。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Visual generation
- MaLiang-Harness: A Programmable Path to Image and Video Generation ▲367
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation ▲364
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models ▲325
- UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation ▲197
- Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds ▲182
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.