[NeurIPS 2026] Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers
☆48Jul 1, 2026Updated 4 months ago
Alternatives and similar repositories for piecewise-sparse-attention
Users that are interested in piecewise-sparse-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official code of "Mano: Restriking Manifold Optimization for LLM Training".☆27Jun 1, 2026Updated 5 months ago
- [ICML 2026] The official code for our work "LIVEditor-14B: Lightning Unified Video Editor via In-Context Sparse Attention".☆40May 15, 2026Updated 6 months ago
- Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer☆16Nov 21, 2024Updated last year
- [TPAMI] The official implementation of our paper "Improved and Accelerated Text-to-Image Generation with Collect, Reflect, and Refine".☆30Mar 8, 2026Updated 8 months ago
- [ICLR2026] The official code of "Weak-to-Strong Diffusion with Reflection".☆59Jan 28, 2026Updated 9 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICLR2025] IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis☆39Feb 17, 2025Updated last year
- ☆16May 2, 2026Updated 6 months ago
- Piecewise-Taylor Attention☆48Aug 4, 2026Updated 3 months ago
- [ICLR2025] The code of Z-Sampling, proposed in our paper "Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflectio…☆104May 20, 2026Updated 5 months ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆65Jul 1, 2025Updated last year
- [ICML 2026][Ultra Powerful Few-Step Diffusion RL] TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward☆125May 25, 2026Updated 5 months ago
- The official implementation of "Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation"☆25Feb 8, 2026Updated 9 months ago
- Implementation of "FlashPreill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling"☆57Apr 27, 2026Updated 6 months ago
- The official code repository for "Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Spa…☆26Jun 9, 2026Updated 5 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Triton implement of bi-directional (non-causal) linear attention☆84Aug 10, 2026Updated 3 months ago
- Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers☆24May 26, 2026Updated 5 months ago
- [ICLR 2026] Official implementation of "Enhancing Multi-Image Understanding Through Delimiter Token Scaling"☆19Jul 10, 2026Updated 4 months ago
- ☆37Mar 24, 2026Updated 7 months ago
- Sparsity as a Variance Regulator for Improved Depth Utilization in Language Models☆16May 11, 2026Updated 6 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆609Nov 11, 2025Updated last year
- [CVPR-26] Official repository of "CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization"☆20Mar 9, 2026Updated 8 months ago
- [CVPR 2026 Highlight] Official implementation of Log-linear Sparse Attention (LLSA).☆94May 1, 2026Updated 6 months ago
- [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".☆199Mar 17, 2026Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆18Mar 10, 2026Updated 8 months ago
- Official repository for AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers. Code coming soon.☆30Nov 11, 2026Updated last week
- [AAAI 2026] Offical implementation of the paper "IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generat…☆13Jul 27, 2026Updated 3 months ago
- [CVPR 2026] IOMM: Fast Pre-training of Unified Multimodal Models without Text-Image Pairs☆26Apr 11, 2026Updated 7 months ago
- Mamba SSM architecture that supports training on variable-length sequences. Implementation of ECCV24' <PackMamba: Efficient processing of…☆12Sep 24, 2026Updated last month
- CoTj (Chain-of-Trajectories) upgrades diffusion models from fixed System-1 denoising schedules to System-2 style, condition-adaptive traj…☆23Mar 24, 2026Updated 7 months ago
- Anemoi is a high-performance serving framework for transformer-based video generation models.☆53Sep 29, 2026Updated last month
- FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving☆12Aug 3, 2026Updated 3 months ago
- [ICLR 2026🔥] MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head☆161May 19, 2026Updated 6 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆87Jul 3, 2026Updated 4 months ago
- [CVPR 2026 Findings] V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think☆56Apr 28, 2026Updated 6 months ago
- Learning Native Reflection in Unified Models: reflection SFT and multi-round Flow-GRPO RL for BAGEL☆34Oct 20, 2026Updated 3 weeks ago
- Training-free inference acceleration framework for interactive video world models, with tested support for HY-WorldPlay and Matrix-Game-3…☆23Jun 18, 2026Updated 5 months ago
- ☆17Aug 30, 2026Updated 2 months ago
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆554Oct 18, 2026Updated last month
- 3DSceneBench: a benchmark that tests whether coding agents can build simulated worlds that support a scene's many uses.☆27Updated this week
Are these results useful?