The official code repository for "Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering" [ICML 26]
☆20Jun 9, 2026Updated last month
Alternatives and similar repositories for SVOO
Users that are interested in SVOO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Awesome Video Diffusion Transformers Sparse Attention Papers☆42May 30, 2026Updated 2 months ago
- Genie Envisioner World Simulator 2.0 (GE-Sim 2.0)☆122Jun 25, 2026Updated last month
- [ECCV 2022] Multiview Regenerative Morphing with Dual Flows☆12Sep 12, 2022Updated 3 years ago
- [ESEC/FSE'23] Hue: A User-Adaptive Parser for Hybrid Logs☆10Aug 24, 2023Updated 2 years ago
- ☆11Jan 19, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning☆22Jun 3, 2026Updated 2 months ago
- VGDFR: Diffuison-based Video Generation with Dynamic Frame Rate☆18May 16, 2025Updated last year
- Anderson points-to analysis implementation based on LLVM☆12Jan 3, 2021Updated 5 years ago
- ☆14Jul 23, 2024Updated 2 years ago
- Official PyTorch implementation of CPO: Change Robust Panorama to Point Cloud Localization (ECCV 2022)☆14Feb 26, 2024Updated 2 years ago
- The official implementation of "Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation"☆22Feb 8, 2026Updated 5 months ago
- FlashDreamer, a training-free approach for completing a 3D scene from a single image, significantly reducing the need for multi-view inpu…☆23Apr 9, 2025Updated last year
- Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”☆92Mar 25, 2026Updated 4 months ago
- ☆16Sep 26, 2017Updated 8 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆12Jul 7, 2023Updated 3 years ago
- MinT-2M: Long-context training system for resident-prefix GRPO☆41Jul 24, 2026Updated last week
- A simple SQL parser based on Apache Calcite.☆14May 8, 2026Updated 2 months ago
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆323Jun 23, 2026Updated last month
- Scaling Automated Database System Testing. ASPLOS'26☆16Apr 18, 2026Updated 3 months ago
- Official Code for 'AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction' (ICCV 2025)☆64Nov 8, 2025Updated 8 months ago
- ☆31Jul 11, 2026Updated 3 weeks ago
- ☆15Jul 23, 2025Updated last year
- Official WACV 2025 code for Point-GN: A non-parametric, training-free method for 3D point cloud classification using Gaussian Positional …☆15Jul 22, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Tool to design and optimize autonomous vehicle concepts.☆12Aug 29, 2022Updated 3 years ago
- ☆13Apr 9, 2024Updated 2 years ago
- A LiDAR-Derived Point Cloud Dataset of One Million English Buildings Linked to Energy Characteristics☆16Oct 6, 2023Updated 2 years ago
- 程考资料(C++)☆11Jan 16, 2019Updated 7 years ago
- LibQPEP-Enhanced ORB-SLAM3 System☆11Sep 12, 2021Updated 4 years ago
- Resnet-34 with light-weighted decoder for pose estimation. (Pytorch)☆21Sep 21, 2018Updated 7 years ago
- PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation (ECCV 2026)☆69Jun 20, 2026Updated last month
- Unofficial version of LaneExtraction☆13Oct 12, 2022Updated 3 years ago
- ☆18Jul 22, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Produce a "morph" animation of one image into another image.☆19Nov 1, 2017Updated 8 years ago
- ☆19Dec 12, 2024Updated last year
- ☆26Jun 10, 2022Updated 4 years ago
- ☆17Jan 3, 2024Updated 2 years ago
- Official implementation of "CU-Net: LiDAR Depth-only Completion with Coupled U-Net", RAL 2022.☆17Oct 13, 2022Updated 3 years ago
- ☆16Aug 16, 2024Updated last year
- Undistorted Depth Support for ScanNet++☆17Dec 8, 2023Updated 2 years ago