Espere-1119-Song / VideoNSALinks
VideoNSA: Native Sparse Attention Scales Video Understanding
☆65Updated 2 weeks ago
Alternatives and similar repositories for VideoNSA
Users that are interested in VideoNSA are comparing it to the libraries listed below
Sorting:
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆40Updated 9 months ago
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…☆53Updated 8 months ago
- ☆39Updated 6 months ago
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆87Updated last year
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆72Updated last year
- [ICCV 2025] Dynamic-VLM☆26Updated 11 months ago
- ☆79Updated 5 months ago
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆72Updated 2 months ago
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆40Updated 8 months ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆94Updated 9 months ago
- Implementation for "The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer"☆73Updated last month
- ☆64Updated 6 months ago
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆49Updated 5 months ago
- The code for "VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation" [CVPR2025]☆20Updated 9 months ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆173Updated last week
- [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark☆133Updated 6 months ago
- [ICLR2025] MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models☆90Updated last year
- [NeurIPS 2024 D&B Track] Official Repo for "LVD-2M: A Long-take Video Dataset with Temporally Dense Captions"☆73Updated last year
- The official repo of continuous speculative decoding☆30Updated 8 months ago
- [ICLR 2025] Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding☆47Updated 7 months ago
- ☆63Updated 4 months ago
- [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegr…☆79Updated 11 months ago
- Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment☆62Updated 4 months ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆55Updated 5 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆78Updated 4 months ago
- ☆94Updated 5 months ago
- High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning☆52Updated 4 months ago
- Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]☆95Updated 4 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆58Updated 11 months ago
- ☆135Updated last month