AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
☆309Sep 13, 2026Updated last month
Alternatives and similar repositories for AutoGaze
Users that are interested in AutoGaze are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Cambrian-S: Towards Spatial Supersensing in Video☆570Apr 3, 2026Updated 6 months ago
- Foundation models for 4D spatial and temporal vision tasks.☆383Oct 1, 2026Updated 2 weeks ago
- Official Implementation for our NeurIPS 2024 paper, "Don't Look Twice: Run-Length Tokenization for Faster Video Transformers".☆238Mar 29, 2025Updated last year
- Official Repository of VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents☆117May 3, 2026Updated 5 months ago
- Recursive Visual Programming (ECCV 2024)☆19Nov 20, 2024Updated last year
- 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.
- A simple video streaming baseline that outperforms SOTAs.☆173May 1, 2026Updated 5 months ago
- Official implementation of the paper "TOKENTRIM: INFERENCE-TIME TOKEN PRUNING FOR AUTOREGRESSIVE LONG VIDEO GENERATION"☆15Feb 8, 2026Updated 8 months ago
- NVIDIA FastGen: Fast Generation from Diffusion Models☆1,030Aug 21, 2026Updated last month
- Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"☆185May 9, 2026Updated 5 months ago
- Evaluation code for "Benchmarking Visual State Tracking in Multimodal Video Understanding"☆48Oct 2, 2026Updated last week
- Official FlashDecoder Github☆20Apr 4, 2026Updated 6 months ago
- Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence☆403Jun 20, 2026Updated 3 months ago
- ☆56Nov 6, 2025Updated 11 months ago
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders☆266Feb 13, 2026Updated 8 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Real-Time Physical Action-Conditioned Video Generation☆229Mar 6, 2026Updated 7 months ago
- [ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis☆776May 23, 2026Updated 4 months ago
- [ICML 2026] Pytorch implementation of Self-Refining Video Sampling☆190May 1, 2026Updated 5 months ago
- [CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens☆272Jul 17, 2026Updated 2 months ago
- Tempo: Small Vision-Language Models are Smart Compressors for Long Video Understanding, ECCV 2026☆85Jul 26, 2026Updated 2 months ago
- StreamingVLM: Real-Time Understanding for Infinite Video Streams☆1,095Oct 15, 2025Updated last year
- ☆32Jul 22, 2026Updated 2 months ago
- [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control☆846Jun 9, 2025Updated last year
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,382Apr 13, 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.
- AllTracker is a model for tracking all pixels in a video.☆431May 8, 2026Updated 5 months ago
- 🔥🔥🔥 [Awesome] Latest Papers, Codes & Datasets on Streaming / Online Video Understanding — Building Always-on, Real-time Video AI 🤖☆475Aug 5, 2026Updated 2 months ago
- Official implementation of "Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model" (CVPR 2026)☆70Mar 9, 2026Updated 7 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,765Mar 23, 2026Updated 6 months ago
- [NeurIPS'24] Large Spatial Model: End-to-end Unposed Images to Semantic 3D☆240Feb 11, 2026Updated 8 months ago
- Streaming Video Instruction Tuning☆93Feb 25, 2026Updated 7 months ago
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆499Apr 16, 2026Updated 5 months ago
- Full model implementation for Flow Equivariant World Models (ICML 2026), world models with memory for dynamic scenes☆62Jul 29, 2026Updated 2 months ago
- Echo: "Constantly Improving Image Models Need Constantly Improving Benchmarks" (ICLR 2026)☆20Sep 22, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Scaling Vision Pre-Training to 4K Resolution☆225Jan 4, 2026Updated 9 months ago
- Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"☆760Jul 10, 2026Updated 3 months ago
- Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation☆758Jul 22, 2026Updated 2 months ago
- [NeurIPS 2026] PISCO: Precise Video Instance Insertion with Sparse Control☆63Sep 30, 2026Updated 2 weeks ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆398Feb 21, 2026Updated 7 months ago
- The first multiplayer video world model in Minecraft☆230Mar 3, 2026Updated 7 months ago
- ☆310May 20, 2026Updated 4 months ago