AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
☆305Sep 13, 2026Updated last week
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☆569Apr 3, 2026Updated 5 months ago
- Foundation models for 4D spatial and temporal vision tasks.☆303Updated this week
- 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☆115May 3, 2026Updated 4 months ago
- Recursive Visual Programming (ECCV 2024)☆18Nov 20, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A simple video streaming baseline that outperforms SOTAs.☆167May 1, 2026Updated 4 months ago
- Official implementation of the paper "TOKENTRIM: INFERENCE-TIME TOKEN PRUNING FOR AUTOREGRESSIVE LONG VIDEO GENERATION"☆15Feb 8, 2026Updated 7 months ago
- NVIDIA FastGen: Fast Generation from Diffusion Models☆1,005Aug 21, 2026Updated 3 weeks ago
- Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"☆184May 9, 2026Updated 4 months ago
- Evaluation code for "Benchmarking Visual State Tracking in Multimodal Video Understanding"☆46Aug 12, 2026Updated last month
- Official FlashDecoder Github☆19Apr 4, 2026Updated 5 months ago
- Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence☆400Jun 20, 2026Updated 3 months ago
- ☆56Nov 6, 2025Updated 10 months ago
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders☆263Feb 13, 2026Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Real-Time Physical Action-Conditioned Video Generation☆228Mar 6, 2026Updated 6 months ago
- [ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis☆766May 23, 2026Updated 3 months ago
- [ICML 2026] Pytorch implementation of Self-Refining Video Sampling☆186May 1, 2026Updated 4 months ago
- [CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens☆260Jul 17, 2026Updated 2 months ago
- Tempo: Small Vision-Language Models are Smart Compressors for Long Video Understanding, ECCV 2026☆84Jul 26, 2026Updated last month
- StreamingVLM: Real-Time Understanding for Infinite Video Streams☆1,083Oct 15, 2025Updated 11 months ago
- ☆27Jul 22, 2026Updated last month
- [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control☆838Jun 9, 2025Updated last year
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,367Apr 13, 2026Updated 5 months ago
- 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.
- AllTracker is a model for tracking all pixels in a video.☆429May 8, 2026Updated 4 months ago
- Official implementation of "Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model" (CVPR 2026)☆68Mar 9, 2026Updated 6 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,654Mar 23, 2026Updated 5 months ago
- [NeurIPS'24] Large Spatial Model: End-to-end Unposed Images to Semantic 3D☆238Feb 11, 2026Updated 7 months ago
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆498Apr 16, 2026Updated 5 months ago
- Streaming Video Instruction Tuning☆89Feb 25, 2026Updated 6 months ago
- Full model implementation for Flow Equivariant World Models (ICML 2026), world models with memory for dynamic scenes☆59Jul 29, 2026Updated last month
- Echo: "Constantly Improving Image Models Need Constantly Improving Benchmarks" (ICLR 2026)☆20Jan 29, 2026Updated 7 months ago
- Scaling Vision Pre-Training to 4K Resolution☆225Jan 4, 2026Updated 8 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"☆756Jul 10, 2026Updated 2 months ago
- Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation☆755Jul 22, 2026Updated last month
- PISCO: Precise Video Instance Insertion with Sparse Control☆61Feb 13, 2026Updated 7 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆393Feb 21, 2026Updated 6 months ago
- The first multiplayer video world model in Minecraft☆229Mar 3, 2026Updated 6 months ago
- Cambrian-P: Pose-Grounded Video Understanding☆113Jul 28, 2026Updated last month
- ☆310May 20, 2026Updated 3 months ago