AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
☆297May 5, 2026Updated 2 months ago
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:
- ☆181Jun 8, 2026Updated last month
- Cambrian-S: Towards Spatial Supersensing in Video☆564Apr 3, 2026Updated 4 months 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☆113May 3, 2026Updated 3 months ago
- Recursive Visual Programming (ECCV 2024)☆18Nov 20, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A simple video streaming baseline that outperforms SOTAs.☆156May 1, 2026Updated 3 months ago
- Official implementation of the paper "TOKENTRIM: INFERENCE-TIME TOKEN PRUNING FOR AUTOREGRESSIVE LONG VIDEO GENERATION"☆15Feb 8, 2026Updated 5 months ago
- NVIDIA FastGen: Fast Generation from Diffusion Models☆918Jul 24, 2026Updated last week
- Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"☆179May 9, 2026Updated 2 months ago
- Evaluation code for "Benchmarking Visual State Tracking in Multimodal Video Understanding"☆38Jun 3, 2026Updated 2 months ago
- Official FlashDecoder Github☆18Apr 4, 2026Updated 4 months ago
- Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence☆391Jun 20, 2026Updated last month
- ☆56Nov 6, 2025Updated 8 months ago
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders☆255Feb 13, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Real-Time Physical Action-Conditioned Video Generation☆219Mar 6, 2026Updated 4 months ago
- [ICML'26] Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis☆696May 23, 2026Updated 2 months ago
- [ICML 2026] Pytorch implementation of Self-Refining Video Sampling☆185May 1, 2026Updated 3 months ago
- [CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens☆219Jul 17, 2026Updated 2 weeks ago
- Tempo: Small Vision-Language Models are Smart Compressors for Long Video Understanding, ECCV 2026☆78Jul 26, 2026Updated last week
- ☆20Jul 22, 2026Updated last week
- StreamingVLM: Real-Time Understanding for Infinite Video Streams☆1,055Oct 15, 2025Updated 9 months ago
- [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control☆825Jun 9, 2025Updated last year
- State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!☆2,332Apr 13, 2026Updated 3 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- AllTracker is a model for tracking all pixels in a video.☆422May 8, 2026Updated 2 months ago
- Official implementation of "Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model" (CVPR 2026)☆64Mar 9, 2026Updated 4 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,424Mar 23, 2026Updated 4 months ago
- [NeurIPS'24] Large Spatial Model: End-to-end Unposed Images to Semantic 3D☆236Feb 11, 2026Updated 5 months ago
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆489Apr 16, 2026Updated 3 months ago
- Streaming Video Instruction Tuning☆84Feb 25, 2026Updated 5 months ago
- Echo: "Constantly Improving Image Models Need Constantly Improving Benchmarks" (ICLR 2026)☆20Jan 29, 2026Updated 6 months ago
- Full model implementation for Flow Equivariant World Models (ICML 2026), world models with memory for dynamic scenes☆54Updated this week
- Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"☆741Jul 10, 2026Updated 3 weeks ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Scaling Vision Pre-Training to 4K Resolution☆226Jan 4, 2026Updated 7 months ago
- Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation☆739Jul 22, 2026Updated last week
- PISCO: Precise Video Instance Insertion with Sparse Control☆59Feb 13, 2026Updated 5 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆381Feb 21, 2026Updated 5 months ago
- ☆304May 20, 2026Updated 2 months ago
- The first multiplayer video world model in Minecraft☆221Mar 3, 2026Updated 5 months ago
- Cambrian-P: Pose-Grounded Video Understanding☆104Jul 28, 2026Updated last week