AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
☆262Apr 20, 2026Updated 2 weeks 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:
- The implementation for FREE-Merging: Fourier Transform for Model Merging with Lightweight Experts (ICCV25)☆15Jun 26, 2025Updated 10 months ago
- super-resolution; post-training quantization; model compression☆14Nov 10, 2023Updated 2 years ago
- PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation☆23Jun 20, 2025Updated 10 months ago
- Code & data for "Towards flexible perception with visual memory" (ICML 2025)☆18Sep 24, 2024Updated last year
- ☆14Dec 11, 2025Updated 4 months ago
- 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.
- The official implementation of Latte: Latent Diffusion Transformer for Video Generation.☆35Feb 26, 2025Updated last year
- Evaluating Multiview Object Correspondence between Humans and Image models☆20Feb 12, 2025Updated last year
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding☆40Mar 16, 2025Updated last year
- ☆53Nov 6, 2025Updated 6 months ago
- 拡散モデルを学びたい初学者向けです。書籍「コンピュータビジョン最前線 Summer 2023」の「イマドキノ拡散モデル」の解説をベースに、CIFER-10で画像生成をします☆19Jul 2, 2023Updated 2 years ago
- PhysGame Benchmark for Physical Commonsense Evaluation in Gameplay Videos☆48Jul 3, 2025Updated 10 months ago
- ☆25Nov 17, 2025Updated 5 months ago
- ☆42Oct 23, 2025Updated 6 months ago
- Visual haptic using depth image☆19Dec 20, 2021Updated 4 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [NeurIPS 2022] (Amortized) distributional control for pre-trained generative models☆121Sep 4, 2023Updated 2 years ago
- real-to-sim evaluation suite for robot parkour☆11Jan 19, 2025Updated last year
- LatentMorph: Morphing Latent Reasoning into Image Generation☆40Mar 29, 2026Updated last month
- ☆15Jan 17, 2018Updated 8 years ago
- 🔥 [CVPR 2024] Official implementation of "See, Say, and Segment: Teaching LMMs to Overcome False Premises (SESAME)"☆46Jun 16, 2024Updated last year
- [ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"☆74Jan 13, 2026Updated 3 months ago
- Keras implementation of EfficientNet model for age and gender estimation☆14Mar 18, 2020Updated 6 years ago
- ☆57Mar 5, 2026Updated 2 months ago
- [ICML24] Official Implementation of "ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections"☆16May 31, 2024Updated last year
- 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.
- Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training☆39Jun 20, 2025Updated 10 months ago
- An CUDA-based library for computed tomography (CT) reconstruction with differentiable operators.☆20Apr 23, 2026Updated last week
- Code for Paper "The Geometry of Reasoning: Flowing Logics in Representation Space" (ICLR 2026)☆47Jan 31, 2026Updated 3 months ago
- ☆20Mar 16, 2020Updated 6 years ago
- ☆11Apr 5, 2023Updated 3 years ago
- [NeurIPS 2025] PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation☆125Feb 22, 2026Updated 2 months ago
- Python implementation of HlibertSort for sorting 3D point clouds using space-filling curves☆11Apr 17, 2019Updated 7 years ago
- Official repository for Robust Multimodal Large Language Models Against Modality Conflict☆20Jul 9, 2025Updated 9 months ago
- [CVPR 2025 Highlight] FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation☆29Jun 16, 2025Updated 10 months 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.
- Siggraph 2025 Journal track☆26Aug 13, 2025Updated 8 months ago
- [ICCV 2023] Official repository for "Tree-Structured Shading Decomposition"☆45Jan 2, 2025Updated last year
- This is the official training code of OmniSVG☆39Jan 19, 2026Updated 3 months ago
- [ICCV 2023] PATMAT Person Aware Tuning of Mask Aware Transformer for Face Inpainting☆30Jan 5, 2024Updated 2 years ago
- ☆13Aug 14, 2025Updated 8 months ago
- [ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos☆507Feb 11, 2026Updated 2 months ago
- ☆21Jun 30, 2025Updated 10 months ago