Official Implementation (Pytorch) of the "Representation Shift: Unifying Token Compression with FlashAttention", ICCV 2025
☆32Feb 22, 2026Updated last month
Alternatives and similar repositories for Representation-Shift
Users that are interested in Representation-Shift are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2025] FastVID: Dynamic Density Pruning for Fast Video Large Language Models☆31Nov 10, 2025Updated 4 months ago
- [NeurIPS25] Official Implementation (Pytorch) of "DeepVideo-R1"☆31Feb 22, 2026Updated last month
- XDoG(Extended Difference of Gaussians)アルゴリズムを用いた線画抽出のサンプルです。☆15Jan 28, 2021Updated 5 years ago
- A ComfyUI and ComfyScript Gradio-based app for generating characters using a multi-step process.☆19Nov 5, 2025Updated 4 months ago
- Multipurpose lens post process effects node for ComfyUI. Realistic or stylistic lens distortions, chromatic aberration, post-process scal…☆22Jul 10, 2025Updated 8 months ago
- Code for the paper "No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations"☆12Oct 31, 2024Updated last year
- ☆13Oct 30, 2023Updated 2 years ago
- ☆10Jun 28, 2023Updated 2 years ago
- Pytorch、Numpy实现NMS、Soft-NMS代码☆12Mar 22, 2021Updated 5 years ago
- [CVPR 2026] A training-free, mask-free framework for 3D shape editing.☆26Dec 12, 2025Updated 3 months ago
- In our implementation of Qwen-Image-Edit, we employ block causal attention to improve inference speed.☆44Feb 16, 2026Updated last month
- ☆21Jul 6, 2022Updated 3 years ago
- ☆54Sep 27, 2024Updated last year
- [NeurIPS '25] FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed☆27Mar 9, 2026Updated 2 weeks ago
- This repo holds the official code and data for "Beyond Literal Descriptions: Understanding and Locating Open-World Objects Aligned with H…☆16May 21, 2024Updated last year
- VideoGPA is a self-supervised framework that enhances 3D consistency in Video Diffusion Models.☆42Updated this week
- ☆12Apr 26, 2022Updated 3 years ago
- Official implementation of Decoupled MeanFlow☆37Oct 28, 2025Updated 4 months ago
- [ 🎯 NeurIPS 2025 ] 3D-RAD 🩻: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks☆27Oct 28, 2025Updated 4 months ago
- ☆12Jan 4, 2022Updated 4 years ago
- [TMM 2025] Official Implementation of DreamJourney: Perpetual View Generation with Video Diffusion Models☆18Jun 24, 2025Updated 8 months ago
- Basic Artificial Intelligence Theory☆10Mar 11, 2025Updated last year
- Richer Convolutional Features for Edge Detection model in pytorch CVPR2017☆10Dec 23, 2021Updated 4 years ago
- 2023-1 고려대학교 AIKU 딥러닝 방학 부트캠프: Deep into Deep☆10Jul 10, 2023Updated 2 years ago
- [ICCV 2025] The official implementation for EgoM2P: Egocentric Multimodal Multitask Pretraining.☆35Jan 3, 2026Updated 2 months ago
- Official implementation for "Pruning Large Language Models with Semi-Structural Adaptive Sparse Training" (AAAI 2025)☆18Jul 1, 2025Updated 8 months ago
- [NeurIPS 24] Official Implementation (Pytorch) of "Inversion-based Latent Bayesian Optimization"☆10Nov 15, 2024Updated last year
- ☆12May 26, 2023Updated 2 years ago
- Customized implementation of the U-Net in PyTorch for super-resolving hyper-low-field MRI images.☆19Apr 5, 2023Updated 2 years ago
- Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models (ICLR 2026)☆45Mar 3, 2026Updated 2 weeks ago
- ☆26Jul 23, 2025Updated 8 months ago
- Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval (ICCV 2025 Highlight)☆20Aug 1, 2025Updated 7 months ago
- ☆16Jun 5, 2023Updated 2 years ago
- [ICCV'23] UATVR: Uncertainty-Adaptive Text-Video Retrieval☆13Nov 5, 2023Updated 2 years ago
- code for Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning☆20Jul 16, 2024Updated last year
- Quartet II Official Code☆61Updated this week
- [NeurIPS 2024] Activating Self-Attention for Multi-Scene Absolute Pose Regression☆14Feb 24, 2025Updated last year
- ☆45Nov 26, 2025Updated 3 months ago
- ☆12Dec 16, 2025Updated 3 months ago