Stars
The course provides a comprehensive introduction to the fundamental concepts, techniques, and applications of NLP, covering both classical and modern approaches to language processing
Repository for the paper "Are We Done Yet?": A Vision-Based Judge for Autonomous Task Completion of Computer Use Agents
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!
A repository that includes the code for experiments for paper "Characterizing Knowledge Manipulation in a Russian Wikipedia Fork"
[CVPRW 2025] Official code of "IAUNet: Instance-Aware U-Net"
[IV 2025, Oral] Official code of "LiDPM: Rethinking Point Diffusion for Lidar Scene Completion"
OmniGen2: Exploration to Advanced Multimodal Generation.
Machine Learning Containers for NVIDIA Jetson and JetPack-L4T
Explainable AI Using Generative Adversarial Networks
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
VMamba: Visual State Space Models,code is based on mamba
Official code for ICCV 2023 paper "Convolutional Networks with Oriented 1D Kernels"
A PyTorch implementation of PointRend: Image Segmentation as Rendering
[CVPR2023] This is an official implementation of paper "DETRs with Hybrid Matching".
Official Code for DragGAN (SIGGRAPH 2023)
[CVPR2023] FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation
The largest pre-trained medical image segmentation model (1.4B parameters) based on the largest public dataset (>100k annotations), up until April 2023.
[CVPR 2022] SparseInst: Sparse Instance Activation for Real-Time Instance Segmentation
pix2pix3D: Generating 3D Objects from 2D User Inputs
BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix
StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation
Python module for computing the weighted distance transform of an image
Code release for ConvNeXt V2 model
[MICCAI 2023] DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation