TTRV: Test-Time Reinforcement Learning for Vision–Language Models (CVPR 2026)

VisualOverload (CVPR 2026) is a VQA benchmark for image understanding in dense, high-resolution scenes.

Repository for the paper: Teaching VLMs to Localize Specific Objects from In-context Examples

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

ImageBind One Embedding Space to Bind Them All

Official repository for the MMFM challenge

Official inference library for Mistral models

Video Test-Time Adaptation for Action Recognition (CVPR 2023)

Code for the paper: Rotating Features for Object Discovery

Cleaner and Formatter for BibTeX files

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/sp…

SAM with text prompt

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Official implementation of Cold-Diffusion for different transformations in pytorch.

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

code for deep learning courses

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

The simplest, fastest repository for training/finetuning medium-sized GPTs.

EVA Series: Visual Representation Fantasies from BAAI

Test-time Prompt Tuning (TPT) for zero-shot generalization in vision-language models (NeurIPS 2022))

3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.

pytorch based implementation faster rcnn

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296

Refine high-quality datasets and visual AI models

LiDAR snowfall simulation