Stars
Official code for paper "GRIT: Teaching MLLMs to Think with Images"
Official implementation of 🛸 "UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface"
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
A curated list of awesome papers on dataset distillation and related applications.
PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437
[ICLR 2025] Official repository for “Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model”
Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
[ICLR 2025] On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
pytorch implementation of openai paper "Glow: Generative Flow with Invertible 1×1 Convolutions"
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
This repository is for the first comprehensive survey on Meta AI's Segment Anything Model (SAM).
[ICLR 2024] ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
Codes for ICLR 2024: "MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection"
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…
[TGRS 2025] Code for "PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images"
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
[CVPR 2022] Official CoTTA Code for our paper Continual Test-Time Domain Adaptation
Point Cloud Mamba: Point Cloud Learning via State Space Model
Python package to corrupt arbitrary images.
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States
[CVPR2024 Hightlight] No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
[ECCV 2024] The official code of paper "Open-Vocabulary SAM".
[IGARSS 2024] Code for "CLIP-Guided Source-Free Object Detection in Aerial Images"
Convolutional layer for Kolmogorov-Arnold Network (KAN)
A comprehensive collection of KAN(Kolmogorov-Arnold Network)-related resources, including libraries, projects, tutorials, papers, and more, for researchers and developers in the Kolmogorov-Arnold N…