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.

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Best Practices, code samples, and documentation for Computer Vision.

Reference PyTorch implementation and models for DINOv3

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

TPAMI：Frequency-aware Feature Fusion for Dense Image Prediction

Implementation of various topic models

Official Codes for "Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality"

🎮 Advanced Deep Learning and Reinforcement Learning at UCL & DeepMind | YouTube videos 👉

Train InternViT-6B in MMSegmentation and MMDetection with DeepSpeed

[IGARSS 2025 Oral] A Simple Aerial Detection Baseline of Multimodal Language Models.

Feature guided masked Autoencoder for self-supervised learning in remote sensing

code for "Spectral Removal of Guarded Attribute Information"