🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!

Official inference framework for 1-bit LLMs

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Hackable and optimized Transformers building blocks, supporting a composable construction.

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

🚀 「大模型」1小时从0训练67M参数的视觉多模态VLM！🌏 Train a 67M-parameter VLM from scratch in just 1 hours!

95.47% on CIFAR10 with PyTorch

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

Everything about the SmolLM and SmolVLM family of models

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

NSGA2, NSGA3, R-NSGA3, MOEAD, Genetic Algorithms (GA), Differential Evolution (DE), CMAES, PSO

[IEEE TMI] Official Implementation for UNet++

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

This is a collection of our NAS and Vision Transformer work.

Nvidia Semantic Segmentation monorepo

Denoising Diffusion Implicit Models

Pytorch implementation of various Knowledge Distillation (KD) methods.