Natural Language Processing Best Practices & Examples

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

SOTA Re-identification Methods and Toolbox

A curated list of the latest breakthroughs in AI (in 2022) by release date with a clear video explanation, link to a more in-depth article, and code.

A curated list of the latest breakthroughs in AI (in 2021) by release date with a clear video explanation, link to a more in-depth article, and code.

The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web

A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code

A curated list of the most impressive AI papers

Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

🔥3D点云目标检测&语义分割(深度学习)-SOTA方法,代码,论文,数据集等

Paper bank for Self-Supervised Learning

Shape and dimension inference (Keras-like) for PyTorch layers and neural networks

[ICLR 2026] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

无人驾驶相关论文速递

LoongFlow: A Thinking & Learning Framework for Expert-Grade AI Agents.

A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/

A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS

Comparison of famous convolutional neural network models

FIBO is a SOTA, first open-source, JSON-native text-to-image model built for controllable, predictable, and legally safe image generation.

Official repository of the paper "HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment".

State-of-the-art methods on monocular 3D pose estimation / 3D mesh recovery

A collection of SOTA Image Classification Models in PyTorch

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Official implementation of SuperSimpleNet [ICPR 2024, JIMS 2025]

A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS

CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images

A curated list of the top 10 computer vision papers in 2021 with video demos, articles, code and paper reference.

A state of art detector for densely packed scenes dataset SKU-110K

A Gluon implement of Residual Attention Network. Best acc on cifar10-97.78%.