Explore Projects
Discover 140 open source projects
Showing 61-80 of 140 projects
IDEA-Research/Grounded-SAM-2
Grounded SAM 2 is an open-source library for ground and track anything in videos using state-of-the-art AI models.
hankcs/pyhanlp
An open-source Chinese NLP library providing state-of-the-art tools for word segmentation, dependency parsing, named entity recognition, and more.
sbrugman/deep-learning-papers
A curated collection of deep learning research papers organized by task and with the latest state-of-the-art work labeled.
louisfb01/best_AI_papers_2022
A curated list of the latest AI breakthroughs in 2022 with explanatory videos, articles, and code.
CatchTheTornado/text-extract-api
An API for extracting, anonymizing, and parsing text from various document formats using state-of-the-art OCR and LLM models.
IntelLabs/nlp-architect
A model library for exploring state-of-the-art deep learning techniques for optimizing NLP neural networks.
louisfb01/best_AI_papers_2021
A curated list of the latest AI research papers from 2021 with explanations and code samples
megvii-research/NAFNet
State-of-the-art image restoration model without nonlinear activation functions
jonyzhang2023/awesome-embodied-vla-va-vln
A curated list of state-of-the-art research in embodied AI, focusing on VLA, VLN, and related multimodal learning approaches.
llm-d/llm-d
Achieve state-of-the-art inference performance on modern accelerators with this Kubernetes-based solution.
wenbihan/reproducible-image-denoising-state-of-the-art
A comprehensive collection of popular and reproducible image denoising techniques and implementations.
NVIDIA/physicsnemo
An open-source deep learning framework for building, training, and fine-tuning models using physics-ML methods.
mravanelli/pytorch-kaldi
A PyTorch-based project for developing state-of-the-art speech recognition systems using the Kaldi toolkit.
lmnr-ai/index
An open-source browser agent that autonomously performs complex web tasks using state-of-the-art AI tools.
Rayhane-mamah/Tacotron-2
Tacotron-2 is a state-of-the-art text-to-speech model that vibe coders can use to build speech synthesis applications.
ailia-ai/ailia-models
A collection of pre-trained, state-of-the-art AI models for the ailia SDK, supporting a wide range of computer vision and natural language processing tasks.
Cloud-CV/EvalAI
Open-source platform for evaluating state-of-the-art in AI and machine learning models and challenges.
MinishLab/model2vec
A high-performance library for generating state-of-the-art static embeddings for natural language processing tasks.
guillaumegenthial/sequence_tagging
Named Entity Recognition (NER) library for Tensorflow, using LSTM + CRF for state-of-the-art performance.
WuJie1010/Facial-Expression-Recognition.Pytorch
A state-of-the-art PyTorch implementation for facial expression recognition, useful for developers working on computer vision and AI applications.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.