Best AI Models & LLMs

Mistral-7B-v0.1

AI Models

Pretrained generative text model with 7 billion parameters, designed to advance artificial intelligence through open source. It outperforms Llama 2 13B on…Mistral-7B-v0.1 is a pretrained generative text model with 7 billion parameters, designed to advance artificial intelligence through open source. It outperforms Llama 2 13B on…

Phi-4-reasoning-vision-15B

AI Models

Multimodal AI model developed by Microsoft, designed for tasks requiring vision-language understanding and reasoning capabilities. It excels in…Phi-4-reasoning-vision-15B is a multimodal AI model developed by Microsoft, designed for tasks requiring vision-language understanding and reasoning capabilities. It excels in…

BAAI/bge-large-en-v1.5 · Hugging Face

AI Models

State-of-the-art embedding model designed for retrieval-augmented language models. It enhances retrieval capabilities and supports various tasks,…BAAI/bge-large-en-v1.5 is a state-of-the-art embedding model designed for retrieval-augmented language models. It enhances retrieval capabilities and supports various tasks,…

Falcon-H1R-7B

LLMs

Reasoning-specialized AI model designed to enhance performance in mathematics, programming, and logic tasks. Developed by the Technology Innovation Institute,…Falcon-H1R-7B is a reasoning-specialized AI model designed to enhance performance in mathematics, programming, and logic tasks. Developed by the Technology Innovation Institute,…

OmniParser: Vision-Based GUI Agent

AI Models

Method for parsing user interface screenshots into structured elements. It enhances the ability of vision language models like GPT-4V to generate actions on…OmniParser is a method for parsing user interface screenshots into structured elements. It enhances the ability of vision language models like GPT-4V to generate actions on…

pollinations.ai

AI Apps

Build AI applications with a single API for text, image, audio, and video. Pollinations.ai handles models and infrastructure, allowing users to spend from their own credits.…

DeepSeek-v3 AI Model

AI Apps

Offers instant AI solutions powered by advanced MoE architecture and state-of-the-art language models. Experience cutting-edge AI capabilities with this stable, free,…DeepSeek-v3 offers instant AI solutions powered by advanced MoE architecture and state-of-the-art language models. Experience cutting-edge AI capabilities with this stable, free,…

Reflection 70B Online

AI Apps

Try Reflection 70B, an open-source LLM based on Llama 70B. It features innovative self-correction, outperforming GPT-4 and Llama 3.1 405B on benchmarks. Access the chat interface…

DeepSeek R1 Online

AI Apps

Open-source AI model for advanced reasoning, outperforming OpenAI's o1. It features a Mixture of Experts architecture with 37B active parameters and 128K…DeepSeek R1 Online is an open-source AI model for advanced reasoning, outperforming OpenAI's o1. It features a Mixture of Experts architecture with 37B active parameters and 128K…

Auto-regressive generative AI model that creates audio samples based on descriptive text captions. It addresses challenges in audio generation, such as separating…AudioGen is an auto-regressive generative AI model that creates audio samples based on descriptive text captions. It addresses challenges in audio generation, such as separating…

Meta Segment Anything Model 2

AI Models

Unified segmentation model for images and videos. It enables fast, precise object selection using clicks, boxes, or masks, offering…Meta Segment Anything Model 2 (SAM 2) is a unified segmentation model for images and videos. It enables fast, precise object selection using clicks, boxes, or masks, offering…

FFMPerative-7B

AI Models

Llama 2 7B LLM fine-tuned for video production workflows. It allows users to control video editing tasks via natural language commands, interacting with the…FFMPerative-7B is a Llama 2 7B LLM fine-tuned for video production workflows. It allows users to control video editing tasks via natural language commands, interacting with the…

OPT-175B

AI Models

175-billion-parameter language model released by Meta AI for the research community. It provides access to large-scale language models, enabling deeper understanding…OPT-175B is a 175-billion-parameter language model released by Meta AI for the research community. It provides access to large-scale language models, enabling deeper understanding…

Gato Generalist Agent

AI Models

Single generalist AI agent developed by Google DeepMind. It can perform a wide variety of tasks, including playing Atari games, captioning images, chatting, and…Gato is a single generalist AI agent developed by Google DeepMind. It can perform a wide variety of tasks, including playing Atari games, captioning images, chatting, and…

Densenet – PyTorch

AI Models

Deep convolutional neural network architecture available through PyTorch. It enhances feature propagation and reuse by connecting each layer to every other layer in…Densenet is a deep convolutional neural network architecture available through PyTorch. It enhances feature propagation and reuse by connecting each layer to every other layer in…

SqueezeNet – PyTorch

AI Models

Deep convolutional neural network model available through PyTorch. It achieves AlexNet-level accuracy with significantly fewer parameters and a smaller model size,…SqueezeNet is a deep convolutional neural network model available through PyTorch. It achieves AlexNet-level accuracy with significantly fewer parameters and a smaller model size,…

Xception

AI Models

Deep learning model available through the Keras 3 API. It is part of Keras Applications, offering pre-trained models for various computer vision tasks. Xception is…Xception is a deep learning model available through the Keras 3 API. It is part of Keras Applications, offering pre-trained models for various computer vision tasks. Xception is…

Transfo-XL-WT103

AI Models

Causal transformer model with relative positioning embeddings that can reuse hidden states for longer context. Developed by Zihang Dai and others, it uses…Transfo-XL-WT103 is a causal transformer model with relative positioning embeddings that can reuse hidden states for longer context. Developed by Zihang Dai and others, it uses…

Gopher

AI Models

280-billion-parameter transformer language model from Google DeepMind, part of a family ranging from 44 million to 280 billion parameters. Introduced in a 2021…Gopher is a 280-billion-parameter transformer language model from Google DeepMind, part of a family ranging from 44 million to 280 billion parameters. Introduced in a 2021…

Chinchilla

AI Models

70-billion-parameter language model from Google DeepMind, trained on 1.3 trillion tokens to test whether a smaller model trained on more data can outperform a…Chinchilla is a 70-billion-parameter language model from Google DeepMind, trained on 1.3 trillion tokens to test whether a smaller model trained on more data can outperform a…

Parti: Pathways Autoregressive Text-to-Image Model

AI Models

Autoregressive text-to-image generation model that creates high-fidelity photorealistic images. It treats image generation as a sequence-to-sequence problem,…Parti is an autoregressive text-to-image generation model that creates high-fidelity photorealistic images. It treats image generation as a sequence-to-sequence problem,…

LaMDA

AI Models

Google's breakthrough conversational AI model, designed to engage in free-flowing dialogue across a vast array of topics. It builds upon Transformer architecture, trained…LaMDA is Google's breakthrough conversational AI model, designed to engage in free-flowing dialogue across a vast array of topics. It builds upon Transformer architecture, trained…

InstructGPT

AI Models

InstructGPT models are AI language models trained to better follow user intentions than GPT-3. They are more truthful, less toxic, and aligned with user goals through…

DreamFusion

AI Models

AI model that generates 3D objects from text descriptions. It leverages pre-trained 2D diffusion models to create relightable 3D assets like Neural Radiance…DreamFusion is an AI model that generates 3D objects from text descriptions. It leverages pre-trained 2D diffusion models to create relightable 3D assets like Neural Radiance…

Longformer Base 4096

AI Models

Transformer model designed for processing long documents. It builds upon RoBERTa, pretrained on extended sequences up to 4,096 tokens. This model employs…Longformer Base 4096 is a transformer model designed for processing long documents. It builds upon RoBERTa, pretrained on extended sequences up to 4,096 tokens. This model employs…

google/bigbird-roberta-base

AI Models

The BigBird base model is a transformer that extends BERT to handle much longer sequences using block sparse attention. It is pre-trained on English text for masked language…

Phi-2 Language Model

AI Models

2.7 billion-parameter language model from Microsoft Research. It demonstrates outstanding reasoning and language understanding, achieving state-of-the-art performance…Phi-2 is a 2.7 billion-parameter language model from Microsoft Research. It demonstrates outstanding reasoning and language understanding, achieving state-of-the-art performance…

Introduces alias-free generative adversarial networks by overhauling signal processing within the generator. This innovation eliminates "texture sticking," enabling more…StyleGAN3 introduces alias-free generative adversarial networks by overhauling signal processing within the generator. This innovation eliminates "texture sticking," enabling more…

Universal Sentence Encoder

AI Models

The Universal Sentence Encoder by Google encodes text into high-dimensional vectors for tasks like text classification, semantic similarity, and clustering. It is optimized for…

PaLM-E

AI Models

Embodied multimodal language model that integrates real-world continuous sensor data with text. It enables robots to perform complex tasks by grounding language in…PaLM-E is an embodied multimodal language model that integrates real-world continuous sensor data with text. It enables robots to perform complex tasks by grounding language in…

DGCNN

AI GitHub Repos

AI model for learning on point clouds, implementing Dynamic Graph CNN. It achieves state-of-the-art performance in tasks like classification and segmentation of 3D…DGCNN is an AI model for learning on point clouds, implementing Dynamic Graph CNN. It achieves state-of-the-art performance in tasks like classification and segmentation of 3D…

Wav2vec 2.0

AI Models

Self-supervised learning algorithm for automatic speech recognition. It learns from raw audio, requiring minimal transcribed data to achieve high accuracy. This…Wav2vec 2.0 is a self-supervised learning algorithm for automatic speech recognition. It learns from raw audio, requiring minimal transcribed data to achieve high accuracy. This…

AI model that generates high-quality audio with long-term consistency. It treats audio generation as a language modeling task, mapping audio to discrete tokens. The…AudioLM is an AI model that generates high-quality audio with long-term consistency. It treats audio generation as a language modeling task, mapping audio to discrete tokens. The…

Flamingo

AI Models

Single visual language model (VLM) from Google DeepMind that excels at few-shot learning across diverse multimodal tasks. It processes interleaved images, videos,…Flamingo is a single visual language model (VLM) from Google DeepMind that excels at few-shot learning across diverse multimodal tasks. It processes interleaved images, videos,…

BEiT Image Transformer

AI Models

Self-supervised vision representation model that uses masked image modeling to pre-train vision transformers. It tokenizes images into visual tokens and recovers masked…BEiT is a self-supervised vision representation model that uses masked image modeling to pre-train vision transformers. It tokenizes images into visual tokens and recovers masked…

ImageBind by Meta AI

AI Models

Multimodal AI model from Meta AI that binds data from six modalities: image, video, audio, text, depth, and thermal. It learns a single embedding space without…ImageBind is a multimodal AI model from Meta AI that binds data from six modalities: image, video, audio, text, depth, and thermal. It learns a single embedding space without…

HuggingFaceH4/zephyr-7b-beta

AI Models

Zephyr-7B-β is an open-source language model fine-tuned from Mistral-7B-v0.1 using Direct Preference Optimization. It excels as a helpful assistant, demonstrating strong…

Fuyu-8B Multimodal Architecture

AI Models

Open-source multimodal AI model designed for digital agents. Its simplified architecture supports arbitrary image resolutions, enabling it to answer questions about…Fuyu-8B is an open-source multimodal AI model designed for digital agents. Its simplified architecture supports arbitrary image resolutions, enabling it to answer questions about…

IDEFICS Visual Language Model

AI Models

Open-access visual language model that reproduces state-of-the-art capabilities. It accepts interleaved image and text inputs to generate text outputs, comparable to…IDEFICS is an open-access visual language model that reproduces state-of-the-art capabilities. It accepts interleaved image and text inputs to generate text outputs, comparable to…

AI model that enhances vision-language understanding by aligning a frozen visual encoder with a large language model. It can generate detailed image descriptions,…MiniGPT-4 is an AI model that enhances vision-language understanding by aligning a frozen visual encoder with a large language model. It can generate detailed image descriptions,…

LLaVA

AI Models

Large multimodal model that combines a vision encoder with a language model for general-purpose visual and language understanding. It excels at multimodal chat…LLaVA is a large multimodal model that combines a vision encoder with a language model for general-purpose visual and language understanding. It excels at multimodal chat…

Mamba SSM Architecture

AI GitHub Repos

Novel state space model architecture designed for efficient sequence modeling, particularly effective on information-dense data like language. It offers a…Mamba is a novel state space model architecture designed for efficient sequence modeling, particularly effective on information-dense data like language. It offers a…

RWKV Language Model

AI Models

Powerful language model that offers efficient inference and flexible fine-tuning capabilities. It supports various applications, including desktop GUIs, web-based…RWKV is a powerful language model that offers efficient inference and flexible fine-tuning capabilities. It supports various applications, including desktop GUIs, web-based…

OpenELM Language Model

AI Models

State-of-the-art open language model family from Apple Machine Learning Research. It features a layer-wise scaling strategy for enhanced accuracy and provides a…OpenELM is a state-of-the-art open language model family from Apple Machine Learning Research. It features a layer-wise scaling strategy for enhanced accuracy and provides a…

N-BEATS

AI GitHub Repos

Neural-network based model for univariate time-series forecasting. Developed by ServiceNow Research, it implements the N-BEATS algorithm for reproducible experimental…N-BEATS is a neural-network based model for univariate time-series forecasting. Developed by ServiceNow Research, it implements the N-BEATS algorithm for reproducible experimental…

DBRX LLM

AI Models

State-of-the-art open large language model from Databricks, excelling in benchmarks for language, programming, and math. It offers improved efficiency and quality,…DBRX is a state-of-the-art open large language model from Databricks, excelling in benchmarks for language, programming, and math. It offers improved efficiency and quality,…

This AI model offers a general-purpose solution for image-to-image translation tasks. It learns both the image mapping and the appropriate loss function, enabling versatile…

DM-GAN

AI GitHub Repos

PyTorch implementation of Dynamic Memory Generative Adversarial Networks for text-to-image synthesis. This repository provides code, pretrained models, and evaluation…DM-GAN is a PyTorch implementation of Dynamic Memory Generative Adversarial Networks for text-to-image synthesis. This repository provides code, pretrained models, and evaluation…

Text-to-image diffusion model developed by Google Research. It generates photorealistic images with a deep understanding of language. Imagen excels at image-text…Imagen is a text-to-image diffusion model developed by Google Research. It generates photorealistic images with a deep understanding of language. Imagen excels at image-text…

OpenLLaMA

AI GitHub Repos

Permissively licensed, open-source reproduction of Meta AI's LLaMA 7B model. Trained on the RedPajama dataset, it offers 3B, 7B, and 13B parameter versions,…OpenLLaMA is a permissively licensed, open-source reproduction of Meta AI's LLaMA 7B model. Trained on the RedPajama dataset, it offers 3B, 7B, and 13B parameter versions,…

UNITER

AI GitHub Repos

Research code repository for the ECCV 2020 paper 'UNITER: UNiversal Image-TExt Representation Learning'. It provides code for finetuning and inference across various…UNITER is a research code repository for the ECCV 2020 paper 'UNITER: UNiversal Image-TExt Representation Learning'. It provides code for finetuning and inference across various…

Explore audio synthesis demos powered by DiffWave, a versatile diffusion model. This resource showcases neural vocoding, class-conditional generation, unconditional waveform…

End-to-end text-to-speech model that enhances voice quality and training speed. It directly incorporates speech variation information like pitch and energy,…FastSpeech 2 is an end-to-end text-to-speech model that enhances voice quality and training speed. It directly incorporates speech variation information like pitch and energy,…

Generative adversarial network for efficient and high-fidelity speech synthesis. It models periodic patterns in audio to enhance sample quality, achieving human-like…HiFi-GAN is a generative adversarial network for efficient and high-fidelity speech synthesis. It models periodic patterns in audio to enhance sample quality, achieving human-like…

Open-source toolkit for end-to-end speech processing. It provides comprehensive recipes and tools for tasks like Automatic Speech Recognition (ASR), Text-to-Speech…ESPnet is an open-source toolkit for end-to-end speech processing. It provides comprehensive recipes and tools for tasks like Automatic Speech Recognition (ASR), Text-to-Speech…

FNet

AI GitHub Repos

Efficient Transformer-like encoder architecture that replaces self-attention with Fourier Transforms. Developed by Google Research, it offers a high-performance…FNet is an efficient Transformer-like encoder architecture that replaces self-attention with Fourier Transforms. Developed by Google Research, it offers a high-performance…

SpanBERT

AI GitHub Repos

AI model focused on improving pre-training by representing and predicting spans. It offers pre-trained base and large cased models, compatible with HuggingFace BERT…SpanBERT is an AI model focused on improving pre-training by representing and predicting spans. It offers pre-trained base and large cased models, compatible with HuggingFace BERT…

LayoutLM

AI GitHub Repos

Multimodal pre-training model for visually-rich document understanding and information extraction. It combines text, layout, and image information to achieve…LayoutLM is a multimodal pre-training model for visually-rich document understanding and information extraction. It combines text, layout, and image information to achieve…

MASS

AI GitHub Repos

Pre-training method for sequence-to-sequence language generation tasks. It masks sentence fragments for the encoder to predict in the decoder, enhancing tasks like…MASS is a pre-training method for sequence-to-sequence language generation tasks. It masks sentence fragments for the encoder to predict in the decoder, enhancing tasks like…

ProphetNet

AI GitHub Repos

Research project by the MSRA NLC team focused on natural language generation. It provides official implementations of pretrained models, including those for future…ProphetNet is a research project by the MSRA NLC team focused on natural language generation. It provides official implementations of pretrained models, including those for future…

DeBERTa - Microsoft Research

AI Models

Large-scale pre-trained language model developed by Microsoft Research. It surpasses T5 11B models in performance and achieves human-level results on SuperGLUE…DeBERTa is a large-scale pre-trained language model developed by Microsoft Research. It surpasses T5 11B models in performance and achieves human-level results on SuperGLUE…

Funnel-Transformer

AI GitHub Repos

AI model that compresses hidden states to reduce computation cost. It allows for deeper or wider models with the same FLOPs and can recover token-level…Funnel-Transformer is an AI model that compresses hidden states to reduce computation cost. It allows for deeper or wider models with the same FLOPs and can recover token-level…

ConvBERT

AI GitHub Repos

Open-source AI model for pre-training language models, introducing a novel architecture with span-based dynamic convolution. This GitHub repository provides the…ConvBERT is an open-source AI model for pre-training language models, introducing a novel architecture with span-based dynamic convolution. This GitHub repository provides the…

MPNet

AI GitHub Repos

Novel pre-training method for language understanding tasks, improving upon BERT and XLNet. It offers a unified implementation for various pre-training models and…MPNet is a novel pre-training method for language understanding tasks, improving upon BERT and XLNet. It offers a unified implementation for various pre-training models and…

node2vec

AI Models

Scalable framework for learning continuous feature representations of nodes in graphs. It optimizes neighborhood preservation through biased random walks, enabling…node2vec is a scalable framework for learning continuous feature representations of nodes in graphs. It optimizes neighborhood preservation through biased random walks, enabling…

SEAL Link Prediction

AI GitHub Repos

Novel framework for link prediction that transforms the problem into a subgraph classification task. It extracts h-hop enclosing subgraphs and node information matrices,…SEAL is a novel framework for link prediction that transforms the problem into a subgraph classification task. It extracts h-hop enclosing subgraphs and node information matrices,…

StyleSwin: Transformer-based GAN

AI GitHub Repos

Transformer-based Generative Adversarial Network (GAN) designed for high-resolution image generation. It leverages Swin transformers and a novel double attention…StyleSwin is a transformer-based Generative Adversarial Network (GAN) designed for high-resolution image generation. It leverages Swin transformers and a novel double attention…

Text-to-audio generation framework utilizing latent diffusion models. It translates various modalities into a unified 'language of audio' (LOA) for generating…AudioLDM is a text-to-audio generation framework utilizing latent diffusion models. It translates various modalities into a unified 'language of audio' (LOA) for generating…

Text-to-audio generation system employing prompt-enhanced diffusion models. It addresses data scarcity and audio complexity by using pseudo prompt enhancement…Make-An-Audio is a text-to-audio generation system employing prompt-enhanced diffusion models. It addresses data scarcity and audio complexity by using pseudo prompt enhancement…

Voicebox

AI GitHub Repos

Open-source AI voice studio that allows users to clone, dictate, and create voice projects. It provides a platform for voice synthesis and manipulation, making it…Voicebox is an open-source AI voice studio that allows users to clone, dictate, and create voice projects. It provides a platform for voice synthesis and manipulation, making it…

Decision Transformer

AI Models

Reframes reinforcement learning as a sequence modeling problem, leveraging Transformer architectures like GPT-x and BERT. It generates optimal actions by…Decision Transformer reframes reinforcement learning as a sequence modeling problem, leveraging Transformer architectures like GPT-x and BERT. It generates optimal actions by…

SciBERT

AI Apps

The Allen Institute for AI (AI2) is a non-profit research institute dedicated to conducting high-impact AI research and engineering. They focus on advancing AI for the common…

Deep Learning Models for Tabular Data

AI GitHub Repos

This GitHub repository provides the official implementation for the NeurIPS 2021 paper 'Revisiting Deep Learning Models for Tabular Data.' It explores deep learning architectures…

SPP_net

AI GitHub Repos

Re-implementation of the Spatial Pyramid Pooling algorithm for deep convolutional networks in visual recognition. It aims to reproduce object detection results from a…SPP_net is a re-implementation of the Spatial Pyramid Pooling algorithm for deep convolutional networks in visual recognition. It aims to reproduce object detection results from a…

ShuffleNet Series

AI GitHub Repos

The ShuffleNet Series repository offers a collection of highly efficient convolutional neural network models designed for mobile devices and resource-constrained environments. It…

ConvMixer

AI GitHub Repos

This repository provides an implementation of ConvMixer, a convolutional neural network architecture for image recognition tasks. It is based on the paper "Patches Are All You…

RepVGG

AI GitHub Repos

Powerful and simple ConvNet architecture that achieves high accuracy on ImageNet. It utilizes a VGG-style design with re-parameterization techniques, allowing for…RepVGG is a powerful and simple ConvNet architecture that achieves high accuracy on ImageNet. It utilizes a VGG-style design with re-parameterization techniques, allowing for…

MobileOne

AI Models

Efficient neural network backbone designed for mobile devices. It optimizes for inference speed, achieving under 1 ms on an iPhone12 with high accuracy. This model…MobileOne is an efficient neural network backbone designed for mobile devices. It optimizes for inference speed, achieving under 1 ms on an iPhone12 with high accuracy. This model…

Vision GNN (ViG)

AI GitHub Repos

PyTorch implementation of Vision Graph Neural Networks developed by Huawei Noah's Ark Lab. It offers efficient AI backbones for image processing tasks,…Vision GNN (ViG) is a PyTorch implementation of Vision Graph Neural Networks developed by Huawei Noah's Ark Lab. It offers efficient AI backbones for image processing tasks,…

Deformable ConvNets

AI GitHub Repos

Deformable Convolutional Networks (DCN) enhance deep learning models by adaptively learning sampling offsets for convolutional kernels. This allows networks to better capture…

RETRO Language Model

AI Models

AI model that augments transformer architectures with retrieval capabilities. It accesses a vast database of text passages, including…RETRO (Retrieval Enhanced Transformers) is an AI model that augments transformer architectures with retrieval capabilities. It accesses a vast database of text passages, including…

LS-GAN

AI Models

Or Loss-Sensitive Generative Adversarial Networks, is a project focused on advancing GANs. It introduces a novel approach to loss functions, aiming for improved generation…LS-GAN, or Loss-Sensitive Generative Adversarial Networks, is a project focused on advancing GANs. It introduces a novel approach to loss functions, aiming for improved generation…

SNGAN Projection

AI GitHub Repos

This GitHub repository provides an official Chainer implementation for conditional image generation. It utilizes spectral normalization and a projection discriminator for…

PyTorch MADE

AI GitHub Repos

This repository provides a PyTorch implementation of MADE (Masked Autoencoder Density Estimation). It enables turning auto-encoders into autoregressive density models by masking…

StyleGAN-XL

AI GitHub Repos

AI model for generating high-resolution images from large, diverse datasets. It scales StyleGAN architecture for improved image synthesis quality and diversity.…StyleGAN-XL is an AI model for generating high-resolution images from large, diverse datasets. It scales StyleGAN architecture for improved image synthesis quality and diversity.…

StyleGAN3 is a generative adversarial network that eliminates "texture sticking" by overhauling signal processing. It achieves translation and rotation equivariance, enabling more…

AI model for efficient, non-autoregressive audio generation. It produces high-quality audio two orders of magnitude faster than previous methods, maintaining…SoundStorm is an AI model for efficient, non-autoregressive audio generation. It produces high-quality audio two orders of magnitude faster than previous methods, maintaining…

DimeNet and DimeNet++

AI GitHub Repos

Advanced neural network models for molecular graphs, focusing on directional message passing. These models, proposed in ICLR 2020 and NeurIPS-W 2020,…DimeNet and DimeNet++ are advanced neural network models for molecular graphs, focusing on directional message passing. These models, proposed in ICLR 2020 and NeurIPS-W 2020,…

GluonTS

AI Frameworks

Python package for probabilistic time series modeling, leveraging deep learning models built on PyTorch and MXNet. It facilitates accurate forecasting by generating…GluonTS is a Python package for probabilistic time series modeling, leveraging deep learning models built on PyTorch and MXNet. It facilitates accurate forecasting by generating…

LSTNet

AI GitHub Repos

Deep learning model designed for time series forecasting. It effectively models both long-term and short-term temporal patterns using a combination of recurrent neural…LSTNet is a deep learning model designed for time series forecasting. It effectively models both long-term and short-term temporal patterns using a combination of recurrent neural…

Autoformer

AI GitHub Repos

AI model for long-term time series forecasting, leveraging decomposition transformers and auto-correlation mechanisms. It achieves state-of-the-art results across…Autoformer is an AI model for long-term time series forecasting, leveraging decomposition transformers and auto-correlation mechanisms. It achieves state-of-the-art results across…

Informer2020

AI GitHub Repos

The Informer2020 GitHub repository provides the PyTorch implementation for the Informer model, designed for efficient long sequence time-series forecasting. It features ProbSparse…

FEDformer

AI GitHub Repos

Frequency Enhanced Decomposed Transformer designed for efficient long-term time series forecasting. It achieves linear complexity with sequence length,…FEDformer is a Frequency Enhanced Decomposed Transformer designed for efficient long-term time series forecasting. It achieves linear complexity with sequence length,…

PatchTST

AI Models

Official implementation of a Transformer-based model for long-term time series forecasting. It segments time series into patches and processes them independently,…PatchTST is an official implementation of a Transformer-based model for long-term time series forecasting. It segments time series into patches and processes them independently,…

LTSF-Linear

AI GitHub Repos

Official PyTorch implementation for "Are Transformers Effective for Time Series Forecasting?". It introduces a family of linear models (Linear, DLinear, NLinear)…LTSF-Linear is an official PyTorch implementation for "Are Transformers Effective for Time Series Forecasting?". It introduces a family of linear models (Linear, DLinear, NLinear)…

TimesNet

AI Models

Foundation model for general time series analysis, transforming 1D series into 2D space for enhanced modeling. It achieves state-of-the-art results in forecasting,…TimesNet is a foundation model for general time series analysis, transforming 1D series into 2D space for enhanced modeling. It achieves state-of-the-art results in forecasting,…

maml_rl

AI GitHub Repos

This repository provides code for reinforcement learning experiments detailed in the "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks" paper. It enables…

Prototypical Networks

AI GitHub Repos

This repository contains the code for the NeurIPS 2017 paper "Prototypical Networks for Few-shot Learning." It provides an implementation of a novel approach to few-shot learning,…

LearningToCompare_FSL

AI GitHub Repos

This repository provides PyTorch code for the CVPR 2018 paper 'Learning to Compare: Relation Network for Few-Shot Learning'. It focuses on the Few-Shot Learning aspect, offering…

Model-Based Policy Optimization

AI GitHub Repos

This GitHub repository contains the code for the "When to Trust Your Model: Model-Based Policy Optimization" paper. It provides implementations for model-based policy optimization…

Handful of Trials

AI GitHub Repos

This repository contains experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models." It implements the PETS algorithm, combining…

AlphaStar

AI Models

AI model that achieved Grandmaster level in StarCraft II, a complex real-time strategy game. It utilizes multi-agent reinforcement learning and imitation learning,…AlphaStar is an AI model that achieved Grandmaster level in StarCraft II, a complex real-time strategy game. It utilizes multi-agent reinforcement learning and imitation learning,…

Relational Graph Convolutional Networks

AI GitHub Repos

This project provides a Keras-based implementation of Relational Graph Convolutional Networks (R-GCNs). It is designed for semi-supervised node classification on directed…

CompGCN

AI GitHub Repos

PyTorch implementation of Composition-Based Multi-Relational Graph Convolutional Networks. It enables advanced graph representation learning for tasks like knowledge…CompGCN is a PyTorch implementation of Composition-Based Multi-Relational Graph Convolutional Networks. It enables advanced graph representation learning for tasks like knowledge…

PPNP & APPNP Models

AI GitHub Repos

This GitHub repository provides TensorFlow and PyTorch implementations for the PPNP and APPNP models, introduced in the "Predict then Propagate: Graph Neural Networks meet…

Simplifying Graph Convolutional Networks

AI GitHub Repos

This repository provides the official implementation for the "Simplifying Graph Convolutional Networks" paper. It offers a streamlined Graph Convolutional Network (GCN) model that…

Graph Neural PDEs

AI GitHub Repos

Open-source project providing Python code for Graph Neural Networks (GNNs) that treat graph learning as a continuous diffusion process. It implements GRAND…Graph Neural PDEs is an open-source project providing Python code for Graph Neural Networks (GNNs) that treat graph learning as a continuous diffusion process. It implements GRAND…

This blog post introduces a new PyTorch Hopfield layer based on modern Hopfield Networks. It generalizes classical Hopfield Networks to continuous states and patterns, offering…

Temporal Graph Networks

AI GitHub Repos

Offer a generic, efficient framework for deep learning on dynamic graphs. This Python-based library utilizes novel memory modules and graph-based…Temporal Graph Networks (TGNs) offer a generic, efficient framework for deep learning on dynamic graphs. This Python-based library utilizes novel memory modules and graph-based…

xDeepFM

AI GitHub Repos

Open-source deep learning toolkit for factorization models, specifically releasing the source code for the eXtreme Deep Factorization Machine (xDeepFM) model. It…xDeepFM is an open-source deep learning toolkit for factorization models, specifically releasing the source code for the eXtreme Deep Factorization Machine (xDeepFM) model. It…

Attentional Factorization Machine

AI GitHub Repos

This GitHub repository provides a TensorFlow implementation of the Attentional Factorization Machine (AFM) model. It allows users to train and evaluate AFM for tasks like…

LightGCN

AI GitHub Repos

Simplified Graph Convolutional Network designed for recommendation systems. It focuses on the essential neighborhood aggregation component for collaborative…LightGCN is a simplified Graph Convolutional Network designed for recommendation systems. It focuses on the essential neighborhood aggregation component for collaborative…

Neural Graph Collaborative Filtering

AI GitHub Repos

Recommendation framework leveraging graph neural networks. It explicitly encodes collaborative signals through high-order…Neural Graph Collaborative Filtering (NGCF) is a recommendation framework leveraging graph neural networks. It explicitly encodes collaborative signals through high-order…

Cohere

AI Platforms

Builds enterprise AI models and platforms that companies can deploy privately, including on-premises or in isolated cloud environments. Its North platform provides agentic…Cohere builds enterprise AI models and platforms that companies can deploy privately, including on-premises or in isolated cloud environments. Its North platform provides agentic…

StarCoder

AI GitHub Repos

Large language model trained on source code and natural language. It excels at code generation, completion, and text generation tasks. This repository provides…StarCoder is a large language model trained on source code and natural language. It excels at code generation, completion, and text generation tasks. This repository provides…

LLaVA

AI GitHub Repos

Visual instruction tuning model that combines large language and vision capabilities. It aims to achieve GPT-4V level performance, enabling multimodal understanding and…LLaVA is a visual instruction tuning model that combines large language and vision capabilities. It aims to achieve GPT-4V level performance, enabling multimodal understanding and…

Kandinsky 2

AI GitHub Repos

Multilingual text-to-image latent diffusion model. It offers advanced image generation capabilities, including text-to-image, image-to-image, and inpainting. The…Kandinsky 2 is a multilingual text-to-image latent diffusion model. It offers advanced image generation capabilities, including text-to-image, image-to-image, and inpainting. The…

Qwen3 Large Language Model

AI GitHub Repos

Series of large language models developed by the Qwen team at Alibaba Cloud. It offers enhanced capabilities in instruction following, reasoning, text comprehension,…Qwen3 is a series of large language models developed by the Qwen team at Alibaba Cloud. It offers enhanced capabilities in instruction following, reasoning, text comprehension,…

V-JEPA

AI GitHub Repos

PyTorch implementation for self-supervised learning from video. It utilizes a joint-embedding predictive architecture to learn visual representations without human…V-JEPA is a PyTorch implementation for self-supervised learning from video. It utilizes a joint-embedding predictive architecture to learn visual representations without human…

Anthropic SDK Python

AI GitHub Repos

The Anthropic SDK for Python provides developers with direct access to the Claude API. This open-source library facilitates integration of advanced AI capabilities into Python…

Audiocraft

AI GitHub Repos

PyTorch library for deep learning audio generation and processing. It offers state-of-the-art models like MusicGen for controllable music generation and AudioGen…Audiocraft is a PyTorch library for deep learning audio generation and processing. It offers state-of-the-art models like MusicGen for controllable music generation and AudioGen…

StableLM

AI GitHub Repos

Open-source language model series developed by Stability AI. This GitHub repository hosts ongoing development, providing access to various checkpoints like…StableLM is an open-source language model series developed by Stability AI. This GitHub repository hosts ongoing development, providing access to various checkpoints like…

StyleCLIP

AI GitHub Repos

Official implementation for text-driven manipulation of StyleGAN imagery. It leverages StyleGAN's generative capabilities with CLIP's visual-language understanding…StyleCLIP is an official implementation for text-driven manipulation of StyleGAN imagery. It leverages StyleGAN's generative capabilities with CLIP's visual-language understanding…

MiniGPT-4 & MiniGPT-v2

AI GitHub Repos

Open-sourced code for MiniGPT-4 and MiniGPT-v2, advanced large language models enhancing vision-language understanding. These models enable multi-task learning for vision-language…

AUI Apollo-1

AI Models

Apollo-1 is a neuro-symbolic foundation model for task-oriented dialogue. It reasons in code, not weights, enabling companies to build agents that follow business rules…AUI's Apollo-1 is a neuro-symbolic foundation model for task-oriented dialogue. It reasons in code, not weights, enabling companies to build agents that follow business rules…

Text Generator API

AI Apps

Offers a unified API for advanced AI text, vision, and speech capabilities. It focuses on strong output quality, privacy-first infrastructure, and predictable…Text Generator offers a unified API for advanced AI text, vision, and speech capabilities. It focuses on strong output quality, privacy-first infrastructure, and predictable…

DeepSeek-OCR

AI GitHub Repos

GitHub project focused on Contexts Optical Compression. It allows developers to contribute to its development, enhancing its capabilities in optical character…DeepSeek-OCR is a GitHub project focused on Contexts Optical Compression. It allows developers to contribute to its development, enhancing its capabilities in optical character…

Nano Banana Pro API on Kie.ai

AI Apps

A cost-effective API on Kie.ai for Google's Nano Banana Pro (Gemini 3.0 Pro Image) that lets developers generate and edit high-fidelity images at 1K, 2K, and 4K with a single,…

OfoxAI

AI Apps

Provides a unified API gateway for accessing over 100 AI models, including GPT, Claude, and Gemini. It offers seamless integration with existing systems, enabling…OfoxAI provides a unified API gateway for accessing over 100 AI models, including GPT, Claude, and Gemini. It offers seamless integration with existing systems, enabling…

Open-source AI model that turns a single portrait photo plus a script or audio into a lip-synced talking video, generating aligned audio and video together…daVinci-MagiHuman is an open-source AI model that turns a single portrait photo plus a script or audio into a lip-synced talking video, generating aligned audio and video together…

Miso One

AI Apps

Information, demo, and access site for Miso TTS 8B, an open-weights, English-only text-to-speech model from Miso Labs built for expressive conversational speech and…Miso One is an information, demo, and access site for Miso TTS 8B, an open-weights, English-only text-to-speech model from Miso Labs built for expressive conversational speech and…

DeepSeek Online

AI Apps

A free online demo of the open-source DeepSeek V3 model (671B parameters) that runs in your browser with no registration, plus links to run the model locally for personal and…

SJolt

AI Apps

Unified API platform that enables product teams, developers, and creators to explore, compare, and utilize various image, video, and audio generation models seamlessly.…SJolt is a unified API platform that enables product teams, developers, and creators to explore, compare, and utilize various image, video, and audio generation models seamlessly.…

APIMODELS

AI Platforms

Multi-model AI API platform that aggregates over 110 models, including Claude and GPT, offering them at prices up to 95% lower than official APIs. It provides a…APIMODELS is a multi-model AI API platform that aggregates over 110 models, including Claude and GPT, offering them at prices up to 95% lower than official APIs. It provides a…

Tencent Hunyuan Large Model

AI Apps

Advanced AI model designed for various applications, including language translation and visual understanding. It offers enhanced performance and…Tencent Hunyuan Large Model is an advanced AI model designed for various applications, including language translation and visual understanding. It offers enhanced performance and…

Flux 3 — Multimodal AI

AI Apps

Flux 3 by Black Forest Labs is a multimodal foundation model that learns from images, videos, and audio. It enables creators to generate content seamlessly across different media…

Provides a unified API for accessing over 80 AI models, offering significant savings of up to 90% compared to direct provider rates. Users can pay only for successful…you.bot provides a unified API for accessing over 80 AI models, offering significant savings of up to 90% compared to direct provider rates. Users can pay only for successful…

Emix.ai

AI Apps

Provides a unified API to access leading AI models like GPT, Gemini, and Kling. It offers free API credits, transparent pricing, and no charges for failed generations,…Emix.ai provides a unified API to access leading AI models like GPT, Gemini, and Kling. It offers free API credits, transparent pricing, and no charges for failed generations,…

Cat-MaineCoon

AI Models

Real-time audio-visual generation model optimized for social-interactive applications. With 22B parameters, it enables streaming generation and sub-second…Cat-MaineCoon is a real-time audio-visual generation model optimized for social-interactive applications. With 22B parameters, it enables streaming generation and sub-second…

flatkey

AI Apps

AI API gateway that consolidates access to over 100 AI models and 1,000 tools through a single key. It simplifies billing and usage tracking while providing flexible…flatkey is an AI API gateway that consolidates access to over 100 AI models and 1,000 tools through a single key. It simplifies billing and usage tracking while providing flexible…

MiMo

AI Platforms

AI platform by Xiaomi that facilitates a dialogue between users and the essence of intelligence. It aims to compress complex information into understandable language…MiMo is an AI platform by Xiaomi that facilitates a dialogue between users and the essence of intelligence. It aims to compress complex information into understandable language…

OfoxAI Models

AI Apps

Offers access to over 100 AI models, including GPT-5.5, Claude Opus 4.8, and Gemini 3.5 Flash, through a single API. It provides real-time pricing and is compatible with…OfoxAI offers access to over 100 AI models, including GPT-5.5, Claude Opus 4.8, and Gemini 3.5 Flash, through a single API. It provides real-time pricing and is compatible with…

APIMaster

AI Apps

Provides a single API key for accessing multiple AI models like GPT, Claude, and DeepSeek at discounted rates. New users receive a $50 trial credit, making it an…APIMaster provides a single API key for accessing multiple AI models like GPT, Claude, and DeepSeek at discounted rates. New users receive a $50 trial credit, making it an…

Nano Banana - Google DeepMind

AI Models

Google DeepMind's brand for its Gemini Image models, used for AI image generation and editing. It understands text prompts and uploaded images together, follows…Nano Banana is Google DeepMind's brand for its Gemini Image models, used for AI image generation and editing. It understands text prompts and uploaded images together, follows…

Meta AI Developer

AI Apps

Offers a suite of AI models and tools for developers, including access to Muse Spark and the Meta Model API. These resources help streamline the development process and…Meta offers a suite of AI models and tools for developers, including access to Muse Spark and the Meta Model API. These resources help streamline the development process and…

Nous Research

AI Apps

Leader in the American open source AI movement, specializing in training open source language models and building infrastructure for unbiased training. Their…Nous Research is a leader in the American open source AI movement, specializing in training open source language models and building infrastructure for unbiased training. Their…

Try NVIDIA NIM APIs

AI Apps

NVIDIA NIM APIs enable developers to build enterprise generative AI applications using leading models. With tools like NemoClaw for secure agent execution, users can create AI…

Liquid AI

AI Apps

Develops efficient Liquid Foundation Models (LFMs) for on-device, edge, and cloud AI, focusing on low latency, privacy, and hardware-aware deployment. Their models are…Liquid AI develops efficient Liquid Foundation Models (LFMs) for on-device, edge, and cloud AI, focusing on low latency, privacy, and hardware-aware deployment. Their models are…

Falcon LLM

LLMs

Generative large language model designed to advance applications and use cases, making advanced AI accessible and impactful across various industries and…Falcon LLM is a generative large language model designed to advance applications and use cases, making advanced AI accessible and impactful across various industries and…

Claude Fable 5

LLMs

Designed for complex reasoning and long-horizon tasks. It features safety classifiers to manage request refusals, ensuring secure and efficient operations.Claude Fable 5 is designed for complex reasoning and long-horizon tasks. It features safety classifiers to manage request refusals, ensuring secure and efficient operations.