#Foundation-models
Showing 60 of 108 repositories tagged #foundation-models, ranked by stars
Making large AI models cheaper, faster and more accessible
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Janus-Series: Unified Multimodal Understanding and Generation Models
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
β‘ TabPFN: Foundation Model for Tabular Data β‘
Data processing for and with foundation models! π π π½ β‘οΈ β‘οΈπΈ πΉ π·
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
OpenSquilla β Token-Efficient AI Agent with same budget, higher intelligence density
Chronos: Pretrained Models for Time Series Forecasting
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code π.
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model
𦦠Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
SuperCLUE: δΈζιη¨ε€§ζ¨‘εη»Όεζ§εΊε | A Benchmark for Foundation Models in Chinese
Images to inference with no labeling (use foundation models to train supervised models).
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
A curated list of Graph/Transformer-based fraud, anomaly, and outlier detection papers & resources
Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models
ζ₯ζ¬θͺLLMγΎγ¨γ - Overview of Japanese LLMs
TabICLv2: A state-of-the-art tabular foundation model
A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.
Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024) and subsequent works
[CVPR 2024 π₯] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.
Implementation of the Aurora model for Earth system forecasting
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention
Foundation Models for Genomics & Transcriptomics
Explore and understand your training and validation data.
A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites
β¨β¨Latest Papers and Benchmarks in Reasoning with Foundation Models
[CVPR26] TESSERA is a foundation model that can process time-series satellite imagery for applications such as land classification and canopy height prediction. Developed at the University of Cambridge, it enables efficient extraction of temporal patterns from Earth observation
Free self-driving car stack - fully open-source ADAS and autonomous driving system
[ICLR2025 Spotlightπ₯] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
MathCode: A Frontier Mathematical Coding Agent
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
Large Language & Foundation Models for Time Series.
Recent research papers about Foundation Models for Combinatorial Optimization
π¦βπ₯ Agent Runtime, MacOS/iOS/Linux Pure Swift 6.3
This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.
Framework and Language for Neurosymbolic Programming.
[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"
The official repo for [TPAMI'25] "HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model"
A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.
π Mega Scale Multimodal DataPipeline for SOTA Foundation Models
Playground examples to demonstrate Foundation Models Framework
Segment-anything related awesome extensions/projects/repos.
Platform for General Robot Intelligence Development
React Native Apple LLM plugin using Foundation Models
Neon Vision Editor - A lightweight, modern code & text editor for macOS built for speed, readability, and automatic syntax highlighting β minimal by design, with fast file access and a focused editing experience.
[ICLR'24] Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
Reliable, minimal and scalable library for pretraining foundation and world models
Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"
Foundation model benchmarking tool. Run any model on any AWS platform and benchmark for performance across instance type and serving stack options.
The official evaluation suite and dynamic data release for MixEval.