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.

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

Chronos: Pretrained Models for Time Series Forecasting

DeepSeek-VL: Towards Real-World Vision-Language Understanding

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 🚀.

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

🦦 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: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

Images to inference with no labeling (use foundation models to train supervised models).

EVA Series: Visual Representation Fantasies from BAAI

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding