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

🦦 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.

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

EVA Series: Visual Representation Fantasies from BAAI

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

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

Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)

Emu Series: Generative Multimodal Models from BAAI

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Creative interactive views of any dataset.

Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

[CVPR 2024 🔥] 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.