NumPy & SciPy for GPU

An implementation of chunked, compressed, N-dimensional arrays for Python.

Variational Animal Motion Embedding - A tool for time series embedding and clustering

Frontier Multimodal Foundation Models for Image and Video Understanding

Variational Animal Motion Embedding - A tool for time series embedding and clustering

Janus-Series: Unified Multimodal Understanding and Generation Models

Fast and accurate automatic speech recognition (ASR) for edge devices

TTS with kokoro and onnx runtime

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

Official implementation of "Test-Time Zero-Shot Temporal Action Localization", CVPR 2024

a state-of-the-art-level open visual language model | 多模态预训练模型

[ECCVW'24] Long-form Video Understanding by Bridging Episodic Memory and Semantic Knowledge

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

Code for ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, Du…

Agno is a lightweight framework for building multi-modal Agents

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

The official code of "CSTA: CNN-based Spatiotemporal Attention for Video Summarization"

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

tiny vision language model

Repository for 2nd generation Bpod platform (formerly beta branch of Bpod repository)

Simple, unified interface to multiple Generative AI providers

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'