Official repository for the paper "CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models"

A generative world for general-purpose robotics & embodied AI learning.

Chronos: Pretrained Models for Probabilistic Time Series Forecasting

DepthAI Python Library

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

CVPR 2024: Language Guided Generation of 3D Embodied AI Environments.

Live reload cad scripting because >lmao UIs

Geometry library for topological robustness

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Official inference framework for 1-bit LLMs

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Code for "AVG-LLaVA: A Multimodal Large Model with Adaptive Visual Granularity"

NeurCADRecon: Neural Representation for Reconstructing CAD Surfaces by Enforcing Zero Gaussian Curvature

[IV2022] Implements a deep RNN based Point Cloud Compression approach for Velodyne Point Clouds. Reference implementation of corresponding IEEE IV22 paper.

Material related to the practical sessions and assessment of the ML module, AIMS-CDT, University of Oxford

Vision infrastructure to turn complex documents into RAG/LLM-ready data

podcastfy.ai gradio demo app

A fast and intuitive tool for visualizing and analyzing model structures from safetensors files, supporting tree-based visualizations and detailed parameter analysis.

OpenMMLab Pose Estimation Toolbox and Benchmark.

Quickly add MediaPipe Pose Estimation and Detection to your iOS app. Enable powerful features in your app powered by the body or hand.

Text analytics for LLM apps. Cluster messages to detect use cases, outliers, power users. Detect intents and run evals with LLM (OpenAI, MistralAI, Ollama, etc.)

[CVPR 2025] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.

PRQL is a modern language for transforming data — a simple, powerful, pipelined SQL replacement

[NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"

Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text" (NeurIPS 2024).

[ECCV 2024] Code for VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models