[CVPR 2024 - Highlight] FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation

PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

The public EgoSim Repository

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

This is the official repository of GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation

An aggregation of human motion understanding research.

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…

Open-source high-performance RISC-V processor

Orbbec SDK v1&v2 Pre-Compiled Repo

Bringing BERT into modernity via both architecture changes and scaling

[ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

This is the official repository of SIGGRAPH Asia 2024 Paper: Autonomous Character-Scene Interaction Synthesis from Text Instruction

Jupyter notebook with Pytorch implementation of Neural Ordinary Differential Equations

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

[CVPR 2025] Prompt Depth Anything

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

[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

T2I-Adapter

Code from the ECCV 2024 paper "Animal Avatar Reconstructing Animatable 3D Animals from Casual Videos".

[NeurIPS D&B Track 2024] Source code for the paper "Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge"

Agent-to-Sim Learning Interactive Behavior from Casual Videos.

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Multi-person trajectory dataset in diverse indoor scenes

SPEAR: A Simulator for Photorealistic Embodied AI Research

Official repository for gathering data of Revisit Human-Scene Interaction via Space Occupancy (ECCV 2024).

A minimal GPU design in Verilog to learn how GPUs work from the ground up