ReactMotion: Generating Reactive Listener Motions from Speaker Utterance

SOMA BVH to humanoid robot motion retargeting library built with Newton and NVIDIA Warp

Monocular whole-body 3D human pose estimation using the SOMA body model

Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.

SOMA: Unifying Parametric Human Body Models

A web application for browsing and viewing the BONES-SEED motion capture dataset

Running VLA at 30Hz frame rate and 480Hz trajectory frequency

Causal video-action world model for generalist robot control

在mujoco仿真环境中收集VLA训练数据，通过lerobot框架进行VLA模型的训练、验证

The unitree_il_lerobot open-source project is a modification of the LeRobot open-source training framework, enabling the training and testing of data collected using the dual-arm dexterous hands of…

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

Spirit-v1.5: A Robotic Foundation Model by Spirit AI

GLM-4-Voice | 端到端中英语音对话模型

Implementation for MIBURI: Towards Expressive Interactive Gesture Synthesis (CVPR 2026)

Implementation of simples transformers, including BERT for text classification and simple GPT using AliBi as positional encoding.

An unified model for 4D human-scene reconstruction

A Pytorch Implementation of Finite Scalar Quantization

🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.

Code release for PianoMotion10M

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838