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

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

RL Extension Library for Robots, Based on IsaacLab.

MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation

MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation

MultiModalWBC is a fully open-source, IsaacLab-based framework for multi-modal whole-body control, designed for motion imitation, motion tracking, and task-conditioned control in legged robots. The…

Create motion for any robot through editing keyframe

WACV 2026: Theory, Experiments, Dataset, and Code for our newly proposed 3D Sign Language Reconstruction method DexAvatar

Official implementation of “Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Framework” (Knowledge-Based Systems, 2026)

the Quest for Generalizable Motion Generation: Data, Model, and Evaluation

以 MDM (Motion Diffusion Model) 为算法底座，引入 LoRA 垂直微调，并结合 LangGraph 实现复杂长任务的智能体编排。

TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control

A reading list of video generation

Code for paper "FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation"

PersonaLive! : Expressive Portrait Image Animation for Live Streaming

End-to-end pipeline converting generative videos (Veo, Sora) to humanoid robot motions

Towards Unified Latent VLA for Whole-body Loco-manipulation Control

Foundation Models and Data for Human-Human and Human-AI interactions.

Training scripts combining HVGMR, GMR, and Beyondmimic

This repository provides a flexible pipeline for converting 3D skeleton joints into their corresponding SMPLX mesh representations. It supports skeleton formats that are not based on OpenPose, such…

Convert CSV motion data to MuJoCo format with velocity visualization

Isaaclab based Parkour locomotion