LAVIS - A One-stop Library for Language-Vision Intelligence

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A library for generative social simulation

A library for human kinematic motion and numerical optimization solvers to apply human motion

[SIGGRAPH Asia 2023] AdaptNet: Policy Adaptation for Physics-Based Character Control

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Fine-tune LLM agents with online reinforcement learning

An open source implementation of CLIP.

code for CVPR'24 "AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents"

Create beautiful diagrams just by typing notation in plain text.

Make human motion capture easier.

A custom view build with Obsidian-Dataview to display tasks from Obsidian-Tasks and from your daily notes in a highly customisable calendar with a wide variety of views

Solving Optical MoCap Automatically

Motion and Shape Capture from Sparse Markers

Long-Term Evolution Project of Reinforcement Learning

[CVPR 2021] Closed-Form Factorization of Latent Semantics in GANs

impact-driven-exploration

Generate Daily Planner from ical feeds

Simulating SMPL humanoid, supporting PHC/PHC-MJX/PULSE/SimXR code bases.

The project page repository for Neural Categorical Priors for Physics-Based Character Control

[CVPR2024] Official implementation of SplattingAvatar.

Controllability-Aware Unsupervised Skill Discovery (ICML 2023)

Lipschitz-constrained Unsupervised Skill Discovery (ICLR 2022)

ICML'20: Intrinsic Reward Driven Imitation Learning via Generative Model

Proximal Policy Optimization(PPO) with Intrinsic Curiosity Module(ICM) on Pyramid env, Unity ML

Code for the paper "Exploration by Random Network Distillation"

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

Author's implementation of Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments (ICCV 2023)