Runze Liu's Projects
An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"
DeepMimic Mujoco version; Python only; No Bullet, No C++
Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"
Voice Conversion Experiments for THUHCSI Course : <Digital Processing of Speech Signals>
The repository for the largest and most comprehensive empirical study of visual foundation models for Embodied AI (EAI).
Pytorchππ is delicious, just eat it! ππ
Implements the Equivalent-Policy Invariant Comparison (EPIC) distance for reward functions.
Library to compare and evaluate reward functions
Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation (2023)
Code for "Information-theoretic Task Selection for Meta-Reinforcement Learning".
Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
An initial Attempt at porting Metaworld to a pybullet physics engine
mPLUG-Owlπ¦: Modularization Empowers Large Language Models with Multimodality
[NeurIPS 2022] Official codebase for "Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning".
An open-source framework for training large multimodal models.
Kolmogorov Arnold Networks
A toolkit for robot learning research.
Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback
Open source implementation of "Deep Reinforcement Learning from Human Preferences", updating with evolutionary strategies and augmented morphologies from "Reinforcement Learning for Improved Agent Design"
A large-scale benchmark and learning environment.
Code for paper: Reward Uncertainty for Exploration in Preference-based Reinforcement Learning
Config files for my GitHub profile.