Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

Official PyTorch Implementation of "History-guided Video Diffusion"

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Easily run PyTorch on multiple GPUs & machines

[CVPR 2024] SinSR: Diffusion-Based Image Super-Resolution in a Single Step

Less is More: High-value Data Selection for Visual Instruction Tuning

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Comparison between Frechet Video Distance implementation from StyleGAN-V and the original paper

A comprehensive library for implementing LLMs, including a unified training pipeline and comprehensive model evaluation.

Official implementation of AnimateDiff.

[ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.

(ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life

Code for "Goal-Conditioned Predictive Coding for Offline Reinforcement Learning" (NeurIPS 2023)

This repository contains a collection of resources and papers on Diffusion Models for RL, accompanying the paper "Diffusion Models for Reinforcement Learning: A Survey"

Related papers for reinforcement learning, including classic papers and latest papers in top conferences

Code for EMNLP 2023 paper "Emergence of Abstract State Representations in Embodied Sequence Modeling"

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

A beautiful, simple, clean, and responsive Jekyll theme for academics

本人的科研经验

MTM Masked Trajectory Models for Prediction, Representation, and Control.

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

A curated list of Diffusion Model in RL resources (continually updated)

A new markup-based typesetting system that is powerful and easy to learn.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…