CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch.

[ICCV 2025] PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos

(CVPR2026 Oral) ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning

Materials related to Hang Li's book "Machine Learning Methods", in both Chinese and English

My Python scripts to make high-quality figures for publications in top AI conferences and journals.

[ICML 2026] ZwZ model family: SOTA fine-grained perception performace; ZoomBench: a new challenging perception benchmark

⭐️ A cross-platform CLI All-in-One assistant tool for Claude Code, Codex & Gemini CLI.

[NeurIPS 2025 Spotlight] Code for MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting

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

Official Implementation of Accelerating Visual-Policy Learning through Parallel Differentiable Simulation

[ICCV 2025] PyTorch code for the paper "Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning"

ICCV 2025 | TesserAct: Learning 4D Embodied World Models

计算机自学指南

A curated list of behavior(al) foundation model (BFM) papers, articles, tutorials, slides and projects

[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"

[CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation

The official implementations of Intention-conditioned Flow Occupancy Models (InFOM)

[ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".

A framework for training world models with virtual environments, complete with annotated environment dataset (RetroAct), exploration agent (AutoExplore Agent), and GenieRedux-G - an implementation …

RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven explora…

Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning.

PreLAR: World Model Pre-training with Learnable Action Representation, ECCV 2024

[ICCV2025] A Token-level Text Image Foundation Model for Document Understanding

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

Code from the Deep Reinforcement Learning in Action book from Manning, Inc

Edit latex of any arxiv.org paper directly on overleaf

[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"