High-Resolution Image Synthesis with Latent Diffusion Models

Official repo of BesiegeField, an interactive and real-time environment for machine construction and simulation (arXiv:2510.14980).

This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"

learning classical density functionals for ionic fluids

Package for training neural free energy functionals in 1D.

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Full code for all experiments in the paper "Denoising Hamiltonian Network for Physical Reasoning"

A curated list of resources about generative flow networks (GFlowNets).

Official Implementation for "Consistency Flow Matching: Defining Straight Flows with Velocity Consistency"

[ICLR 2025 Spotlight] Grounding Video Models to Actions through Goal Conditioned Exploration

Denoising Hamiltonian Network for Physical Reasoning

Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and shaping the future!

Code for the tutorial/review paper for RL-based-fine-tuniing. In this code, we especially focus on the design of biological sequences like DNA (enhancers) and RNA (UTRs) design.

Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

Dimple, the first Discrete Diffusion Multimodal Large Language Model

Time- and space-continuous neural PDE forecaster based on INRs and ODEs - ICLR 2023

A library for scientific machine learning and physics-informed learning

Python package for solving partial differential equations using finite differences.

Lets make video diffusion practical!

Public development project of the LAMMPS MD software package

[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.

[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

Molecular dynamics in external potentials using PyLAMMPS