Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

Academic Research Skills for Claude Code: research → write → review → revise → finalize

Elevate your AI research writing, no more tedious polishing ✨

Validate your remarkable idea with Claude Skill. 用 AI Skill 验证你的好想法

Equivariant machine learning interatomic potentials in JAX.

Torch-native, batchable, atomistic simulations.

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

🌸 A command-line fuzzy finder

Independent PyTorch implementation of Scene Representation Transformer

MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.

Solv@TUM - The Solvation Free Energy Database

Training Neural Network potentials through customizable routines in JAX.

Distributed Asynchronous Hyperparameter Optimization in Python

Deep reinforcement learning to perform shape optimization

Learning in infinite dimension with neural operators.

北航研究生学位论文模板（Word+LaTeX）.

Learning Continuous Signed Distance Functions for Shape Representation

Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems

Universal modeling and simulation of fluid mechanics upon machine learning. From the Boltzmann equation, heading towards multiscale and multiphysics flows.

Must-read papers on graph neural networks (GNN)

TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.

This AI Smart Speaker uses speech recognition, TTS (text-to-speech), and STT (speech-to-text) to enable voice and vision-driven conversations, with additional web search capabilities via OpenAI and…

Have a conversation with ChatGPT using your voice, and have it talk back.

PDEBench: An Extensive Benchmark for Scientific Machine Learning

All course materials for the Zero to Mastery Deep Learning with TensorFlow course.

Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data