- Toronto
-
04:23
(UTC -04:00) - https://orcid.org/0000-0002-7827-7179
- https://scholar.google.com/citations?user=O4S9gP0AAAAJ
- @JuHuang0802
Highlights
- Pro
Stars
🐟 An OpenAI Fine Tuner written in PowerShell
Agentic framework for computational chemistry and materials science workflows
Paper list of agent for science
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
Learning Hamiltonian Flow Maps via Mean Flow Consistency for Large-Timestep Molecular Dynamics
Community plugin to control Blender 3D with any LLM of your choice
Port of Skala model by Microsoft to JAX. I included tests that test both Torch and JAX equivalence and benchmarks. Models qualitatively agree with non-parallelity errors within 2 kcal / mol. Tested…
Intergrating Atomistic Skills into Agentic IDEs (Cursor, Claude Code, Google Antigravity, OpenClaw, etc)
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
A chemical language model for reticular materials design
Full-pipeline AI agent for Nature-series journal writing. Supports OpenClaw, Claude Code, and Codex. Covers journal selection, drafting, figure generation, citation verification, and reviewer respo…
Code for XRD-based structure optimization that was used in the study presented in "The Loss Landscape of Powder X-Ray Diffraction-Based Structure Optimization Is Too Rough for Gradient Descent".
[EMNLP '25] A web app and Python API for multi-modal RAG framework to ground LLMs on high-fidelity materials informatics. An agentic materials scientist powered by @materialsproject, @langchain-ai,…
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
Data repository for the paper "How Accurate Are DFT Forces? Unexpectedly Large Uncertainties in Molecular Datasets"
Universal Transfer Learning in Porous Materials, including MOFs.
Tools to facilitate NLP of scientific literature
Academic Research Skills for Claude Code: research → write → review → revise → finalize
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
About JARVIS-Tools: an open-source software package for data-driven atomistic materials design. Publications: https://scholar.google.com/citations?user=3w6ej94AAAAJ https://www.youtube.com/@dr_k_ch…