Liu Feng

DataEvolver. Autonomous synthetic data construction via VLM-guided iterative rendering — let your data build and improve itself.

cross-domain-seismic-fm-master. Cross-domain transfer learning framework that adapts vision foundation models for seismic interpretation. Includes seismic-to-vision bridging, LoRA/prefix tuning, geological prompting, and interpretation examples.

slab2. Slab2.0 is a three-dimensional compilation of global subduction geometries, separated into regional models for each major subduction zone.

bubblewrap. Low-level unprivileged sandboxing tool used by Flatpak and similar projects

nature-skills. 符合nature论文学术表达和科研绘图的Skill

codegraph. Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

PaperRadar. Track and summarize new geophysics preprints from arXiv and EarthArXiv. 自动追踪、解析并总结 arXiv 与 EarthArXiv 最新地球科学预印本。

Cool-EarthScience-Foundation-Models.

scp. Jupyter Notebook

awesome-agent-skills. A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

codex. Lightweight coding agent that runs in your terminal

ml-intern. 🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

LightRAG. [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

graphify. Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

DataFlow. Easy Data Preparation with latest LLMs-based Operators and Pipelines.

ResearchClawBench. 🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

supermemory. Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

mineru-tianshu. 天枢 - 企业级 AI 一站式数据预处理平台 | PDF/Office转Markdown | 支持MCP协议AI助手集成 | Vue3+FastAPI全栈方案 | 文档解析 | 多模态信息提取

voiss-net. Detection and characterization of volcanic tremor using machine learning

inkos. Story Creation AI Agent for novel, scripts, translation, interactive games, and IP content

deer-flow. An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

InternAgent. InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

prompt-optimizer. An AI prompt optimizer for writing better prompts and getting better AI results.

DisbaTomo. C++

MLEvolve. MLEvolve is an open-source autonomous system for end-to-end machine learning algorithm design and optimization powered by progressive search and experience-driven memory.

autoresearch. AI agents running research on single-GPU nanochat training automatically

langextract. A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Awesome-Scientific-Skills. An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it!

skills. Public repository for Agent Skills

scientific-agent-skills. Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

VASPilot. An automatic tool utilizing multi agent framework CrewAI and MCP for VASP calculation.

py_cap. Python utilities for running GCAP (a source mechanism inversion code by Zhu L.)

hashpy. Python wrapped fork of HASH first motion focal mechanism code.

covseisnet. Python

simpeg. Simulation and Parameter Estimation in Geophysics - A python package for simulation and gradient based parameter estimation in the context of geophysical applications.

SciEvalKit. A unified evaluation toolkit and leaderboard for rigorously assessing the scientific intelligence of large language and vision–language models across the full research workflow.

SGI-Bench. Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

bruces. A bunch of really useful codes for earthquake stuff

global_tectonics. Tectonic maps for data analysis applications in solid Earth science

etas. calibrate ETAS, simulate using ETAS, estimate completeness magnitude & magnitude frequency distribution

fullwave25. Fullwave 2.5: Ultrasound wave propagation simulation with heterogeneous power law attenuation modelling capabilities

oq-engine. OpenQuake Engine: a software for Seismic Hazard and Risk Analysis

OpenHands. 🙌 OpenHands: AI-Driven Development

nanochat. The best ChatGPT that $100 can buy.

neuraloperator. Learning in infinite dimension with neural operators.

urban_das. Urban sensing using existing fiber-optic networks

ToolUniverse. Democratizing AI scientists with ToolUniverse

CRESt. Automated robotic platform for conducting electrochemical reactions at MIT

qseek. The earthquake detection and localization framework 🔥

SeismoStats. A Python package for seismicity analysis.

bookmarks. Links for Geophysics & Seismology research

REAL. Rapid Earthquake Association and Location

hypoDDpy. A collection of scripts to steer HypoDD by Felix Waldhauser.

Hypo-Interface-Py. Interface for HypoInverse & HypoDD, implemented with Python.

earthquake_catalog_book. Repository for the Cascadia earthquake catalog project: https://cascadiaquakes.github.io/earthquake_catalog_book/

nllgrid. Python class for reading and writing NLLoc grid files.

NonLinLoc. Probabilistic, Non-Linear, Global-Search Earthquake Location in 3D Media

LLM-Geo. Jupyter Notebook

pyrocko. An official read-only mirror of https://git.pyrocko.org/pyrocko/pyrocko. A seismology toolkit for Python.

seislib. Seismic imaging at local, regional, and global scale

SciToolAgent. SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

markitdown. Python tool for converting files and office documents to Markdown.

deepwiki-md-chrome-extension. chrome extension used to convert deepwiki/github-repo to markdown can be downloaded

GaMMA. GaMMA: Earthquake Phase Association using a Bayesian Gaussian Mixture Model

segyio. Fast Python library for SEGY files.

SurfQuake. Python

seismoviz. A Python library for efficient seismic catalog visualization and analysis - from quick data exploration to publication-ready figures in few lines of code.

EQcorrscan. Earthquake detection and analysis in Python.

EarthLink. EarthLink: A Self-Evolving AI Agent System for Climate Science

OpenSWI. A Massive-Scale Benchmark Dataset for Surface Wave Dispersion Curve Inversion

IDEA. The Intelligent Data Exploring Assistant (IDEA) helps users efficiently explore and visualize datasets, specializing in geophysical data like sea levels. IDEA was developed at the University of Hawaii Sea Level Center for the Station Explorer Assistant (SEA) and other science applications.

obspy. ObsPy: A Python Toolbox for seismology/seismological observatories.

epymarl. An extension of the PyMARL codebase that includes additional algorithms and environment support

synthoseis. Generating seismic data and associated labels to train deep learning networks.

HAVEN. Codes for the paper "HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism"

guitar. [SIGGRAPH Asia 2024] Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing

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

Pi3. [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning

Time-R1. Time-R1 is a two-stage reinforcement fine-tuning framework that trains large language models to perform slow-thinking, step-by-step reasoning for accurate and explainable time series forecasting.

GlobalTomo. The first global synthetic dataset for physics-ML seismic wavefield modeling and full-waveform inversion

PKIKP_Onset_Picker. This is the repo for article: Deep-Learning Phase-Onset Picker for Deep Earth Seismology: PKIKP Waves

ddim. Denoising Diffusion Implicit Models

stable-diffusion. A latent text-to-image diffusion model

Fast-GPR-FWI. This repository gives the codes for "Fast ground penetrating radar dual parameters full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorch".

Py-lithology. Using python to plot some lithology patterns.

PEACE. PEACE: Empowering Geologic Map Holistic Understanding with MLLMs [Official, CVPR 2025]

StructuralGeo. Jupyter Notebook

ExtremeCast. ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast

EQNet. Jupyter Notebook

TradingAgents. TradingAgents: Multi-Agents LLM Financial Trading Framework

SWChinaCVM-1.0.

VAE-FWI. Full waveform inversion uncertainty analysis using variational deep learning

QuakeScope. Jupyter Notebook

DAS-realtime. Python

OmniEarth-Bench. Official repo for "OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data"

CCformer. Code in "Attention Mechanism-based Improvement of Stacked Surface Wave Cross-correlation from High-frequency Ambient Noise"

MinerU. Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

XLRS-Bench. [CVPR 2025 HIghlight] XLRS-Bench: ould Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?

Falcon. Falcon: A Remote Sensing Vision-Language Foundation Model

Siamese_FWI-pub. Official reproducible material for SiameseFWI: A Deep Learning Network for Enhanced Full Waveform Inversion

SeismicFoundationModel. Seismic Foundation Model

Official_TSSUN. Official implementation code of Temporal-Spectral-Spatial Unified Network

SeisMoLLM. Official Pytorch Implementation of [GRL] SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Model

Elastic-Full-Waveforrm-Inversion. Python

SurfTomoCNN-new. Using Deep-Learning to do surface wave tomography

Wasserstein-Cycle-GAN-for-Surface-Wave-Tomography. Code and Benchmark Examples for JGR: Solid Earth paper

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

ADD-FWI. Python

Time-Series-Library. A Library for Advanced Deep Time Series Models for General Time Series Analysis.

TimesNet. About Code release for "TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis" (ICLR 2023), https://openreview.net/pdf?id=ju_Uqw384Oq

DiffusionPDE. Official implementation of NeurIPS 2024 paper "DiffusionPDE: Generative PDE-Solving Under Partial Observation"

csm. A Conversational Speech Generation Model

Crossformer. Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting"

TSFpaper. This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the type of model.

Informer2020. The GitHub repository for the paper "Informer" accepted by AAAI 2021.

VisionTS. Code for our paper "VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters".

RevIN. RevIN: Reversible Instance Normalization For Accurate Time-series Forecasting Against Distribution Shift

PatchTST. An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

iTransformer. Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)

cvpr-latex-template. Extended LaTeX template for CVPR/ICCV papers

AA-Forecast. Repository for the AA-Forecast paper ECML PKDD 2022

Awesome-time-series. A comprehensive survey on the time series domains

Aseq_DIP. Jupyter Notebook

Autoformer. About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008

Ada-MSHyper. Python

DAPS. [CVPR 2025 Oral] Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing

litellm. The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

DispFormer. DispFormer: A Pretrained Transformer Incorporating Physical Constraints for Dispersion Curve Inversion

FyeldGenerator. Easily generate random fields

POT. POT : Python Optimal Transport

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

FastXC. High Performance Noise Cross-Corelation Computing Code for 9-component Recordings

aisuite. Simple, unified interface to multiple Generative AI providers

Skip-DiT. ✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

efficient-kan. An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

seisLM. Jupyter Notebook

GeophysicalJointInversion. Python

AI_Science_Engineering. This repository is the official project page of the course AI in the Sciences and Engineering, ETH Zurich.

IQA-PyTorch. 🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

deep-generative-prior. Code for deep generative prior (ECCV2020 oral)

evodcinv. Inversion of dispersion curves using Evolutionary Algorithms

WeatherGFT. [NeurIPS'24] Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling

FiT. [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model

OpenFWI. A collection of codes with OpenFWI project

GPT_API_free. Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。

EmbodiedScan. [CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

PLAN4Earthquake_Monitoring. Code of 'An all-in-one seismic phase picking, location, and association network for multi-task multi-station earthquake monitoring'

diffseis. Jupyter Notebook

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

diffefwi. Official repository for the "Learned regularizations for multi-parameter elastic full waveform inversion using diffusion models" paper.

guided-diffusion. Python

MCG_diffusion. Official PyTorch implementation of the NeurIPS 2022 paper "Improving Diffusion Models for Inverse Problems using Manifold Constraints (https://arxiv.org/abs/2206.00941)"

ADTomo. Python

ArgumentProcessor.jl. Commandline argument parser

FWIGAN. This repo contains a PyTorch implementation with DeepWave for the manuscript FWIGAN: Full-waveform inversion via a physics-informed generative adversarial network

Geophysics. FD/RTM/FWI/TOMO/RayTracing, ISO/VTI/TTI, su/segy/sgy, C/C++/java, MPCH/OpenMPI/OpenMP/CUDA/, CWP/Madagascar

Azure2019. Azure workflow for SLIM algorithms.

CTDiagnosis. Python

score_inverse_problems. Official repo for "Solving Inverse Problems in Medical Imaging with Score-Based Generative Models"

distpy. An Open Source python module for rapid prototyping Distributed Acoustic Sensing (DAS) processing flows

DASPy. DASPy: A Python Toolbox for DAS (Distributed Acoustic Sensing) data processing.

dascore. A python library for distributed fiber optic sensing

awesome-das. A curated list of DAS tools and resources.

zotero-style. Ethereal Style for Zotero

DENISE-Black-Edition. 2D time-domain isotropic (visco)elastic FD modeling and full waveform inversion (FWI) code for P/SV-waves

FDwave3D. MATLAB

ADTomo.jl. Eikonal Tomography and Earthquake Location using Automatic Differentiation

PGNN. Physics-guided Neural Networks (PGNN) : An Application In Lake Temperature Modelling

single-station-earthquake-location. Single station earthquake location through full waveform matching

wassdistance. Approximating Wasserstein distances with PyTorch

soft-dtw. Python implementation of soft-DTW.

pytorch-softdtw. An implementation of SoftDTW for PyTorch.

pysdtw. Torch implementation of Soft-DTW, supports CUDA.

LOC-FLOW. Earthquake Location WorkFlow

pysit. Python

SeisT. [TGRS] SeisT: A Foundational Deep-Learning Model for Earthquake Monitoring Tasks

USTC-Pickers. A Unified Set of seismic phase pickers Transfer learned for China

ADOL-C. A Package for Automatic Differentiation of Algorithms Written in C/C++

PyFWI. This repository is for PyFWI, a Python package for seismic FWI and reservoir monitoring (time-lapse FWI)

pinn_fwi. PGNN-FWI: performing physics-guided neural network for FWI

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

stead-earthquake-cnn. Python

CapsPhase. CapsPhase: Capsule Neural Network for Seismic Phase Classification and Picking

PhaseNet. PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method

readDiTingExample. the jupyter notebook for reading DiTing dataset

PhaseGen. Synthesizing fake waveforms conditioned by given P- and S- arrivals

SeisCLIP. The code of Paper 'SeisCLIP: A seismology foundation model pre-trained by multimodal data for multipurpose seismic feature extraction'

ADsurf. An automatic differentiation based (AD-based) multimodal surface wave inversion tools

FastSpeech2. An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

MockingBird. 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

StudyNotes. 个人学习笔记

programming-tutorial. 🎈 Welcome to programming-notebook, a notebook mainly about scientific notes.

awesome-self-supervised-learning. A curated list of awesome self-supervised methods

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

AP-BSN. Official PyTorch implementation of "AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network" in CVPR 2022.

noise2self. A framework for blind denoising with self-supervision.

CSBDeep. Image restoration for fluorescence microscopy

n2v. This is the implementation of Noise2Void training.