Stars
[ACL 2026 Oral] Official implementation of "STReasoner: Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning"
CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?
[CVPR' 26] Benchmarking PhD-Level Coding in 3D Geometric Computer Vision
[CVPR 2026 Highlight] GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing
IntelliGeo is QGIS plugin that facilitates interaction with Large Language Models in QGIS environment.
[ECCV 2026 🔥] OpenEarthAgent is a unified framework for tool-augmented geospatial agents.
[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
[ICLR 2025] DSBench: How Far are Data Science Agents from Becoming Data Science Experts?
[EMNLP 2024] DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
[TIFS 2025] The official code for TIFS paper "New Visible Watermark Protection Mechanism Based on Information Hiding"
[Neural Networks 2025] The official code for the paper "MNet: A Multi-Scale Network for Visible Watermark Removal."
GeoAnalystBench: A GeoAI benchmark for assessing large language models for spatial analysis workflow and code generation
LLM-agents benchmark set of geospatial tasks requiring multi-step tool use; and LLM-as-Judge based evaluation framework.
[NeurIPS 2024] Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth
SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
[ICCV 2025] UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoing and Understanding.
一个基于 SSH 的正向代理工具，让你的 HTTP/HTTPS 请求从远程主机的网络环境中发出，实现对其可达资源的透明访问。An SSH-powered forward proxy CLI that makes your network requests originate from the remote host.
Dynamic Few shot learning for Knowledge graph Question Answering