Skip to content

@DataArcTech DataArcTech

Change the repository type filter

All

    Repositories list

    35 repositories

    • ConflictHarm

      Public
      [ACL'26] Repository for the Paper "Conflicts Make Large Reasoning Models Vulnerable to Attacks"
      Python
      •
      MIT License
      •0•0•1•0•Updated Apr 14, 2026Apr 14, 2026

    • ToG-3

      Public
      Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval
      raggraphragmultimodal-rag
      raggraphragmultimodal-rag
      Python
      •
      MIT License
      •13•86•6•0•Updated Apr 9, 2026Apr 9, 2026

    • GraphSearch

      Public
      GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation
      Python
      •
      Apache License 2.0
      •12•95•0•0•Updated Apr 9, 2026Apr 9, 2026

    • Awesome-FinLLMs

      Public
      🥇 A curated list of awesome large language models in finance(FinLLMs), including papers,models,datasets and codebases. 金融大模型列表，特别是中英双语大模型。
      Apache License 2.0
      •7•60•0•0•Updated Apr 7, 2026Apr 7, 2026

    • Awesome-LLMs-for-Mathematical-Modeling

      Public
      🥇 A curated list of awesome Large Language Models/Agents for Mathematical Modeling tasks, including papers,models,datasets and codebases. 专门用于数学建模任务的大模型/Agent。
      Apache License 2.0
      •0•6•0•0•Updated Apr 7, 2026Apr 7, 2026

    • F5-TTS-NPU

      Public
      NPU version of "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
      Python
      •
      MIT License
      •2.1k•0•0•0•Updated Mar 27, 2026Mar 27, 2026

    • ai-video-dubber

      Public
      AI Video Dubbing Agent — automatically dubs videos from any language to any language with speaker cloning, Gemini multimodal optimization, and ElevenLabs TTS
      Python
      •0•0•0•0•Updated Mar 23, 2026Mar 23, 2026

    • team-dev-agent

      Public
      AI-driven software development workflow for teams. Claude Code + Codex best practices, frontend UI prompts, quality gates, and automation scripts.
      frontendskillsoftware-development
      frontendskillsoftware-developmentfullstackcodexai-agentsprompt-engineeringclaude-codeopenclaw
      Shell
      •1•2•0•0•Updated Mar 20, 2026Mar 20, 2026

    • RAG-ARC

      Public
      A modular, high-performance Retrieval-Augmented Generation framework with multi-path retrieval, graph extraction, and fusion ranking
      knowledge-basemultimodalrag
      knowledge-basemultimodalragllmagenticgraphrag
      Python
      •
      MIT License
      •12•42•0•1•Updated Mar 4, 2026Mar 4, 2026

    • DataArc-SynData-Toolkit

      Public
      Synthetic Data Generation Platform By DataArcTech
      Python
      •53•1.7k•8•1•Updated Feb 28, 2026Feb 28, 2026

    • .github

      Public
      0•0•0•0•Updated Feb 9, 2026Feb 9, 2026

    • DataSet-Gen

      Public
      用于多PDF的多跳QA对合成
      dataset-generationdocdancer
      dataset-generationdocdancer
      Python
      •0•2•0•0•Updated Jan 21, 2026Jan 21, 2026

    • AIPracticePartner

      Public
      Go
      •0•0•0•0•Updated Jan 13, 2026Jan 13, 2026

    • SoE

      Public
      [EACL'26] Repository for the Paper "Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs"
      Python
      •
      Apache License 2.0
      •1•4•1•0•Updated Jan 12, 2026Jan 12, 2026

    • RAGExplorer

      Public
      This is the code repository for the paper "RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systems".
      TypeScript
      •3•0•0•0•Updated Dec 11, 2025Dec 11, 2025

    • SQL-R1

      Public
      [NeurIPS'25] Official Repository for the Paper "SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning"
      databasereinforcement-learningreasoning
      databasereinforcement-learningreasoningnl2sqltext2sql
      Python
      •
      Apache License 2.0
      •18•137•3•0•Updated Nov 20, 2025Nov 20, 2025

    • LLM-as-a-Judge

      Public
      6•174•3•0•Updated Oct 12, 2025Oct 12, 2025

    • JudgeAgent

      Public
      This is the source code of the paper "JudgeAgent: Dynamically Evaluate LLMs with Agent-as-Interviewer".
      Python
      •0•4•0•0•Updated Sep 25, 2025Sep 25, 2025

    • LongFaith

      Public
      LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data (ACL 2025)
      Python
      •1•9•0•0•Updated May 29, 2025May 29, 2025

    • CATS

      Public
      Offical code implementation of our AAAI2025 paper "Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning"
      Python
      •2•25•0•0•Updated May 26, 2025May 26, 2025

    • ChartBench

      Public
      Python
      •1•15•5•0•Updated May 15, 2025May 15, 2025

    • CSPO

      Public
      This repository contains the implementation of CSPO, a novel framework for stock price movement forecasting that leverages cross-market synergy and pseudo-volat…
      Python
      •6•1•0•0•Updated Apr 15, 2025Apr 15, 2025

    • ChartMoE

      Public
      [ICLR2025 Oral] ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding
      transformerscode-generationtable-generation
      transformerscode-generationtable-generationvision-language-modelmultimodal-large-language-modelsjson-generationchart-understanding
      Jupyter Notebook
      •9•99•5•0•Updated Apr 1, 2025Apr 1, 2025

    • ToG-2

      Public
      Python
      •
      Apache License 2.0
      •20•110•3•0•Updated Feb 18, 2025Feb 18, 2025

    • Simple-HHEA

      Public
      Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
      Python
      •1•17•3•0•Updated Feb 18, 2025Feb 18, 2025

    • Golden-Touchstone

      Public
      🥇 [EMNLP 2025] Golden Touchstone is a simple, effective, and systematic benchmark for bilingual (Chinese-English) financial large language models, driving the r…
      Python
      •
      Apache License 2.0
      •0•9•0•0•Updated Feb 10, 2025Feb 10, 2025

    • RagVL

      Public
      Official PyTorch Implementation of MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-inj…
      Python
      •
      MIT License
      •5•91•5•0•Updated Nov 15, 2024Nov 15, 2024

    • ChatEA

      Public
      Python
      •0•13•2•0•Updated Oct 9, 2024Oct 9, 2024

    • self-improving

      Public
      Python
      •0•1•0•0•Updated Jul 19, 2024Jul 19, 2024

    • timesfm-pytorch

      Public
      Pytorch Implementation of TimesFM (Time Series Foundation Model) , a pretrained time-series foundation model developed by Google Research for time-series foreca…
      Python
      •
      Apache License 2.0
      •1.8k•2•0•0•Updated Jul 9, 2024Jul 9, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.