Skip to content

@AQ-MedAI AQ | Medical AGI

Change the repository type filter

All

    Repositories list

    17 repositories

    • LiveClin

      Public
      LiveClin is a live benchmark designed for the faithful replication of clinical practice
      Python
      •
      Apache License 2.0
      •0•13•0•0•Updated Feb 27, 2026Feb 27, 2026

    • ClinAlign

      Public
      Python
      •
      Apache License 2.0
      •0•6•1•0•Updated Feb 11, 2026Feb 11, 2026

    • PulseMind

      Public
      Python
      •0•18•3•0•Updated Jan 28, 2026Jan 28, 2026

    • RagQALeaderboard

      Public
      RAG-QA Leaderboard
      qabenchmarkrag
      qabenchmarkrag
      Python
      •
      Other
      •1•25•0•0•Updated Jan 27, 2026Jan 27, 2026

    • Diver

      Public
      Complex Reasoning Rag System, Agentic Rag System
      Python
      •
      Apache License 2.0
      •24•252•4•0•Updated Jan 21, 2026Jan 21, 2026

    • MrlX

      Public
      MrlX: A Multi-Agent Reinforcement Learning Framework
      Python
      •
      MIT License
      •12•199•1•0•Updated Jan 19, 2026Jan 19, 2026

    • Laos_System

      Public
      Laos_System provides a configurable end-to-end pipeline that converts clinical speech/text notes into structured JSON documents for: admission, surgery and disc…
      Python
      •
      Apache License 2.0
      •2•20•0•0•Updated Jan 7, 2026Jan 7, 2026

    • Kimi-K2-Instruct-EAGLE3

      Public
      Complete EAGLE3-based speculative decoding solution for Kimi-K2-Instruct, including the draft model and training dataset, achieving a 3+ token acceptance rate o…
      0•0•0•0•Updated Dec 5, 2025Dec 5, 2025

    • PRGB

      Public
      [AAAI 2026]RAG, Benchmark, robust RAG generation
      qabenchmarkrag
      qabenchmarkrag
      Python
      •
      Other
      •4•34•0•0•Updated Nov 20, 2025Nov 20, 2025

    • MHB

      Public
      Medical Hallucination Benchmark
      0•0•0•0•Updated Nov 12, 2025Nov 12, 2025

    • MedEQBench

      Public
      The MedEQBench is the first evaluation suite specifically designed for medical contexts to assess Large Language Models' (LLMs) capabilities in emotional percep…
      Python
      •0•17•0•0•Updated Nov 11, 2025Nov 11, 2025

    • MedicalAiBenchEval

      Public
      A comprehensive medical AI evaluation framework based on GAPS methodology. Features automated assessment pipeline, thoracic surgery dataset (92 cases), multi-mo…
      Python
      •
      MIT License
      •3•41•0•0•Updated Nov 3, 2025Nov 3, 2025

    • QReward

      Public
      [QReward] RewardService Python Client, make RL Training reward function more faster
      trainingreinforcement-learningrl
      trainingreinforcement-learningrlreward-service
      Python
      •
      Apache License 2.0
      •0•15•1•0•Updated Oct 17, 2025Oct 17, 2025

    • .github

      Public
      0•0•0•0•Updated Sep 30, 2025Sep 30, 2025

    • MedResearcher-R1

      Public
      MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.
      agentmedical-aillm
      agentmedical-aillmdeepresearch
      Python
      •
      Apache License 2.0
      •45•489•5•0•Updated Sep 1, 2025Sep 1, 2025

    • medDQA_benchmark

      Public
      Official repository of RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning (https://arxiv.org/abs/2402.14840)
      Python
      •
      Other
      •2•7•1•0•Updated Apr 16, 2024Apr 16, 2024

    • SPs_benchmark

      Public
      Python
      •0•4•0•0•Updated Apr 13, 2024Apr 13, 2024