Freedom AI ORG

The largest open-source medical AI skills library for OpenClaw🦞.

[NeurIPS 2025 & ICLR 2025 Financial AI Best Paper Award] A multi-agent framework that leverages LLMs to simulate socio-economic systems

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

A curated list of medical LLMs, multimodal systems, datasets, benchmarks, and more. 🏥

Medical o1, Towards medical complex reasoning with LLMs

HuatuoGPT, Towards Taming Language Models To Be a Doctor. (An Open Medical GPT)

A Benchmark of Text Classification in PyTorch

HuatuoGPT2, One-stage Training for Medical Adaption of LLMs. (An Open Medical GPT)

Medical Multimodal LLMs

The Largest-scale Chinese Medical QA Dataset： with 26,000,000 question answer pairs.

No description.

No description.

Harnessing 1.4M GPT4V-synthesized Data for A Lite Vision-Language Model

BlenderLLM: A LLM specifically designed to generate CAD scripts based on user instructions. These scripts are then executed in Blender to render 3D models.

CMB, A Comprehensive Medical Benchmark in Chinese

The official Soundwave repository

LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture

Multilingual Medicine: Model, Dataset, Benchmark, Code

paper list on reasoning in NLP

TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis [CVPR 2026 Findings]

Code and Data for paper "GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?"

The code and data for GrammarGPT.

An interpretable large language model (LLM) for medical diagnosis.

Code and data for crosstalk text generation tasks, exploring whether large models and pre-trained language models can understand humor.

No description.

[EMNLP 2025] RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions

An Evaluation of ChatGPT on Information Extraction task, including Named Entity Recognition (NER), Relation Extraction (RE), Event Extraction (EE) and Aspect-based Sentiment Analysis (ABSA).

No description.

A Paper collection for LLM based Patient Simulators

No description.

A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Rubrics

MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning

Towards Fine-grained Audio Captioning with Multimodal Contextual Cues

No description.

MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria

No description.

A collection of research on specialized medical LLMs for specific diseases and distinct medical specialties, organized by ICD-10 chapters.

[ICLR'25] ApolloMoE: Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

No description.

Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];

[ACL 2025] Exploring Compositional Generalization of Multimodal LLMs for Medical Imaging

A factory to standardize LLM adaptation through modularization

Incentivizing Multimodal Complex Reasoning in Dentistry

A trainable user simulator

MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos.

Reproduction of the complete process of DeepSeek-R1 on small-scale models, including Pre-training, SFT, and RL.

Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model

The example for finetuning chatgpt.

Code for COLING22 paper, DPTDR: Deep Prompt Tuning for Dense Passage Retrieval

MyPhoneBench: Do Phone-Use Agents Respect Your Privacy?

The "GPT-API-Accelerate" project provides a set of Python classes for accelerating the process of generating responses to prompts using the OpenAI GPT-3.5 API.

We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance.

No description.

MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols

LLMArena is an open-source platform designed to facilitate AI competitions between large language models.

No description.

No description.

This repository includes the full release of PrinciplismQA dataset and assessment scripts.

Mamo: a Mathematical Modeling Benchmark with Solvers

Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning

Code for the paper: Modular Retrieval for Generalization and Interpretation.

No description.

Codes and dataset for the paper: Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text

LLMs Could Autonomously Learn Without External Supervision. (An Autonomous Learning Method)

No description.

[ICLR 2026] MicroVerse: A Preliminary Exploration Toward a Micro-World Simulation

No description.

GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration

No description.

No description.

From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents

RAG to reduce medical haluccination.

No description.

[EMNLP 2025 Findings] Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization

Paper: Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

No description.

No description.

Embody_AI with car as Demo

Chat data for training LLMs

No description.

An Evaluator Kit for different kinds of evaluation datasets.

Multilingual Medical Model Based On Jamba

Chinese Medical instruction-tuning Dataset

Open benchmark leaderboard for AI accelerators on LLM inference workloads. Run on your GPU, submit your result, get on the board. NVIDIA · AMD · Ascend · Apple Silicon

No description.

医疗AI研究集合

No description.

Datasets and description of Arabic model evaluation task

No description.

No description.

No description.

No description.

No description.

No description.

GPT药剂师考试脚本

No description.

No description.

No description.

Website for CUHK-SZ NLP group (under construction)

No description.

The official code for paper: QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

MedPajama: A Large-scale Trustworthy Medical Corpus

MiniCPM on Android platform.

No description.

CUHKSZAIBot, AI Assistant across all Campus

Phoenix2 code in dev

Medical instruction

Economic World Models Initiative GitHub Pages site

A research prototype for shared token economics and verifiable distributed intelligent work.

Project website for TokenMosaic.

AI4S2 Center for AI for Social Science homepage

No description.

No description.

No description.

No description.

No description.

Website for CUHKSZ NLP group (under construction)

No description.

No description.

No description.

No description.

Minecraft AI Campus for CUHK(SZ)

No description.

预问诊和病例生成评测之后的界面展示

No description.

No description.

No description.

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

No description.

No description.

benchmarking medical LLMs in Chinese

Chinese And Medically Enhanced Langauge models