[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

Hierarchical Reasoning Model Official Release

Enhancing Reasoning Skills in Small Persian Medical Language Models Can Outperform Large-Scale Data Training

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

Unlike vanilla contextual pre-trained fundamentally \textit{small} language models (e.g., ClinicalBERT), our interest lies in compressed and optimized approaches for language models in healthcare, …

Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model

Train transformer language models with reinforcement learning.

We present a comprehensive and deep review of the HFM in challenges, opportunities, and future directions. The released paper: https://arxiv.org/abs/2404.03264

Deep reinforcement learning (PPO) apply in FrozenLakev1

Implementations of Coursera Reinforcement Learning Specialization

MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

Summarize existing representative LLMs text datasets.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Towards Medical Small Language Models with Self-Evolved \\ Slow Thinking

Code for the MedRAG toolkit

Official repository of the MIRAGE benchmark

A comprehensive suite of high-level NLP tasks for Persian language

PLPR utilizes YOLOv5 and custom models for high-accuracy Persian license plate recognition, featuring real-time processing and an intuitive interface in an open-source framework.

نمونه قالب برای تز کارشناسی ارشد دانشگاه صنعتی شریف با استفاده از لاتک

Code for paper "G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment"

A free and open source online judge system for programming courses

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

A "حکم" game which is written in html, css, & javascript using react, mui, & zustand libraries. ♦♥♣♠🃏

The official Python library for the OpenAI API

Graph theory approach for Modeling Electrical Circuits

using kmeans to segment

Implementing Mean Shift Image Segmentation in Python