Masud Rahman

Predicting Usefulness of Code Review Comments using Textual Features and Developer Experience

Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

This repository hosts all of my public files

Introduction to Machine Learning Systems

Helpful tools and examples for working with flex-attention

Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory

Awesome-papers is a collection of awesome papers about cloud computing including resource management, serverless, microservice, observerbility and so on.

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

Recommending Insightful Comments for Source Code using Crowdsourced Knowledge

No description provided.

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Fit interpretable models. Explain blackbox machine learning.

RACK: Code Search in the IDE using Crowdsourced Knowledge

NLP2API: Query Reformulation for Code Search using Crowdsourced Knowledge and Extra-Large Data Analytics.

Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI

Improving IR-Based Bug Localization with Context-Aware Query Reformulation

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

Predicting Usefulness of Code Review Comments using Textual Features and Developer Experience

CORRECT: Code Reviewer Recommendation Based on Cross-Project & Technology Experience

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

An open information extraction system that provides compact extractions

Empirical Software Engineering

Tool version of NLP2API technique

Replication package of RACK : Automated Query Reformulation for Code Search using Crowdsourced Knowledge

PageRank implementation in Java

The source code for the paper - Search Keyword Identification for Concept Location using Graph-Based Term Weighting

The replication package for EMSE 2019 submission