Stars
An open source benchmarking framework for IT automation
Interactive web-based digital logic circuit designer & simulator with AI-powered features.
[ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
Tool to statically recompile N64 games into native executables
Virtual whiteboard for sketching hand-drawn like diagrams
An open-source network stresser tool but it's Hatsune Miku
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Desktop environment in the browser
A free and strong UCI chess engine
Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".
OCR, layout analysis, reading order, table recognition in 90+ languages
(NeurIPS D&B 2024) STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Repoformer: Selective Retrieval for Repository-Level Code Completion (ICML 2024)
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
BilGPT is an advanced chatbot currently powered by the GPT-4 API. It is specifically designed to assist individuals with the Bilkent AI Society. You can try BilGPT right now! 😄
This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.
[ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"
Visualization of MCTS algorithm applied to Tic-tac-toe.
[NAACL 2024] End-to-End Beam Retrieval for Multi-Hop Question Answering