Stars
KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs)
🔍 AI search engine - self-host with local or cloud LLMs
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
Code to enable layer-level steering in LLMs using sparse auto encoders
Retrieve author and publication information from Google Scholar in a friendly, Pythonic way without having to worry about CAPTCHAs!
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
Reverse Engineering the Abstraction and Reasoning Corpus
A compiler for the esoteric language Piet, targeting multiple backends.
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
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]
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Your self-hosted, globally interconnected microblogging community
Source code for the X Recommendation Algorithm
Attempt at Neuralink's Compression Challenge
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.
a highly efficient compression algorithm for the n1 implant (neuralink's compression challenge)
Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization
[ICML 2021 Oral] We show pure attention suffers rank collapse, and how different mechanisms combat it.
A framework for few-shot evaluation of language models.