brutalsavage
Follow
Stars
A LaTex paper template for security and machine learning conferences
Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym
End-to-end Generative Optimization for AI Agents
SymQEMU: Compilation-based symbolic execution for binaries
A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Grandmaster-Level Chess Without Search
Fork of project1-education-pathways-group-10-4sight created by GitHub Classroom
Efficient and general syntactical decoding for Large Language Models
Agentless🐱: an agentless approach to automatically solve software development problems
A web app to view the location of all Guelph Transit buses
Scrollytelling with IntersectionObserver.
RepoQA: Evaluating Long-Context Code Understanding
The most advanced AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
A small library for automatically adjustment of text position in matplotlib plots to minimize overlaps.
KernelGPT: Enhanced Kernel Fuzzing via Large Language Models (ASPLOS 2025)
[ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
[FSE-2024] Towards AI-Assisted Synthesis of Verified Dafny Methods
WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models (OOPSLA 2024)
[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Lightweight tool to identify Data Contamination in LLMs evaluation
Robust recipes to align language models with human and AI preferences