Stars
Recent symbolic execution papers and tools.
High accuracy RAG for answering questions from scientific documents with citations
SoufflΓ© is a variant of Datalog for tool designers crafting analyses in Horn clauses. SoufflΓ© synthesizes a native parallel C++ program from a logic specification.
A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.
A collection of TLAβΊ specifications of varying complexities
ποΈ + π¬ + π§ = π€ Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]
π° Must-read papers and blogs on LLM based Long Context Modeling π₯
An overview of LLMs for cybersecurity.
Lean 4 programming language and theorem prover
[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, Bβ¦
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.
[LLVM Static Slicer] Various program analyses, construction of dependence graphs and program slicing of LLVM bitcode.
Static Value-Flow Analysis Framework for Source Code
An open-source visual programming environment for battle-testing prompts to LLMs.
pauls658 / joern
Forked from octopus-platform/joernA robust parser for C/C++ storing abstract syntax trees, control flow graphs and program dependence graphs in a neo4j graph database.
cclyzer++ is a precise and scalable pointer analysis for LLVM code.
The artifacts contain all reported alarms from evaluated detectors, analysis results of labeled alarms, and refined CryptoGuard as well as false positive examples.
Research Acceleration Platform that provides interface to multiple state-of-the-art program analysis tools including but not limited to fuzzing, static analysis and program repair.
This is a tutorial on how to write an LLVM Pass using the (kind-of) new PassManager. It is compiled from different sources referenced in the tutorial.
Speed up your OpenAI requests by balancing prompts to multiple API keys.
Set of tools to assess and improve LLM security.