Skip to content

@uiuc-kang-lab uiuc-kang-lab

Change the repository type filter

All

    Repositories list

    41 repositories

    • BIRD-Platinum

      Public
      Python
      •0•0•0•0•Updated Jan 25, 2026Jan 25, 2026

    • text_to_sql_benchmarks

      Public
      Python
      •0•4•1•0•Updated Jan 19, 2026Jan 19, 2026

    • cve-bench

      Public
      CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities
      benchmarklanguage-modelinspect
      Python
      •
      Apache License 2.0
      •29•142•0•1•Updated Jan 14, 2026Jan 14, 2026

    • PilotDB

      Public
      Online AQP with A Priori Error Guarantees
      Python
      •1•5•0•0•Updated Jan 12, 2026Jan 12, 2026

    • SkyRL

      Public
      SkyRL: A Modular Full-stack RL Library for LLMs
      Python
      •
      Apache License 2.0
      •240•1•0•0•Updated Dec 7, 2025Dec 7, 2025

    • drama

      Public
      [SIGMOD'2026] DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries
      Python
      •0•11•1•0•Updated Dec 6, 2025Dec 6, 2025

    • ELT-Bench

      Public
      Python
      •6•23•3•0•Updated Dec 5, 2025Dec 5, 2025

    • jan-0.4.12

      Public
      TypeScript
      •
      GNU Affero General Public License v3.0
      •0•0•0•0•Updated Nov 30, 2025Nov 30, 2025

    • tinker-cookbook

      Public
      Post-training with Tinker
      Python
      •
      Apache License 2.0
      •308•1•0•0•Updated Nov 29, 2025Nov 29, 2025

    • inspect_evals

      Public
      Collection of evals for Inspect AI
      C++
      •
      MIT License
      •237•0•0•0•Updated Nov 17, 2025Nov 17, 2025

    • SWE-bench

      Public
      SWE-bench: Can Language Models Resolve Real-world Github Issues?
      Python
      •
      MIT License
      •745•0•0•0•Updated Nov 14, 2025Nov 14, 2025

    • zk-torch

      Public
      Rust
      •
      Apache License 2.0
      •8•36•3•1•Updated Nov 7, 2025Nov 7, 2025

    • BEAT

      Public
      Python
      •1•4•1•0•Updated Nov 3, 2025Nov 3, 2025

    • REPRO-Bench

      Public
      Python
      •2•6•0•0•Updated Nov 3, 2025Nov 3, 2025

    • leap

      Public
      [VLDB'2025] LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data
      Python
      •0•19•0•0•Updated Nov 3, 2025Nov 3, 2025

    • genie-4.3.0

      Public
      Java
      •
      Apache License 2.0
      •0•0•0•0•Updated Aug 27, 2025Aug 27, 2025

    • lollms-webui-5f93989

      Public
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated Aug 24, 2025Aug 24, 2025

    • agentic-benchmarks

      Public
      Cuda
      •6•49•0•0•Updated Jul 31, 2025Jul 31, 2025

    • llm-annotations

      Public
      Jupyter Notebook
      •0•0•0•0•Updated Jul 20, 2025Jul 20, 2025

    • UTBoost

      Public
      Python
      •
      MIT License
      •0•0•0•0•Updated Jul 14, 2025Jul 14, 2025

    • tau-bench

      Public
      Code and Data for Tau-Bench
      Python
      •
      MIT License
      •180•0•0•0•Updated Jun 12, 2025Jun 12, 2025

    • rllm

      Public
      Democratizing Reinforcement Learning for LLMs
      Python
      •
      MIT License
      •492•0•0•0•Updated May 10, 2025May 10, 2025

    • aider

      Public
      aider is AI pair programming in your terminal
      Python
      •
      Apache License 2.0
      •3.9k•0•0•0•Updated May 6, 2025May 6, 2025

    • verl-pipeline

      Public
      Async pipelined version of Verl
      Python
      •
      Apache License 2.0
      •13•0•0•0•Updated Apr 28, 2025Apr 28, 2025

    • AutoGPT

      Public
      AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
      Python
      •
      Other
      •46k•0•0•0•Updated Apr 23, 2025Apr 23, 2025

    • crosscoder-model-diff-replication

      Public
      Open source replication of Anthropic's Crosscoders for Model Diffing
      Jupyter Notebook
      •25•0•0•0•Updated Apr 21, 2025Apr 21, 2025

    • SWELancer-Benchmark

      Public
      This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"
      Python
      •
      MIT License
      •140•0•0•0•Updated Apr 10, 2025Apr 10, 2025

    • legalbench

      Public
      An open science effort to benchmark legal reasoning in foundation models
      Python
      •81•0•0•0•Updated Apr 5, 2025Apr 5, 2025

    • SkyThought

      Public
      Sky-T1: Train your own O1 preview model within $450
      Python
      •
      Apache License 2.0
      •345•0•0•0•Updated Apr 3, 2025Apr 3, 2025

    • lex-glue

      Public
      LexGLUE: A Benchmark Dataset for Legal Language Understanding in English
      Python
      •43•0•0•0•Updated Apr 3, 2025Apr 3, 2025