Skip to content

@AI4LIFE-GROUP AI4LIFE-GROUP

Change the repository type filter

All

    Repositories list

    29 repositories

    • sae_robustness

      Public
      Official Codebase for Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders (EACL 2026)
      Python
      •
      MIT License
      •1•3•0•0•Updated Feb 14, 2026Feb 14, 2026

    • med-safety-bench

      Public
      MedSafetyBench: Evaluating and Improving the Medical Safety of LLMs, NeurIPS 2024
      Python
      •
      MIT License
      •5•45•0•0•Updated Dec 4, 2025Dec 4, 2025

    • temporal-saes

      Public
      Codebase for Temporal SAEs paper
      Python
      •
      Apache License 2.0
      •2•12•0•0•Updated Nov 14, 2025Nov 14, 2025

    • SpLiCE

      Public
      Sparse Linear Concept Embeddings
      Python
      •
      Apache License 2.0
      •14•132•3•0•Updated Mar 27, 2025Mar 27, 2025

    • RLHF_Trust

      Public
      Python
      •0•3•1•0•Updated Dec 21, 2024Dec 21, 2024

    • interp_interv

      Public
      Code for "Towards Unifying Interpretability and Control: Evaluation via Intervention"
      Python
      •0•2•0•0•Updated Nov 8, 2024Nov 8, 2024

    • rocerf_code

      Public
      Source code for ROCERF
      Jupyter Notebook
      •
      MIT License
      •0•0•0•0•Updated Sep 2, 2024Sep 2, 2024

    • OpenXAI

      Public
      OpenXAI : Towards a Transparent Evaluation of Model Explanations
      benchmarkleaderboardreproducibility
      benchmarkleaderboardreproducibilityinterpretabilityexplainable-aiexplainability
      JavaScript
      •
      MIT License
      •48•254•7•1•Updated Aug 17, 2024Aug 17, 2024

    • LLM_Explainer

      Public
      Code for paper: Are Large Language Models Post Hoc Explainers?
      interpretabilityxaiexplainability
      interpretabilityxaiexplainabilitylarge-language-modelsllm
      Jupyter Notebook
      •
      MIT License
      •5•34•1•0•Updated Jul 22, 2024Jul 22, 2024

    • average-case-robustness

      Public
      Characterizing Data Point Vulnerability via Average-Case Robustness, UAI 2024
      robustnessadversarial-robustnessrobustness-verification
      robustnessadversarial-robustnessrobustness-verificationrandomized-smoothingmultivariate-normal-distribution
      Python
      •
      MIT License
      •0•0•0•0•Updated May 7, 2024May 7, 2024

    • disagreement-problem

      Public
      The Disagreement Problem in Explainable ML, TMLR 2025
      Jupyter Notebook
      •
      MIT License
      •0•2•0•0•Updated Apr 16, 2024Apr 16, 2024

    • fair-unlearning

      Public
      Fair Machine Unlearning: Data Removal while Mitigating Disparities
      Python
      •
      Apache License 2.0
      •2•3•0•0•Updated Feb 15, 2024Feb 15, 2024

    • DiET

      Public
      Code for "Discriminative Feature Attributions via Distractor Erasure Tuning"
      Python
      •1•2•0•0•Updated Dec 12, 2023Dec 12, 2023

    • amplify

      Public
      Python
      •0•1•0•0•Updated Nov 27, 2023Nov 27, 2023

    • Balanced_Recourse

      Public
      Jupyter Notebook
      •0•0•0•0•Updated Nov 7, 2023Nov 7, 2023

    • lcnn

      Public
      Low Curvature Neural Networks (NeurIPS 2022)
      Python
      •0•0•0•0•Updated Nov 6, 2023Nov 6, 2023

    • ProbabilisticallyRobustRecourse

      Public
      "Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness". M. Pawelczyk, T. Datta, J. v.d Heuvel, G. Kasneci, H. Lakkaraju. In…
      Python
      •
      MIT License
      •0•0•0•0•Updated Oct 19, 2023Oct 19, 2023

    • CounterfactualDistanceAttack

      Public
      "On the Privacy Risks of Algorithmic Recourse". Martin Pawelczyk, Himabindu Lakkaraju* and Seth Neel*. In International Conference on Artificial Intelligence an…
      Jupyter Notebook
      •0•0•0•0•Updated Oct 19, 2023Oct 19, 2023

    • In-Context-Unlearning

      Public
      "In-Context Unlearning: Language Models as Few Shot Unlearners". Martin Pawelczyk, Seth Neel* and Himabindu Lakkaraju*; arXiv preprint: arXiv:2310.07579; 2023.
      Jupyter Notebook
      •0•0•0•0•Updated Oct 19, 2023Oct 19, 2023

    • robust-grads

      Public
      Code for https://arxiv.org/abs/2306.06716
      Python
      •0•1•0•0•Updated Jun 22, 2023Jun 22, 2023

    • UAI22_DataPoisoningAttacksonOff-PolicyPolicyEvaluationMethods_RL

      Public
      DOPE: Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
      Python
      •0•0•0•0•Updated May 9, 2023May 9, 2023

    • GraphXAI

      Public
      GraphXAI: Resource to support the development and evaluation of GNN explainers
      Python
      •
      MIT License
      •37•1•0•0•Updated Mar 18, 2023Mar 18, 2023

    • lfa

      Public
      Local function approximation (LFA) framework, NeurIPS 2022
      function-approximationinterpretabilityexplainable-ai
      function-approximationinterpretabilityexplainable-aiexplainable-mlexplainabilityfaithful-explanation
      Python
      •4•5•0•0•Updated Feb 6, 2023Feb 6, 2023

    • arxiv-latex-cleaner

      Public
      arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
      Python
      •
      Apache License 2.0
      •395•0•0•0•Updated Sep 21, 2022Sep 21, 2022

    • ROAR

      Public
      Jupyter Notebook
      •2•5•0•0•Updated Jan 26, 2022Jan 26, 2022

    • unified_representation

      Public
      Python
      •
      MIT License
      •0•1•0•0•Updated Dec 17, 2021Dec 17, 2021

    • fair_ranking_effectiveness_on_outcomes

      Public
      AIES 2021 Paper: Does Fair Ranking Imporve Minority Outcomes?
      Jupyter Notebook
      •0•1•0•0•Updated Dec 5, 2021Dec 5, 2021

    • rise-against-distribution-shift

      Public
      Code base for robust learning for an intersection of causal and adversarial shifts
      Python
      •0•3•0•0•Updated Nov 25, 2021Nov 25, 2021

    • nifty

      Public
      Code for paper https://arxiv.org/abs/2102.13186
      Python
      •
      MIT License
      •13•1•0•0•Updated Apr 3, 2021Apr 3, 2021
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.