Skip to content

@kaustpradalab PRADALab_KAUST

Change the repository type filter

All

    Repositories list

    22 repositories

    • adv-ICL

      Public
      [NeurIPS 2025] Official repository for "Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence"
      Python
      •
      Other
      •1•0•0•0•Updated Feb 19, 2026Feb 19, 2026

    • LLM-sycophancy

      Public
      [AAAI'26 Main🎉] Official code of "When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models"
      transformersai-alignmentmechanistic-interpretability
      Python
      •0•5•0•0•Updated Nov 11, 2025Nov 11, 2025

    • flashdp

      Public
      Python
      •
      Apache License 2.0
      •3•5•0•0•Updated Jul 1, 2025Jul 1, 2025

    • Fraud-R1

      Public
      [ACL 2025 Findings] Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements
      nlpbenchmarkaisafetyethictrustworthy-ai
      Python
      •3•27•1•0•Updated Jun 29, 2025Jun 29, 2025

    • repeat-curse-llm

      Public
      [ACL 2025 Findings] Understanding the Repeat Curse in Large Language Models from a Feature Perspective
      Python
      •2•16•0•0•Updated Jun 13, 2025Jun 13, 2025

    • ECBM

      Public
      Python
      •0•2•1•0•Updated May 27, 2025May 27, 2025

    • zo2

      Public
      ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory
      Python
      •
      Apache License 2.0
      •18•3•0•0•Updated Apr 13, 2025Apr 13, 2025

    • draft

      Public
      Privately Fine-Tuning Extremely Large Language Models with Zeroth-Order Offloading
      Python
      •
      Apache License 2.0
      •18•0•0•0•Updated Mar 10, 2025Mar 10, 2025

    • vanilla-RLAIF-pipeline

      Public
      An implementation of a vanilla RLAIF pipeline, utilizing GPT-2-Large for the summarization task with the TL;DR dataset.
      Python
      •1•1•0•0•Updated Feb 5, 2025Feb 5, 2025

    • LLM-Persona-Steering

      Public
      Official code of "Exploring the Personality Traits of LLMs through Latent Features Steering"
      socialpsychologysafetypersonasocialsciencellmllmpersonality
      Python
      •3•16•0•0•Updated Jan 30, 2025Jan 30, 2025

    • SAE-Factory

      Public
      Training SAEs for your LLM, and visualize it in one place
      Python
      •
      Apache License 2.0
      •0•7•0•0•Updated Nov 4, 2024Nov 4, 2024

    • MLLM_KE

      Public
      MLLM_KE
      0•0•0•0•Updated Sep 9, 2024Sep 9, 2024

    • SEATv2

      Public
      Python
      •1•1•0•0•Updated Sep 1, 2024Sep 1, 2024

    • research-handboook

      Public
      5•83•1•0•Updated Aug 22, 2024Aug 22, 2024

    • core_scheduler

      Public
      CoreScheduler: A High-Performance Scheduler for Large Model Training
      C++
      •
      Apache License 2.0
      •5•2•0•0•Updated Aug 21, 2024Aug 21, 2024

    • LLM-efficient-learning

      Public
      Find the most efficient way for a specific large language model to learn a specific task
      Apache License 2.0
      •1•3•0•0•Updated Aug 19, 2024Aug 19, 2024

    • FViT

      Public
      Jupyter Notebook
      •1•3•1•0•Updated Aug 18, 2024Aug 18, 2024

    • SEAT

      Public
      Python
      •1•3•0•0•Updated Aug 18, 2024Aug 18, 2024

    • FVLC

      Public
      Jupyter Notebook
      •2•5•0•0•Updated Aug 18, 2024Aug 18, 2024

    • Tiny-DeepSpeed

      Public
      Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library
      Python
      •
      Apache License 2.0
      •10•2•0•0•Updated Aug 8, 2024Aug 8, 2024

    • CoT-Dataset

      Public
      Jupyter Notebook
      •1•5•0•0•Updated May 10, 2024May 10, 2024

    • adv-ntk

      Public
      [ICLR 2024] Official repository for "Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach"
      Python
      •
      MIT License
      •1•2•0•0•Updated Feb 4, 2024Feb 4, 2024