-
Max Planck Institute for Intelligent Systems
- Tübingen, Germany
- https://melisilaydabal.github.io/
- @melisilaydabal
Stars
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Code for visualizing the loss landscape of neural nets
List of references and online resources related to data science, machine learning and deep learning.
Technically-oriented PDF Collection (Papers, Specs, Decks, Manuals, etc)
Code for doubly stochastic gradients
🎓 Sharing machine learning course / lecture notes.
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
Universal and Transferable Attacks on Aligned Language Models
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
A curated list of fellowships for graduate students in Computer Science and related fields.
This repository is related to a project of the Introduction to Numerical Imaging (i.e, Introduction à l'Imagerie Numérique in French), given by the MVA Masters program at ENS-Paris Saclay. It was e…
High-quality datasets, tools, and concepts for LLM fine-tuning.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
Must-read Papers on Textual Adversarial Attack and Defense
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
Library containing PyTorch implementations of various adversarial attacks and resources
A curated (most recent) list of resources for Learning with Noisy Labels
List of papers about Proteins Design using Deep Learning
Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization
Get protein embeddings from protein sequences
EPFL Course - Optimization for Machine Learning - CS-439
Evolutionary Scale Modeling (esm): Pretrained language models for proteins