Check out our new paper “Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet” at #ICCV2023. Poster: Today 14:30-16:30, Room ’Nord’, ID 024 Code/data: github.com/YanNeu/spuriou… Paper: arxiv.org/abs/2212.04871

🚨 I'm looking for a postdoc position to start in Fall 2024! My most recent research interests are related to understanding foundation models (especially LLMs!), making them more reliable, and developing principled methods for deep learning. More info: andriushchenko.me

Join us 2mrw @⚡️XAI-in-Action : Past, Present & Future Applications⚡️ workshop NeurIPS Conference for an exciting discussion on how far we've come, the current state & future of XAI ! Bonus: Live Demos! Submit ur ❤️‍🔥 panel questions: app.sli.do/event/6e2A95V2… 🔗xai-in-action.github.io

In our new paper (oral datacomp.ai, ICCV23), we develop a concept-specific pruning criterion (Density-Based-Pruning) which reduces the training cost by 72%. Joint work with Amro Kushal Tirumala Wieland Brendel Kamalika Chaudhuri Ari Morcos (1/5) arxiv.org/abs/2401.04578

Today we release the FLUX.1 suite of models that push the frontiers of text-to-image synthesis.  read more at blackforestlabs.ai/announcing-bla…

⚠️Standard jailbreak attacks overfocus on info that can anyway be easily found online. However, LLM agents can cause much more harm in the near future. 🚨Today we are announcing AgentHarm. It's like HarmBench/JailbreakBench but for agents. It's good :-) arxiv.org/abs/2410.09024

As jailbreaking attacks🤖on SOTA #LLMs (arxiv.org/abs/2404.02151), LLM agents (arxiv.org/abs/2410.09024), and even robots (arxiv.org/abs/2410.13691) become more critical, our paper @ #NeurIPS2024 Red Teaming GenAI workshop proposes a unified threat model🛡️to compare these attacks!

Have you ever wondered whether a few times of data contamination really lead to benchmark overfitting?🤔 Then our latest paper about the effect of data contamination on LLM evals might be for you!🚀 "How Much Can We Forget about Data Contamination?" (accepted at #ICML2025) shows

🚀Thrilled to share my ICML 2025 line-up! Conference paper: “An Interpretable N-gram Perplexity Threat Model for LLM Jailbreaks” (Thu 17 Jul, 11:00–13:30 PDT, East Exhibition Hall A-B) - we propose a fluency-FLOPs threat model with adaptation of popular attacks to it. We can use

🎓 Looking for MSc or PhD opportunities in Machine Learning for Fall 2026? Join my group at Concordia University and Mila - Institut québécois d'IA! 🔍 Focus: autodiff, second-order optimization, and Hessian-based methods for LLMs & scientific ML. 📅 Apply by Dec 1: mila.quebec/en/prospective…