Deep Learning and Optimization Seminar
Deep Learning and Optimization Seminar
JailbreakBench: LLM robustness benchmark
Description: I'm a PhD student in computer science at EPFL advised by Nicolas Flammarion. I'm interested in understanding why machine learning works and why it fails.
jekyll (1205) portfolio-website (945) academic-website (688) jekyll-theme (627)
Enjoying the gorgeous 🇨🇠peaks! This one is Rochers de Naye . [ email ] [ twitter ] [ google scholar ] [ github ] [ cv ]
Short bio. I’m a fourth-year PhD student in computer science at EPFL 🇨🇠advised by Nicolas Flammarion . My research is supported by the Google and Open Phil AI PhD Fellowships. I did my MSc at Saarland University and the University of Tübingen, and interned at Adobe Research.
Research interests. My primary research goal is to understand generalization in deep learning . Towards this goal, I’ve worked on adversarial robustness, out-of-distribution generalization, implicit regularization, and sharpness-aware minimization. These days, I’m looking more into optimization and generalization properties of language models. My full publication list is available here .
Deep Learning and Optimization Seminar
Deep Learning and Optimization Seminar
JailbreakBench: LLM robustness benchmark