Max Torop

I am a fifth year PhD candidate in Prof. Jennifer Dy’s Machine Learning Lab at Northeastern University. I’m broadly interested in interpretable ML, self-supervised learning and inference time steering of LLMs. I also collaborate with scientists at MSKCC, applying ML to dermatology. I was a research intern at Apple during the summer of 2024, where I worked on methods for selecting SFT/RLHF training data for LLMs.
Before coming to Northeastern I completed a Masters in CS at WUSTL, where I developed deep learning methods for MRI processing as a member of Prof. Ulugbek Kamilov’s Computational Imaging Group. I recieved a BS in Data Science from the University of Rochester in 2018.
Outside of research I love to watch anime and read. Some favorites are One Piece, Fullmetal Alchemist, Dororo, One Hundred Years of Solitude, The Stormlight Archive, Jonathan Strange and Mr. Norrell, East of Eden and Hyperion.
News
Oct 24, 2024 | Gave a talk on our work SmoothHess to Prof. Doshi-Velez’s DtAK lab at Harvard. |
---|---|
Apr 22, 2024 | I’ll be joining Apple as an ML Research Intern this Summer! |
Jan 19, 2024 | Our work Boundary-Aware Uncertainty for Feature Attribution Explainers was accepted to AISTATS 2024! |
Sep 22, 2023 | Our work SmoothHess: ReLU Network Feature Interactions via Stein’s Lemma was accepted to NeurIPS 2023! |
May 13, 2022 | Our work using contrastive learning for spirometry accepted to ATS 2022 as an oral presentation. |