Michal Shlapentokh-Rothman

I am a 4th year computer science PhD student at the University of Illinois at Urbana-Champaign. I am co-advised by Professors Derek Hoiem and Yuxiong Wang. Previously, I received my bachelor's and Masters of Engineering degrees in computer science from MIT in 2019 and 2020. At MIT, I was a member of the ALFA Group .

Email / Google Scholar / LinkedIn / CV

News

Nov 2023: Region representations paper released. Combination of DINOv2 and SAM is quite effecitve! Will be presented at CVPR 2024.
May 2023: WebWISE released. Investigates using GPT-3 for web tasks
July 2021: Our Learning Curves paper was presented at ICML.
May 2021: I will be interning at Amazon this summer

Research

My reserach interests are at the intersection of vision and language. I study and develop methods for improving the effectiveness, efficiency and interpretability of foundation models on new and existing multi-modal tasks. During my undergard, I did research on using evolutionary algorithms for cyber security.

	Region Representations Revisited Michal Shlapentokh-Rothman* , Ansel Blume, Yao Xiao, Yuqun Wu, Sethurame TV, Heyi Tao, Jae Yong Lee, Wilfredo Torres, Yu-Xiong Wang, Derek Hoiem CVPR 2024* Region representations used to be popular in the pre-deep learning era. What happens when we create region representations with recently released founation models? We show that our simple method achieves impressive performance on existing tasks such as semantic segmentation as well as new one.
	Language Agent Tree Search Unifies Reasoning, Acting and Planning in Language Models Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, Yu-Xiong Wang In Submission Combines LLM techinques for differnet reasoning and planning benchmarks.
	WebWISE: Web Interface Control and Sequential Exploration with Large Language Models Heyi Tao, Sethuramen TV, Michal Shlapentokh-Rothman, Derek Hoiem In Submission How can we use GPT-3 for web-based tasks? We investigate the performance of GPT-3 on the Mini-WoB dataset uisng Document Object Model (DOM) elements as part of the input.
	Learning Curves for Analysis of Deep Networks Derek Hoiem, Tanmay Gupta, Zhizhong Li, Michal M. Shlapentokh-Rothman ICML 2021 In this work, we use learning curves to investigate the effects of various design choices on neural network performance. We propose a method for estimating learning curves, abstract their parameters into error and data-reliance, and evaluate the effectiveness of different parameterizations.
	Coevolutionary Modeling of Cyber Attack Patterns and Mitigations Using Public Datasets Michal Shlapentokh-Rothman, Jonathan Kelly, Avital Baral, Erik Hemberg, Una-May O’Reilly GECCO 2021 In this work, we use co-evolutionary algorithms to explore the dynamics between cyber attack patterns and potential mitigations.
	Securing the software defined perimeter with evolutionary co-optimizations Michal Shlapentokh-Rothman, Erik Hemberg, Una-May O'Reilly GECCO Workshop on Genetic and Evolutionary Computation in Defense, Security, and Risk Management In this work, we show how we can use a competitive co-evolutionary framework to evaluate different software defined perimeters (SDP).

Teaching

Artificial Intelligence (CS 440): Fall 2020
Computational Photography (CS 445): Spring 2021, Spring 2023

Personal

My Father
My Mother
My Brother
Gauss, the dog (11/21/06-5/31/19)
Markov, the dog
Hilbert, the dog

Website based on template from Jon Barron