Edo Cohen-Karlik
I’m an AI researcher and builder. Over the past several years, I’ve worked on some of the problems I find most fascinating - teaching machines to argue (IBM’s Project Debater), generating novel drug candidates (Google Research), and now shaping AI strategy as VP of AI at a stealth startup. I’m driven by the belief that the most impactful AI work happens where rigorous research meets real-world products.
Teaching
- Workshop in Machine Learning 2019-2023
- Foundations of Deep Learning 2020
- Introduction to Machine Learning 2017-2018
Publications
On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach
E. Cohen-Karlik, I. Zimerman, L. Galanti, I. Atad, A. Globerson, L. Wolf
International Conference on Artificial Intelligence and Statistics (AISTATS) 2026
Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
N. Razin, Y. Alexander , E. Cohen-Karlik, R. Giryes, A. Globerson, N. Cohen
International Conference on Machine Learning (ICML) 2025
Provable Benefits of Complex Parameterizations for Structured State Space Models
Y. Ran-Milo, E. Lumbroso , E. Cohen-Karlik, R. Giryes, A. Globerson, N. Cohen
Advanced in Neural Information Processing Systems (NeurIPS) 2024
Order Agnostic Autoregressive Graph Generation
E. Cohen-Karlik, E. Rozenberg, D. Freedman
Transactions on Machine Learning Research (TMLR) 2024
Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets
E. Cohen-Karlik, I. Menuhin-Gruman, R. Giryes, N. Cohen, A. Globerson
International Conference on Learning Representations (ICLR) 2023
On the Implicit Bias of Gradient Descent for Temporal Extrapolation
E. Cohen-Karlik, A. Ben David, N. Cohen, A. Globerson
International Conference on Artificial Intelligence and Statistics (AISTATS) 2022
An autonomous debating system
N. Slonim, Y. Bilu, C. Alzate, R. Bar-Haim, B. Bogin, F. Bonin, L. Choshen, E. Cohen-Karlik, L. Dankin, L. Edelstein, L. Ein-Dor, R. Friedman-Melamed, A. Gavron, A. Gera, M. Gleize, S. Gretz, D. Gutfreund, A. Halfon, D. Hershcovich, R. Hoory, Y. Hou, S. Hummel, M. Jacovi, C. Jochim, Y. Kantor, Y. Katz, D. Konopnicki, Z. Kons, L. Kotlerman, D. Krieger, D. Lahav, T. Lavee, R. Levy, N. Liberman, Y. Mass, A. Menczel, S. Mirkin, G. Moshkowich, S. Ofek-Koifman, M. Orbach, E. Rabinovich, R. Rinott, S. Shechtman, D. Sheinwald, E. Shnarich, I. Shnayderman, A. Soffer, A. Spector, B. Sznajder, A. Toledo, O. Toledo-Ronen, E. Venezian, R. Aharonov
Nature 2021
Quantification of osteoclasts in culture, powered by machine learning
E. Cohen-Karlik, Z. Awida, A. Bergman, S. Eshed, O. Nestor, M. Kadashev, S. Ben Yosef, H. Saed, Y. Mansour, A. Globerson, D. Neumann, Y. Gabet
Frontiers in Cell and Developmental Biology 2021
Regularizing Towards Permutation Invariance in Recurrent Models
E. Cohen-Karlik, A. Ben David, A. Globerson
Advanced in Neural Information Processing Systems (NeurIPS) 2020
A Large-scale Dataset for Argument Quality Ranking: Construction and Analysis
S. Gretz, R. Friedman, E. Cohen-Karlik, A. Toledo, D. Lahav, R. Aharonov, N. Slonim
Association for the Advancement of Artificial Intelligence (AAAI) 2020
Learning to combine Grammatical Error Corrections
Y. Kantor, Y. Katz, L. Choshen, E. Cohen-Karlik, N. Liberman, A. Toledo, A. Menczel, N. Slonim
Workshop at Association for Computational Linguistics (ACL) 2019
Automatic Argument Quality Assessment–New Datasets and Methods
A. Toledo, S. Gretz, E. Cohen-Karlik, R. Friedman, E. Venezian, D. Lahav, M. Jacovi, R. Aharonov, N. Slonim
Empirical Methods in Natural Language Processing (EMNLP) 2019
Object Oriented Consensus
Y. Afek, J. Aspnes, E. Cohen-Karlik, D. Vainstein
Brief announcement at Principles of Distributed Computing (PODC) 2017