Itai Shapira

I'm a CS PhD student at Harvard University. I am privileged to be advised by Prof. Ariel D. Procaccia.
I am a recipient of the 2025 JPMorgan Chase PhD Fellowship, and I was also supported by the Nicole A. Chen and Karina A. Chen Graduate Student Research Fellowship. I am affiliated with the NSF AI Institute for Societal Decision Making and serve on its Student Leadership Council. Before my PhD I worked as a senior quantitative researcher at WorldQuant (Millennium) and interned in 2025 as a quant at Two Sigma on online learning optimization.

Update I’ll be at ICLR 2026 in Rio de Janeiro in April. If you’re attending, feel free to reach out.

Research

Notation: (α) authors listed alphabetically (r) equal contribution with randomized order among authors marked with †

How RLHF Amplifies Sycophancy 2026

Itai Shapira, Gerdus Benadè, Ariel D. Procaccia

Under submission for ICML 2026

Robust AI Evaluation through Maximal Lotteries 2026

(r) Hadi Khalaf, Serena Lutong Wang, Daniel Halpern, Itai Shapira, Flavio P. Calmon, Ariel D. Procaccia

Under submission for ICML 2026

Incentives in Federated Learning with Heterogeneous Agents 2026

(α) Ariel D. Procaccia, Han Shao, Itai Shapira

ICLR 2026

Pairwise Calibrated Rewards for Pluralistic Alignment 2025

(α) Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira

NeurIPS 2025

SOAP: Improving and Stabilizing Shampoo using Adam 2025

Nikhil Vyas, Depen Morwani, Rosie Zhao, Itai Shapira, David Brandfonbrener, Lucas Janson, Sham Kakade

ICLR 2025

A New Perspective on Shampoo’s Preconditioner 2025

(r) Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham M. Kakade, Lucas Janson

ICLR 2025

Axioms for AI Alignment from Human Feedback 2024

(α) Luise Ge, Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira, Yevgeniy Vorobeychik, Junlin Wu

NeurIPS 2024 (Spotlight - 2.1% of submissions)

Learning Social Welfare Functions 2024

(r) Kanad Shrikar Pardeshi, Itai Shapira, Ariel D. Procaccia, Aarti Singh

NeurIPS 2024 (Spotlight - 2.1% of submissions)

Bias Detection Via Signaling 2024

(α) Yiling Chen, Tao Lin, Ariel D. Procaccia, Aaditya Ramdas, Itai Shapira

NeurIPS 2024

Generative Social Choice 2024

(α) Sara Fish, Paul Gölz, David C. Parkes, Ariel D. Procaccia, Gili Rusak, Itai Shapira, Manuel Wüthrich

EC 2024 • Accepted to Journal of the ACM (JACM), Jan 2026.

Optimal Engagement-Diversity Tradeoffs in Social Media 2024

(α) Fabian Baumann, Daniel Halpern, Ariel D. Procaccia, Iyad Rahwan, Itai Shapira, Manuel Wüthrich

2024 ACM Web Conference

Expressivity of Shallow and Deep Neural Networks for Polynomial Approximation 2023

Itai Shapira

2023

Market Power and Strategic Drops: An Approach to Stable Matching Mechanisms 2023

Itai Shapira

2023