Research
Pairwise Calibrated Rewards for Pluralistic Alignment
(α,β) Daniel Halpern, Evi Micha, Ariel D. Procaccia, Itai Shapira
NeurIPS 2025
2025 NSF AI-SDM Workshop on Human-AI Complementarity for Decision Making (Spotlight)
Incentives in Federated Learning with Heterogeneous Agents
(α,β) Ariel D. Procaccia, Han Shao, Itai Shapira
2025. Under submission
SOAP: Improving and Stabilizing Shampoo using Adam
Nikhil Vyas, Depen Morwani, Rosie Zhao, Itai Shapira, David Brandfonbrener, Lucas Janson, Sham Kakade
ICLR 2025
A New Perspective on Shampoo’s Preconditioner
Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham M. Kakade, Lucas Janson
ICLR 2025
Axioms for AI Alignment from Human Feedback
(α,β) 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
Kanad Shrikar Pardeshi, Itai Shapira, Ariel D. Procaccia, Aarti Singh
NeurIPS 2024 (Spotlight - 2.1% of submissions)
Bias Detection Via Signaling
(α,β) Yiling Chen, Tao Lin, Ariel D. Procaccia, Aaditya Ramdas, Itai Shapira
NeurIPS 2024
Generative Social Choice
(α,β) Sara Fish, Paul Gölz, David C. Parkes, Ariel D. Procaccia, Gili Rusak, Itai Shapira, Manuel Wüthrich
[ArXiv] [OpenAI Blog] [Ariel's talk]
EC 2024
Optimal Engagement-Diversity Tradeoffs in Social Media
(α,β) 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
Itai Shapira
2023