Scholar
Ofer Meshi
Google Scholar ID: KMBgMs0AAAAJ
Research Scientist at Google
Citations & Impact
Citations
348
H-index
9
i10-index
9
Publications
20
Co-authors
9
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Asking Clarifying Questions for Preference Elicitation With Large Language Models (SIGIR, 2025)
- Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval (NeurIPS, 2024)
- Model-Free Preference Elicitation (IJCAI, 2024)
- Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies (SIGIR, 2024)
- Preference Elicitation for Music Recommendations (ICML Workshop on Preference Learning, 2023)
- Overcoming Prior Misspecification in Online Learning to Rank (AISTATS, 2023)
- On the Value of Prior in Online Learning to Rank (AISTATS, 2022)
- Advantage Amplification in Slowly Evolving Latent-State Environments (IJCAI, 2019)
- Train and Test Tightness of LP Relaxations in Structured Prediction (JMLR, 2019)
- MAP Estimation: Linear Programming Relaxation and Message-Passing Algorithms (Handbook of Graphical Models, 2018)
- Seq2Slate: Re-ranking and Slate Optimization with RNNs (ArXiv Preprint, 2018)
- Deep Structured Prediction via Nonlinear Output Transforms (NeurIPS, 2018)
- Planning and Learning with Stochastic Action Sets (IJCAI, 2018)
- Asynchronous Parallel Coordinate Minimization for MAP Inference (NIPS, 2017)
- Logistic Markov Decision Processes (IJCAI, 2018)
Research Experience
- Currently a Research Scientist at Google. Previously, a Research Assistant Professor at the Toyota Technological Institute at Chicago.
Education
- Ph.D. and M.Sc. in Computer Science from the Hebrew University of Jerusalem, under the supervision of Amir Globerson and Nir Friedman; B.Sc. in Computer Science from Tel Aviv University.
Background
- Research interests include machine learning and optimization, particularly in recommendation systems, preference elicitation, reinforcement learning, and related problems.
