Eric Elmoznino

5 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) ❓ The Questioner

Venues

ICML (3) ICLR (2)

Top co-authors

Guillaume Lajoie (5) Dhanya Sridhar (2) Sarthak Mittal (2) Leo Gagnon (2) Yoshua Bengio (2) Thomas Jiralerspong (1) Tom Marty (1) Tejas Kasetty (1) Moksh Jain (1) Johannes von Oswald (1)

Research topics

Artificial Intelligence (4) Core AI (4) Machine Learning (2) Deep Learning (1) Interdisciplinary (1) Natural Language Processing (1) Reinforcement Learning (1) Architectures (1) Bayesian & Probabilistic (1) Cognitive Science (1) Core Methods (1) Generation (1) Methods (1) Optimization & Theory (1)

Keywords

in-context learning (2) multi-agent reinforcement learning (1) reinforcement learning (1) compositionality (1) policy gradient (1) chain-of-thought reasoning (1) posterior distribution (1) model complexity (1) data compression (1) generalization (1) latent variable (1) social dilemma (1) generative flow network (1) algorithmic information theory (1) iterated prisoner's dilemma (1) large language model (1) cooperative behavior (1) occam's razor (1) amortized bayesian inference (1) learning-aware agent (1)

Papers

Does learning the right latent variables necessarily improve in-context learning? ICML 2025 In-Context Learning and Occam’s Razor ICML 2025 Multi-agent cooperation through learning-aware policy gradients ICLR 2025 Towards a Formal Theory of Representational Compositionality ICML 2025 Amortizing intractable inference in large language models ICLR 2024