iiinova — where your digital self keeps evolving

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 08/07/2026

✨Excited to share my single author Spotlight paper at ICML 2026!✨ @icmlconf.bsky.social #ICML #ICML26 #ICML2026

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 28/05/2026

✨What should we know about reasoning and generalization capabilities of reinforcement learning? ✨Let’s dive into my new ICLR 2026 paper: #ICLR2026 @iclr-conf.bsky.social How to Lose Inherent Counterfactuality in Reinforcement Learning #ReinforcementLearning #Reasoning #ICLR #AI #LLM #DeepRL

100

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 12/05/2026

✨My single author paper just got accepted as a spotlight presentation at ICML 2026. Truly excited! More news to come! #ICML2026 @icmlconf.bsky.social

010

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 24/04/2026

✨Two single author papers accepted to ICLR 2026 ✨ Excited to share these results at #ICLR2026! @iclr-conf.bsky.social

010

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 25/02/2026

✨Two single author papers accepted to ICLR 2026!✨ Truly excited to present these results at #ICLR2026 ! @iclr-conf.bsky.social #ICLR26 #DeepRL #ICLR #ReinforcementLearning

000

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 27/01/2026

✨Two of my single author papers just got accepted to #ICLR2026 ! Truly excited! More news to come! @iclr-conf.bsky.social

000

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 27/01/2026

If you are interested in reinforcement learning or reinforcement learning training of language models, this might spark your interest! ✨See my new paper on scaling, capacity and complexity of reinforcement learning published at #AAAI2026 ! @aaai.org #AAAI #AAAI26 #ReinforcementLearning #DeepRL

010

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 21/01/2026

✨Excited to present these results at #AAAI2026 ! 📜It is a must read if you are interested in reinforcement learning 📜 @aaai.org Paper: Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms #ReinforcementLearning #AAAI #AAAI26 #DeepRL

030

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 27/11/2025

Excited to present these results at #NeurIPS2025! ✨My new paper on core principles of reinforcement learning was accepted as a Spotlight presentation at @neuripsconf.bsky.social !✨

040

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 06/04/2025

I opened this poll and I will share the results here as well: #ICML #ICML2025

140

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 11/02/2025

If you are interested in large language models see my paper below on how we can uncover the biases learned by these models. Link: neurips2023-enlsp.github.io/papers/paper... #ReinforcementLearning #FoundationModels #DeepRL #DeepReinforcementLearning #ResponsibleAI #AIBias #LLMs #LanguageModels

020

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 02/02/2025

Gave a lecture on Hoeffding's Inequality recently at #LMUMunich! Nice to have a chance to talk about foundations. Find my slides below: Link: ezgikorkmaz.github.io #Statistics #Probability #LMU #MachineLearning

ezgikorkmaz.github.io

Ezgi Korkmaz

030

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 14/01/2025

A recent paper I wrote introduces foundational analysis on deep reinforcement learning decision making and representations learnt by it. Link: proceedings.mlr.press/v235/korkmaz... #ReinforcementLearning #ICLR2025 #ACL2025 #NAACL2025 #NeurIPS2024 #ICML2025 #DeepRL #DeepReinforcementLearning

0142

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 12/01/2025

I wrote a recent survey about deep reinforcement learning. The paper is a compact guide to understand some of the key concepts in reinforcement learning. Link: arxiv.org/pdf/2401.023... #ReinforcementLearning #ICLR2025 #ACL2025 #NAACL2025 #NeurIPS2024 #ICML2025 #DeepRL #DeepReinforcementLearning

1399

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 10/12/2024

The recent paper I wrote on deep reinforcement learning and generalization will appear #NeurIPS2024 @neuripsconf.bsky.social ! #ReinforcementLearning #DeepReinforcementLearning

010

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 07/12/2024

If you are curious about deep reinforcement learning find the compact highlights of my recent papers in this new short piece: #NeurIPS2024 @neuripsconf.bsky.social #NeurIPS24 #reinforcementlearning #AIsafety #AISecurity #ResponsibleAI #TrustworthyAI #RobustAI #DeepRL bsky.app/profile/ezgi...

021

Ezgi Korkmaz @ezgikorkmaz.bsky.social · 05/12/2024

The paper on adversarial non-robustness is now online! This paper highlights what you should now about Robust Reinforcement Learning. Adversarial Robust Deep Reinforcement Learning is Neither Robust Nor Safe Link: openreview.net/pdf?id=EPa0u... #NeurIPS2024 neuripsconf.bsky.social #NeurIPS24

132