PhD Candidate, ECE at UIUC

Hi, I'm Argy.

My research focuses on reinforcement learning, post-training and reasoning methods for LLMs and multimodal models, and transformer theory.

I am a PhD candidate in Electrical and Computer Engineering at the University of Illinois Urbana-Champaign, advised by Venugopal V. Veeravalli. Previously, I earned a Diploma (BSc+MSc) in Electrical and Computer Engineering from the University of Patras, where I worked with George Moustakides. My work has appeared across several A* venues, including AISTATS, ICLR, ICML, EMNLP and NeurIPS. As an intern, I worked at Netradyne, where I developed reinforcement learning methods for autonomous driving, and at Uber, where I worked on transfer learning and reinforcement learning for fraud decision-making.

Curriculum Vitae

Papers

Publications and manuscripts

Publications

NeurIPS 2026 Reinforcement Learning

DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees

Argyrios Gerogiannis, Yu-Han Huang, Venugopal V. Veeravalli

Paper

Annual Conference on Neural Information Processing Systems , 2026

ICML 2026 Bandits

DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits

Argyrios Gerogiannis, Yu-Han Huang, Subhonmesh Bose, Venugopal V. Veeravalli

Paper

International Conference on Machine Learning, 2026

EMNLP 2026 Post-training

LEAF: Growing Trees Without Branching for Speech-Aware Large Language Model Post-Training

Argyrios Gerogiannis, Yekaterina Yegorova, Mark Hasegawa-Johnson, Venugopal V. Veeravalli

Paper

Conference on Empirical Methods in Natural Language Processing, 2026

ICLR 2026 Reasoning

Your Model Diversity, Not Method, Determines Reasoning Strategy

M. Choraria, A. Gerogiannis, A. Das, S. Chakraborty, B. Kapusuzoglu, C.-H. Lee, K. Balasubramaniam, S.-X. Zhang, S. Sahu

Paper

ICLR Workshop on Logical Reasoning of Large Language Models, 2026

ICLR 2026 Transformers Oral

Towards Context-Based Retrieval in Associative Memories

Moulik Choraria*, Argyrios Gerogiannis*, Vidhata Jayaraman, Ankur Mani, Lav R. Varshney

* Equal contribution.

Paper

ICLR Workshop on New Frontiers in Associative Memories, 2026

CDC 2026 Bandits Oral

Learning Where to Look: UCB-Driven Controlled Sensing for Quickest Change Detection

Yu-Han Huang, Argyrios Gerogiannis, Subhonmesh Bose, Venugopal V. Veeravalli

Paper

IEEE Conference on Decision and Control, 2026

TIT 2026 Bandits

Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach

Yu-Han Huang, Argyrios Gerogiannis, Subhonmesh Bose, Venugopal V. Veeravalli

Paper

IEEE Transactions on Information Theory, 2026

TSP 2026 Reinforcement Learning

Track-MDP: Reinforcement Learning for Target Tracking with Controlled Sensing (Extended Version)

Adarsh M. Subramaniam, Argyrios Gerogiannis, James Z. Hare, Venugopal V. Veeravalli

Paper

IEEE Transactions on Signal Processing, 2026

AISTATS 2025 Reinforcement Learning

Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?

Argyrios Gerogiannis, Yu-Han Huang, Venugopal V. Veeravalli

Paper

International Conference on Artificial Intelligence and Statistics, 2025

MILCOM 2025 Reinforcement Learning

Track-MDP++: RL for Target Tracking with General Controlled Sensing Models

Adarsh M. Subramaniam, Argyrios Gerogiannis, James Z. Hare, Venugopal V. Veeravalli

Paper

IEEE Military Communications Conference, 2025

ICASSP 2025 Reinforcement Learning

Track-MDP: Reinforcement Learning for Target Tracking with Controlled Sensing

Adarsh M. Subramaniam, Argyrios Gerogiannis, James Z. Hare, Venugopal V. Veeravalli

Paper

International Conference on Acoustics, Speech, and Signal Processing, 2025

Manuscripts Under Review

Under Submission, 2026 Transformers

Context-Gated Associative Retrieval: From Theory to Transformers

Moulik Choraria*, Argyrios Gerogiannis*, Vidhata Jayaraman, Ankur Mani, Lav R. Varshney

* Equal contribution.

Paper

Under Submission, 2026

Under Submission, 2026 Multimodal LLMs

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

Yekaterina Yegorova, Argyrios Gerogiannis, Haolong Zheng, Julia Hockenmaier, Chang D. Yoo, Mark Hasegawa-Johnson

Paper

Under Submission, 2026

Under Submission, 2026 Reasoning

Know Thy Reasoner: Not All Language Models Explore Alike

Moulik Choraria, Argyrios Gerogiannis, Anirban Das, Supriyo Chakraborty, Sourya Basu, Sambit Sahu, Lav R. Varshney

Paper

Under Submission, 2026