activity
20242026
collaborators

10 papers

cs.CL2026

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

Yekaterina Yegorova, Argyrios Gerogiannis, Haolong Zheng +3

Speech-aware large language models often generalize poorly to out-of-domain settings. We propose SALSA (Speech-Aware LLM Adaptation via Learned Steering Activations), a lightweight…

cs.LG2026

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

Argyrios Gerogiannis, Yekaterina Yegorova, Mark Hasegawa-Johnson +1

State-of-the-art GRPO-style methods for speech-aware large language model post-training suffer from coarse credit assignment, broadcasting the same terminal-reward advantage to eve…

cs.LG2026

DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees

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

We study model-free reinforcement learning (RL) in non-stationary finite-horizon episodic Markov decision processes (MDPs) without prior knowledge of the non-stationarity. We focus…

cond-mat.dis-nn2026

Context-Gated Associative Retrieval: From Theory to Transformers

Moulik Choraria, Argyrios Gerogiannis, Vidhata Jayaraman +2

Hopfield networks and their generalizations have established deep connections among biological associative memories, statistical physics, and transformers. Yet most models treat re…

cs.AI2026

Know Thy Reasoner: Not All Language Models Explore Alike

Moulik Choraria, Argyrios Gerogiannis, Anirban Das +4

Compute scaling for LLM reasoning trades off exploring solution approaches (\emph{breadth}) against refining promising ones (\emph{depth}), yet why a given trade-off works, and why…

cs.IT2026

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

Yu-Han Huang, Argyrios Gerogiannis, Subhonmesh Bose +1

We study the multichannel quickest change detection problem with bandit feedback and controlled sensing, in which an agent sequentially selects one of the data streams to observe a…