10 papers
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…
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…
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…
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…
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…
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…
DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits
Argyrios Gerogiannis, Yu-Han Huang, Subhonmesh Bose +1
We introduce a practical, black-box framework termed Detection Augmented Learning (DAL) for the problem of piecewise stationary bandits without knowledge of the underlying non-stat…
Detection Augmented Bandit Procedures for Piecewise Stationary MABs: A Modular Approach
Yu-Han Huang, Argyrios Gerogiannis, Subhonmesh Bose +1
Conventional Multi-Armed Bandit (MAB) algorithms are designed for stationary environments, where the reward distributions associated with the arms do not change with time. In many…
Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?
Argyrios Gerogiannis, Yu-Han Huang, Venugopal V. Veeravalli
We study the problem of Non-Stationary Reinforcement Learning (NS-RL) without prior knowledge about the system's non-stationarity. A state-of-the-art, black-box algorithm, known as…
Track-MDP: Reinforcement Learning for Target Tracking with Controlled Sensing
Adarsh M. Subramaniam, Argyrios Gerogiannis, James Z. Hare +1
State of the art methods for target tracking with sensor management (or controlled sensing) are model-based and are obtained through solutions to Partially Observable Markov Decisi…