6 papers
Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide
Taejong Joo, Diego Klabjan
Process reward models (PRMs) provide dense step-level guidance for search-based reasoning, enabling inference-time compute to be allocated toward promising partial solutions. Howev…
On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
Taejong Joo, Wenhan Xia, Cheolmin Kim +2
Training large language models (LLMs) relies almost exclusively on dense adaptive optimizers with increasingly sophisticated preconditioners. We challenge this by showing that rand…
Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration
Taejong Joo, Shu Ishida, Ivan Sosnovik +4
As a model-agnostic approach to long context modeling, multi-agent systems can process inputs longer than a large language model's context window without retraining or architectura…
Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
Taejong Joo, Diego Klabjan
Transformers have demonstrated remarkable in-context learning (ICL) capabilities, adapting to new tasks by simply conditioning on demonstrations without parameter updates. Compelli…
Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
Taejong Joo, Diego Klabjan
Self-training often falls short under distribution shifts due to an increased discrepancy between prediction confidence and actual accuracy. This typically necessitates computation…
IW-GAE: Importance Weighted Group Accuracy Estimation for Improved Calibration and Model Selection in Unsupervised Domain Adaptation
Taejong Joo, Diego Klabjan
Distribution shifts pose significant challenges for model calibration and model selection tasks in the unsupervised domain adaptation problem -- a scenario where the goal is to per…