87 citations · 177 across the 13 of their papers we have counts for
13 papers
When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models
Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho +4
Expert pruning reduces the memory and serving cost of Mixture-of-Experts (MoE) models by removing low-importance experts identified by the router, assuming router probabilities pro…
Process Optimization Under Uncertainty for Improving the Bond Quality of Polymer Filaments in Fused Filament Fabrication
Berkcan Kapusuzoglu, Matthew Sato, Sankaran Mahadevan +1
This paper develops a computational framework to optimize the process parameters such that the bond quality between extruded polymer filaments is maximized in fused filament fabric…
Multi-Level Bayesian Calibration of a Multi-Component Dynamic System Model
Berkcan Kapusuzoglu, Sankaran Mahadevan, Shunsaku Matsumoto +2
This paper proposes a multi-level Bayesian calibration approach that fuses information from heterogeneous sources and accounts for uncertainties in modeling and measurements for ti…
Multi-Objective Optimization Under Uncertainty of Part Quality in Fused Filament Fabrication
Berkcan Kapusuzoglu, Paromita Nath, Matthew Sato +2
This work presents a data-driven methodology for multi-objective optimization under uncertainty of process parameters in the fused filament fabrication (FFF) process. The proposed…
Adaptive surrogate modeling for high-dimensional spatio-temporal output
Berkcan Kapusuzoglu, Shunsaku Matsumoto, Yoshitomo Miyagi +2
This paper develops an adaptive surrogate modeling method for problems with very high-dimensional spatio-temporal outputs. The analysis of spatio-temporal multi-physics systems is…
Information fusion and machine learning for sensitivity analysis using physics knowledge and experimental data
Berkcan Kapusuzoglu, Sankaran Mahadevan
When computational models (either physics-based or data-driven) are used for the sensitivity analysis of engineering systems, the sensitivity estimate is affected by the accuracy a…
Physics-Informed and Hybrid Machine Learning in Additive Manufacturing: Application to Fused Filament Fabrication
Berkcan Kapusuzoglu, Sankaran Mahadevan
This article investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven deep-learning models for pr…
Structured Thoughts For Improved Reasoning And Context Pruning
Zain Sarwar, Supriyo Chakraborty, Berkcan Kapusuzoglu +5
Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient. In this work, we introduce Structured T…
On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse
Amritansh Mishra, Supriyo Chakraborty, Berkcan Kapusuzoglu
Group Relative Policy Optimization (GRPO) eliminates the learned critic in PPO by using the mean reward of grouped rollouts as a baseline. We provide a rigorous derivation of GRPO…
CoT-Guard: Small Models for Strong Monitoring
Nirav Diwan, Han Wang, Berkcan Kapusuzoglu +6
Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code generation tasks. While large m…
SPEAR-MM: Selective Parameter Evaluation and Restoration via Model Merging for Efficient Financial LLM Adaptation
Berkcan Kapusuzoglu, Supriyo Chakraborty, Renkun Ni +2
Large language models (LLMs) adapted to financial domains often suffer from catastrophic forgetting of general reasoning capabilities essential for customer interactions and comple…
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
Bo Zhao, Berkcan Kapusuzoglu, Kartik Balasubramaniam +3
Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each proble…
Critique-Guided Distillation for Robust Reasoning via Refinement
Berkcan Kapusuzoglu, Supriyo Chakraborty, Zain Sarwar +2
Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed for robust generalization. While c…