Seongho Son

Cable-Driven Parallel Robot-Based Needle Steering for Imaging-Compatible Interventional Procedures

RSPO: Regularized Self-Play Alignment of Large Language Models

Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. However, the regularization with respect to the reference policy, which is crucial for mitigating over-optimization, has be…

Robust Multi-Objective Controlled Decoding of Large Language Models

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the worst-case rewards. RMOD formulates the robust decoding problem as…

Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift

Current Large Language Model (LLM) preference optimization algorithms do not account for temporal preference drift, which can lead to severe misalignment. To address this limitation, we propose **Non-Stationary Direct Preference Optimisation (NS-DPO)** that models time-dependent reward functions wit…