10 papers
Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting
Kihyun Kim, Hee-Seon Kim, Wonjun Lee +1
Batch prompting is a practical inference strategy for large language models, but its safety implications remain underexplored. We show that the success of batch prompting for utili…
Enhanced Detection of Tiny Objects in Aerial Images
Kihyun Kim, Michalis Lazarou, Tania Stathaki
While one-stage detectors like YOLOv8 offer fast training speed, they often under-perform on detecting small objects as a trade-off. This becomes even more critical when detecting…
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
Kihyun Kim, Chaeyun Kim, Jongho Shin +4
Learning a good action embedding space is fundamental to scalable robot policy learning, yet existing methods treat action latents as task-specific intermediates rather than first-…
Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach
Kihyun Kim, Shripad Deshmukh, Nikos Vlassis +1
Inverse reinforcement learning (IRL) typically assumes demonstrations from a single optimal demonstrator, but in many applications data come from multiple imperfect demonstrators w…
STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
MinJae Jung, YongTaek Lim, Chaeyun Kim +3
While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. This paper introduces STAR-Team…
Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework
Kihyun Kim, Jiawei Zhang, Asuman Ozdaglar +1
Conventional preference learning methods often prioritize opinions held more widely when aggregating preferences from multiple evaluators. This may result in policies that are bias…