Se-Young Yun

Instance-Optimal Estimation with Multiple LLM Judges on a Budget
Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges …
Junghyun Lee, Sanghwa Kim, Yassir Jedra, Alexandre Proutière, Se-Young Yun
PDF Cite
Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits
We revisit regularized regret minimization under full-information and bandit feedback, where a learner optimizes an objective of the …
Junghyun Lee, Yujun Kim, Chulhee Yun, Se-Young Yun
Cite
GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
We present GL-LowPopArt, a novel Catoni-style estimator for generalized low-rank trace regression. Building on LowPopArt (Jang et al., …
Junghyun Lee, Kyoungseok Jang, Kwang-Sung Jun, Milan Vojnović, Se-Young Yun
PDF Cite
GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
Near-Optimal Clustering in Mixture of Markov Chains
We study the problem of clustering T trajectories of length H, each generated by one of K unknown ergodic Markov chains over a finite …
Junghyun Lee, Yassir Jedra, Alexandre Proutière, Se-Young Yun
PDF Cite
Near-Optimal Clustering in Mixture of Markov Chains
Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences
We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit …
Junghyun Lee, Minju Hong, Kwang-Sung Jun, Chulhee Yun, Se-Young Yun
PDF Cite
A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions
We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes various …
Sanghwa Kim, Junghyun Lee, Se-Young Yun
PDF Cite
A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions
AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline …
Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee, Hyeongjin Kim, Ah Yeon Kim, Joonkee Kim, Junghyun Lee, Taehyeon Kim, Se-Young Yun
PDF Cite Code
AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
Probability-Flow ODE in Infinite-Dimensional Function Spaces
Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation …
Kunwoo Na, Junghyun Lee, Se-Young Yun, Sungbin Lim
PDF Cite
Probability-Flow ODE in Infinite-Dimensional Function Spaces
FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL
Multi-agent reinforcement learning has demonstrated significant potential in addressing complex cooperative tasks across various …
Woosung Koh, Wonbeen Oh, Siyeol Kim, Suhin Shin, Hyeongjin Kim, Jaein Jang, Junghyun Lee, Se-Young Yun
PDF Cite Project
FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is …
Junghyun Lee, Se-Young Yun, Kwang-Sung Jun
PDF Cite Code Poster Slides
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits