Article |https://nick-jhlee.github.io/publication_types/article/ArticleHugoBlox Kit (https://hugoblox.com)en-usMon, 25 May 2026 00:00:00 +0000https://nick-jhlee.github.io/media/icon_hu_eee4a95885829ab2.pngArticlehttps://nick-jhlee.github.io/publication_types/article/Instance-Optimal Estimation with Multiple LLM Judges on a Budgethttps://nick-jhlee.github.io/publications/arxiv26-adaptive-llm-judge/Mon, 25 May 2026 00:00:00 +0000https://nick-jhlee.github.io/publications/arxiv26-adaptive-llm-judge/Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Banditshttps://nick-jhlee.github.io/publications/arxiv26-regularized-regret/Thu, 21 May 2026 00:00:00 +0000https://nick-jhlee.github.io/publications/arxiv26-regularized-regret/Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferenceshttps://nick-jhlee.github.io/publications/arxiv26-bilinear-nash/Sun, 22 Feb 2026 00:00:00 +0000https://nick-jhlee.github.io/publications/arxiv26-bilinear-nash/A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptionshttps://nick-jhlee.github.io/publications/arxiv26-corrupted-glm/Thu, 12 Feb 2026 00:00:00 +0000https://nick-jhlee.github.io/publications/arxiv26-corrupted-glm/Learning to Reason in LLMs by Expectation Maximizationhttps://nick-jhlee.github.io/publications/arxiv25-em-reasoning/Tue, 23 Dec 2025 00:00:00 +0000https://nick-jhlee.github.io/publications/arxiv25-em-reasoning/