Talks Show all talks
(Mar. 2026) NVIDIA GTC 2026 Panel — Charting a Course for the Next Decade of Gaming with AI (Dec. 2025) Department Seminar, Seoul National University — AI for Video Games (July 2025) ICML 2025 Workshop on Tiny-Titans (video) — Towards Principled Design of SLM Agents for Edge Devices (May 2025) Department Seminar, Korea University — Generative AI and AI Agents (Apr. 2025) UCSC ECE Seminar — From LIFT to LLM-Lasso (Mar. 2025) Helmholtz/ELLIS Workshop, Berlin — From LIFT to LLM-Lasso for Predictive Modeling (Mar. 2025) EnCORE Workshop, San Diego (video) — Beyond Decoder-Only Next Token Prediction (Feb. 2025) ECE Grad Seminar, University of Pittsburgh — Beyond Decoder-Only Next Token Prediction (Nov. 2024) Seminars on AI Core and Applications, Seoul National University (Oct. 2024) 2024 SIAM Conference on Mathematics of Data Science — Dual Operating Modes of ICL (Apr. 2024) Johns Hopkins University CIS/MINDS seminar — Theoretical Exploration of Foundation Model Adaptation Methods (Feb. 2024) Foundations of Data Science, UCSD/NSF EnCORE (video) — Theoretical Exploration of Foundation Model Adaptation Methods (Dec. 2023) CSP Seminar, University of Michigan (video) — Towards a Theoretical Understanding of Parameter-Efficient Fine-Tuning (Nov. 2023) Efficient ML workshop, Google Research New York — The Expressive Power of Low-Rank Adaptation (Mar. 2026) NVIDIA GTC 2026 Panel — Charting a Course for the Next Decade of Gaming with AI (Dec. 2025) Department Seminar, Seoul National University — AI for Video Games (July 2025) ICML 2025 Workshop on Tiny-Titans (video) — Towards Principled Design of SLM Agents for Edge Devices (May 2025) Department Seminar, Korea University — Generative AI and AI Agents (Apr. 2025) UCSC ECE Seminar — From LIFT to LLM-Lasso (Mar. 2025) Helmholtz/ELLIS Workshop, Berlin — From LIFT to LLM-Lasso for Predictive Modeling (Mar. 2025) EnCORE Workshop, San Diego (video) — Beyond Decoder-Only Next Token Prediction (Feb. 2025) ECE Grad Seminar, University of Pittsburgh — Beyond Decoder-Only Next Token Prediction (Nov. 2024) Seminars on AI Core and Applications, Seoul National University (Oct. 2024) 2024 SIAM Conference on Mathematics of Data Science — Dual Operating Modes of ICL (Apr. 2024) Johns Hopkins University CIS/MINDS seminar — Theoretical Exploration of Foundation Model Adaptation Methods (Mar. 2024) 58th CISS @ Princeton University — A Probabilistic Framework for Understanding In-Context Task Learning and Retrieval (Feb. 2024) 2024 Information Theory and Applications Workshop — The Expressive Power of Low-Rank Adaptation (LoRA) (Feb. 2024) Foundations of Data Science, UCSD/NSF EnCORE (video) — Theoretical Exploration of Foundation Model Adaptation Methods (Dec. 2023) CSP Seminar, University of Michigan (video) — Towards a Theoretical Understanding of Parameter-Efficient Fine-Tuning (Nov. 2023) Efficient ML workshop, Google Research New York — The Expressive Power of Low-Rank Adaptation (June 2021) KRAFTON — Recent Trends of AI Research (June 2021) POSTECH — Information Theory and Coding for Trustworthy and Scalable Machine Learning (May 2021) “Shannon meets Turing” Colloquium, Seoul National University — Information Theory and Coding for Trustworthy and Scalable Machine Learning (Apr. 2021) IFDS Ethics & Algorithms SIG, UC Santa Cruz — Fairness in AI (Mar. 2021) Furiosa.ai — Recent Trends of AI Research (Feb. 2021) Korea Information and Communications Society — Fairness in AI (Dec. 2020) Machine Learning Ideas, Microsoft Research New England — Fairness in AI (Nov. 2020) SILO Seminar, UW-Madison — Fairness in AI (Nov. 2020) BLISS Seminar, UC Berkeley — Fairness in AI (Oct. 2020) The 11th International Conference on ICT Convergence — Information Theory and Coding for Trustworthy and Scalable Machine Learning (May 2020) Air Force Research Laboratory — FR-Train: A mutual information-based approach to fair and robust training (Feb. 2020) The Chaos and Complex Systems Seminar, UW-Madison — Information Theory and Coding for Machine Learning at Scale (Jan. 2020) SK T-Brain — Information Theory and Coding for Machine Learning at Scale (Jan. 2020) Furiosa.ai — Information Theory and Coding for Machine Learning at Scale (Oct. 2019) SILO Seminar, UW-Madison — Binary Rating Estimation with Graph Side Information (Aug. 2019) Samsung Electronics — Learning with Simulated Data (May 2019) The 29th Joint Conference on Communications and Information, Korea — Binary Rating Estimation with Graph Side Information (Apr. 2019) Korea Information and Communications Society — Learning with Simulated Data (Mar. 2019) ECE, UW-Madison — Information Theory and Coding for Machine Learning at Scale (Jan. 2019) Korea Information and Communications Society — Machine Learning (Introduction and Advanced Topics) (May 2018) Kakao Brain — Binary Rating Estimation with Graph Side Information (Jan. 2018) National Information Society Agency, Daegu — Speeding Up Distributed Machine Learning Using Codes (Jan. 2018) DGIST, Daegu — Speeding Up Distributed Machine Learning Using Codes (Dec. 2017) Seoul National University — Speeding Up Distributed Machine Learning Using Codes (Nov. 2017) UC Berkeley BASiCS Seminar — Binary Rating Estimation with Graph Side Information (May 2017) Naver — Speeding Up Distributed Machine Learning Using Codes (May 2017) Information Theory and Machine Learning Workshop, KAIST — Speeding Up Distributed Machine Learning Using Codes (Nov. 2016) National Information Society Agency, Daegu — Machine Learning (Introduction and Advanced Topics) (June 2016) Samsung Electronics DMC R&D Center — Speeding Up Distributed Machine Learning Using Codes (Feb. 2016) Information Theory and Applications Workshop — Speeding Up Distributed Machine Learning Using Codes (Jan. 2016) Seoul National University — Sub-linear Time Algorithms for Sparse Signal Recovery Based on Sparse-graph Codes (May 2015) IEEE Communication Theory Workshop — A VoD System for Massively Scaled, Heterogeneous Environments (May 2015) University of Seoul — A VoD System for Massively Scaled, Heterogeneous Environments (May 2014) KAIST — The MDS Queue: Analysing the Latency Performance of Codes (Oct. 2013) IEEE International Conference on Big Data — The MDS Queue: Analysing the Latency Performance of Codes (Dec. 2013) DIMACS Workshop on Algorithms for Green Data Storage, Rutgers University — When Do Redundant Requests Reduce Latency? Publications Show all publications
Selected Publications ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games Outstanding Paper Award @ EMNLP 2025 Wordplay Workshop VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data (oral) Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition (spotlight) Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges Looped Transformers for Length Generalization Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance (spotlight) Dual Operating Modes of In-Context Learning The Expressive Power of Low-Rank Adaptation Teaching Arithmetic to Small Transformers DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models LIFT: Language-Interfaced FineTuning for Non-Language Machine Learning Tasks Score-based generative modeling secretly minimizes the Wasserstein distance Coded-InvNet for Resilient Prediction Serving Systems (long oral) Speeding Up Distributed Machine Learning Using Codes The Joint Communications Society/Information Theory Society Paper Award, 2020 Preprints Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models In-Context Learning with Hypothesis-Class Guidance LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning Summary | Github How to Correctly Report LLM-as-a-Judge Evaluations Summary | Github Multi-Bin Batching for Increasing LLM Inference Throughput 2026 TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents Github Draft-based Approximate Inference for LLMs Summary | Github ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs Summary | Github Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games Outstanding Paper Award @ EMNLP 2025 Wordplay Workshop | Summary | Github TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs 2025 Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games Outstanding Paper Award Transformers in the Dark: Navigating unknown search spaces via noisy feedback ENTP: Encoder-only Next Token Prediction (spotlight) Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents Summary Improvement-Guided Iterative DPO for Diffusion Models In-batch Ensemble Drafting: Toward Fast and Robust Speculative Decoding for Multimodal Language Models Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges Task Vectors in In-Context Learning: Emergence, Formation, and Benefit VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data (oral) | Summary | Github | HuggingFace Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition (spotlight) Parameter-Efficient Fine-Tuning of State Space Models Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges Looped Transformers for Length Generalization Summary | Github From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data Summary | Github Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance (spotlight) | Summary | Github ENTP: Encoder-only Next Token Prediction Improving CLIP Counting Accuracy via Parameter-Efficient Fine-Tuning Github Buffer-based Gradient Projection for Continual Federated Learning Github 2024 Can MLLMs Perform Text-to-Image In-Context Learning? Summary | Github Dual Operating Modes of In-Context Learning Summary | Github Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks Github Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks The Expressive Power of Low-Rank Adaptation Summary | Github Image Clustering Conditioned on Text Criteria Summary | Github Teaching Arithmetic to Small Transformers Summary | Github Looped Transformers are Better at Learning Learning Algorithms Summary | Github Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression Mini-Batch Optimization of Contrastive Loss Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding Superresolution emulation of large cosmological fields with a 3D conditional diffusion model 2023 DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models Prompted LLMs as Chatbot Modules for Long Open-domain Conversation Improving Fair Training under Correlation Shifts Optimizing DDPM Sampling with Shortcut Fine-Tuning Looped Transformers as Programmable Computers Equal Improvability: A New Fairness Notion Considering the Long-Term Impact FedGP: Buffer-based Gradient Projection for Continual Federated Learning Best Paper Award 2022 Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment Score-based generative modeling secretly minimizes the Wasserstein distance LIFT: Language-Interfaced FineTuning for Non-Language Machine Learning Tasks Rare Gems: Finding Lottery Tickets at Initialization GenLabel: Mixup Relabeling using Generative Models Permutation-Based SGD: Is Random Optimal? 2021 Sample Selection for Fair and Robust Training Gradient Inversion with Generative Image Prior Coded-InvNet for Resilient Prediction Serving Systems (long oral) Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification FairBatch: Batch Selection for Model Fairness 2020 Attack of the Tails: Yes, You Really Can Backdoor Federated Learning Reprogramming GANs via Input Noise Design FR-Train: A mutual information-based approach to fair and robust training 2019 Synthesizing Differentially Private Datasets using Random Mixing Crash to Not Crash: Learn to Identify Dangerous Vehicles using a Simulator long oral SAFFRON: Sparse-Graph Code Framework for Group Testing Community Recovery in Hypergraphs 2018 Binary Rating Estimation with Graph Side Information Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings Speeding Up Distributed Machine Learning Using Codes The Joint Communications Society/Information Theory Society Paper Award, 2020 2017 and earlier The MDS Queue: Analysing the Latency Performance of Erasure Codes On Scheduling Redundant Requests With Cancellation Overheads When Do Redundant Requests Reduce Latency? PhaseCode: Fast and Efficient Compressive Phase Retrieval based on Sparse-Graph-Codes A VoD System for Massively Scaled, Heterogeneous Environments: Design and Implementation Best Paper Award finalist Lee Lab @ UW-Madison Postdocs PhD Students Undergraduate Students Ethan Ewer (ECE, Math, Violin Performance)Lynnix Zou (ECE, CS) Visiting Researchers Alumni — PhD Students Alumni — MS Students Ruisu Zhang (2024) => Machine Learning Engineer @ WeRide Andrew Geng (2023) => Research Engineer @ IBM Liang Shang (2021) => PhD student @ UW Madison Alumni — Postdocs Dr. Jy-yong Sohn (3/2021 – 12/2022) => Assistant Professor @ Yonsei University, KoreaDr. Daewon Seo (1/2020 – 7/2021) => Assistant Professor @ DGIST, KoreaAlumni — Undergraduate Students Jackson Kunde (2024-2025 Hilldale Fellow) => Machine Learning Engineer @ OhaloBryce Chen (2023-2024 Hilldale Fellow) => PhD student @ University of Washington, SeattleMichael Gira (2022-2023 Hilldale Fellow) => Software Engineer @ MicrosoftFurry Collaborators Bokdol Lee (Philosophy, Math, and Kinesiology)
Awards & Service Awards and Honors Outstanding Paper Award, The 5th Wordplay Workshop @ EMNLP 2025 Fusion Fund Distinguished Scholar Network, Inaugural Member, 2025 NSF CAREER Award, 2024. Amazon Research Awards, 2024. Best Paper Award, The Federated Learning Systems (FLSys) Workshop @ MLSys 2023 ECE Grainger Faculty Scholarship Award, 2022, UW Madison ECE. Young Investigator Grants Award, 2022, KSEA. (link) The Joint Communications Society/Information Theory Society Paper Award, 2020, IEEE. (link) The Outstanding Graduate Student Instructor Award, 2016. (link) Best Paper Award Finalist, 2013, IEEE MASCOTS 2013 KFAS Fellowship, 2010 - 2015, Korea Foundation for Advanced Studies (KFAS) Graduated with the highest GPA (4.19/4.30) among all (> 800) students across all departments at KAIST who completed their degrees in 2010. (Presidential Award) Korea Talent Award, 2009, KOFAC Selected Services Conference Senior Program CommitteeArea Chair, NeurIPS 2025, 2024, 2023, 2022, 2021 Area Chair, ICML 2026, 2025, 2024, 2023 Area Chair, ICLR 2026, 2025 Area Chair, COLM 2026, 2025, 2024 Program Committee, MLSys 2026, 2025, 2024, 2023, 2022, 2021, 2020 Journal Associate EditorAction Editor, Transactions on Machine Learning Research, 2026, 2025, 2024, 2023, 2022 Teaching At UW Madison ECE 901 Advanced Topics in Large Language Models , Fall 2025ECE/ISYE 570 Ethics of Data for Engineers, Spring 2025, Spring 2024. ECE/CS/ME 539 Introduction to Artificial Neural Networks, Fall 2024. ECE 901 Theory of Deep Learning Algorithms and Architectures, Spring 2023. ECE/CS 561 Probability and Information Theory in Machine Learning, Fall 2022. ECE/CS/ME 532 Matrix Methods in Machine Learning, Spring 2022, Fall 2020, Fall 2019 ECE 204 Data Science & Engineering, Fall 2021. ECE/CS 761 Mathematical Foundations of Machine Learning, Spring 2021, Spring 2020 At UC Berkeley Head GSI (Outstanding GSI Award), EECS 126 Probability and Random Processes, Fall 2015. webpage Head GSI, EECS 126 Probability and Random Processes, Fall 2014. webpage Background Academic Appointments Associate Professor, UW Madison, 2025.07 – 2026.01 Assistant Professor, UW Madison, 2019.08 – 2025.06 Research Assistant Professor, KAIST, 2018.10 – 2019.06 Postdoctoral Fellow, KAIST, 2016.06 – 2018.09 Graduate Student Researcher, UC Berkeley, 2010.08 – 2016.05 Education Ph.D., University of California, Berkeley, 2010.08 – 2016.05 (EECS) M.S., University of California, Berkeley, 2010.08 – 2012.12 (EECS) B.S., KAIST, 2006.03 – 2010.05 (Electrical Engineering) Work Experience CAIO, KRAFTON, 2026.02 – present CTO, Ludo Robotics, 2026.02 – present Head of Deep Learning R&D, KRAFTON, 2022.04 – 2026.01 Software Engineer Intern, Lytmus Inc., 2013.06 – 2013.09 Software Engineer Intern, Samsung Electronics, 2009.07 Software/Hardware Engineer Intern, LG Display, 2008.06 – 2008.08 
Bokdol Lee (Philosophy, Math, and Kinesiology)