Kangwook Lee

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs EACL 2026 Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition ICML 2025 From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data ICLR 2025 Looped Transformers for Length Generalization ICLR 2025 Parameter-Efficient Fine-Tuning of State Space Models ICML 2025 Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance ICLR 2025 Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges ICML 2025 Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs ACL 2025 VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data ICML 2025 Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks ICML 2024 Dual Operating Modes of In-Context Learning ICML 2024 Image Clustering Conditioned on Text Criteria ICLR 2024 Looped Transformers are Better at Learning Learning Algorithms ICLR 2024 Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks UAI 2024 Teaching Arithmetic to Small Transformers ICLR 2024 The Expressive Power of Low-Rank Adaptation ICLR 2024 Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression JMLR 2024 DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models NeurIPS 2023 Equal Improvability: A New Fairness Notion Considering the Long-term Impact ICLR 2023 Improving Fair Training under Correlation Shifts ICML 2023 Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning AAAI 2023 Looped Transformers as Programmable Computers ICML 2023 Optimizing DDPM Sampling with Shortcut Fine-Tuning ICML 2023 Prompted LLMs as Chatbot Modules for Long Open-domain Conversation ACL 2023 Debiasing Pre-Trained Language Models via Efficient Fine-Tuning ACL 2022 GenLabel: Mixup Relabeling using Generative Models ICML 2022 Learning to Embed Multi-Modal Contexts for Situated Conversational Agents NAACL 2022 LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks NeurIPS 2022 Permutation-Based SGD: Is Random Optimal? ICLR 2022 Rare Gems: Finding Lottery Tickets at Initialization NeurIPS 2022 Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance NeurIPS 2022 Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment EMNLP 2022 Coded-InvNet for Resilient Prediction Serving Systems ICML 2021 Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information ICML 2021 FairBatch: Batch Selection for Model Fairness ICLR 2021 Gradient Inversion with Generative Image Prior NeurIPS 2021 Sample Selection for Fair and Robust Training NeurIPS 2021 Attack of the Tails: Yes, You Really Can Backdoor Federated Learning NeurIPS 2020 Fairness without Demographics through Adversarially Reweighted Learning NeurIPS 2020 FR-Train: A Mutual Information-Based Approach to Fair and Robust Training ICML 2020 SLM: Learning a Discourse Language Representation with Sentence Unshuffling EMNLP 2020 Crash to Not Crash: Learn to Identify Dangerous Vehicles Using a Simulator AAAI 2019 Binary Rating Estimation with Graph Side Information NeurIPS 2018 Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings ICLR 2018