Kangwook Lee

44 papers · 2018–2026 · 10 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🗺️ Taxonomy Completionist (16) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (5) 🌍 Conference Polyglot (9)

🗺️ Taxonomy Completionist (16) 🧭 Keyword Pioneer 🏃 Academic Marathon (7) 🏆 Keyword Champion (2) 🤝 Dynamic Duo (15) 🏆 Grand Slam 👑 Triple Crown 🗃️ Keyword Collector (155) ❓ The Questioner (2) ⚡ Prolific Year (7) 🚀 Conference Pioneer 💎 Century Club (43) 🔥 Unstoppable (8)

Conferences

ICML (13) ICLR (11) NIPS (9) ACL (3) AAAI (2) EMNLP (2) EACL (1) JMLR (1) NAACL (1) UAI (1)

Top co-authors

Dimitris Papailiopoulos (15) Jy-yong Sohn (8) Changho Suh (7) Shashank Rajput (5) Ying Fan (5) Yuchen Zeng (4) Yuji Roh (4) Wonjun Kang (3) Tuan Dinh (3) Kartik Sreenivasan (3)

Keywords

diffusion model (3) sample complexity (2) knowledge distillation (2) robust training (2) large language model (2) domain adaptation (2) generative model (2) matrix completion (2) group fairness (2) recommender system (2) model compression (2) adversarial learning (2) graph side information (2) algorithmic fairness (2) federated learning (2) policy gradient (2) multi-task learning (1) neural network pruning (1) reinforcement learning (1) neural network compression (1)

Papers

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs EACL 2026 Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs ACL 2025 From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data ICLR 2025 Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance ICLR 2025 Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition ICML 2025 VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data ICML 2025 Looped Transformers for Length Generalization ICLR 2025 Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges ICML 2025 Parameter-Efficient Fine-Tuning of State Space Models ICML 2025 The Expressive Power of Low-Rank Adaptation ICLR 2024 Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks UAI 2024 Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression JMLR 2024 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 Looped Transformers are Better at Learning Learning Algorithms ICLR 2024 Image Clustering Conditioned on Text Criteria ICLR 2024 Teaching Arithmetic to Small Transformers ICLR 2024 Improving Fair Training under Correlation Shifts ICML 2023 Looped Transformers as Programmable Computers ICML 2023 Prompted LLMs as Chatbot Modules for Long Open-domain Conversation ACL 2023 Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning AAAI 2023 DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models NIPS 2023 Optimizing DDPM Sampling with Shortcut Fine-Tuning ICML 2023 Equal Improvability: A New Fairness Notion Considering the Long-term Impact ICLR 2023 LIFT: Language-Interfaced Fine-Tuning for Non-language Machine Learning Tasks NIPS 2022 Rare Gems: Finding Lottery Tickets at Initialization NIPS 2022 Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance NIPS 2022 Debiasing Pre-Trained Language Models via Efficient Fine-Tuning ACL 2022 Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment EMNLP 2022 Permutation-Based SGD: Is Random Optimal? ICLR 2022 GenLabel: Mixup Relabeling using Generative Models ICML 2022 Learning to Embed Multi-Modal Contexts for Situated Conversational Agents NAACL 2022 Coded-InvNet for Resilient Prediction Serving Systems ICML 2021 FairBatch: Batch Selection for Model Fairness ICLR 2021 Gradient Inversion with Generative Image Prior NIPS 2021 Sample Selection for Fair and Robust Training NIPS 2021 Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information ICML 2021 FR-Train: A Mutual Information-Based Approach to Fair and Robust Training ICML 2020 Fairness without Demographics through Adversarially Reweighted Learning NIPS 2020 Attack of the Tails: Yes, You Really Can Backdoor Federated Learning NIPS 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 NIPS 2018 Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings ICLR 2018