Kimin Lee

Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance CVPR 2026 Learning Multi-View Spatial Reasoning from Cross-View Relations CVPR 2026 MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control AAAI 2026 Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation AAAI 2026 Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models ICLR 2025 DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models AAAI 2025 DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing ICLR 2025 Enhancing LLM Agent Safety via Causal Influence Prompting ACL 2025 Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers EMNLP 2025 Latent Action Pretraining from Videos ICLR 2025 Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents ICLR 2025 Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models CVPR 2025 Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment ICLR 2025 Subtask-Aware Visual Reward Learning from Segmented Demonstrations ICLR 2025 Understanding Impact of Human Feedback via Influence Functions ACL 2025 What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs ACL 2025 By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting EMNLP 2024 Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models ICLR 2024 Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models NeurIPS 2024 Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback EMNLP 2024 Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences CVPR 2024 Controllability-Aware Unsupervised Skill Discovery ICML 2023 DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models NeurIPS 2023 Guide Your Agent with Adaptive Multimodal Rewards NeurIPS 2023 Multi-View Masked World Models for Visual Robotic Manipulation ICML 2023 Preference Transformer: Modeling Human Preferences using Transformers for RL ICLR 2023 StyleDrop: Text-to-Image Synthesis of Any Style NeurIPS 2023 Masked World Models for Visual Control CoRL 2022 Programmatic Modeling and Generation of Real-Time Strategic Soccer Environments for Reinforcement Learning AAAI 2022 Reinforcement Learning with Action-Free Pre-Training from Videos ICML 2022 Reward Uncertainty for Exploration in Preference-based Reinforcement Learning ICLR 2022 SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning ICLR 2022 Decision Transformer: Reinforcement Learning via Sequence Modeling NeurIPS 2021 Decoupling Representation Learning from Reinforcement Learning ICML 2021 Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings NeurIPS 2021 Improving Transferability of Representations via Augmentation-Aware Self-Supervision NeurIPS 2021 Learning to Sample with Local and Global Contexts in Experience Replay Buffer ICLR 2021 MASKER: Masked Keyword Regularization for Reliable Text Classification AAAI 2021 Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble CoRL 2021 PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training ICML 2021 Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment IJCAI 2021 Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback CoRL 2021 State Entropy Maximization with Random Encoders for Efficient Exploration ICML 2021 SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning ICML 2021 Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning ICML 2020 Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning ICLR 2020 Regularizing Class-Wise Predictions via Self-Knowledge Distillation CVPR 2020 Reinforcement Learning with Augmented Data NeurIPS 2020 Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning NeurIPS 2020 Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild ICCV 2019 Robust Inference via Generative Classifiers for Handling Noisy Labels ICML 2019 Using Pre-Training Can Improve Model Robustness and Uncertainty ICML 2019 A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks NeurIPS 2018 Hierarchical Novelty Detection for Visual Object Recognition CVPR 2018 Learning to Specialize with Knowledge Distillation for Visual Question Answering NeurIPS 2018 Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples ICLR 2018 Confident Multiple Choice Learning ICML 2017