Honglak Lee

Beyond Blind Following: Evaluating Robustness of LLM Agents under Imperfect Guidance EACL 2026 IRPO: Implicit Policy Regularized Preference Optimization EACL 2026 3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation AAAI 2025 Probing Visual Language Priors in VLMs ICML 2025 Step-Calibrated Diffusion for Biomedical Optical Image Restoration AAAI 2025 MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows NAACL 2025 Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? EMNLP 2025 Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents CVPR 2025 Visual Test-time Scaling for GUI Agent Grounding ICCV 2025 Interactive and Expressive Code-Augmented Planning with Large Language Models ACL 2025 Subtask-Aware Visual Reward Learning from Segmented Demonstrations ICLR 2025 Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination ACL 2024 Prospector: Improving LLM Agents with Self-Asking and Trajectory Ranking EMNLP 2024 Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration ICML 2024 Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks EMNLP 2024 View Selection for 3D Captioning via Diffusion Ranking ECCV 2024 Unsupervised Object Interaction Learning with Counterfactual Dynamics Models AAAI 2024 Efficient Dynamic Hard Negative Sampling for Dialogue Selection ACL 2024 Small Language Models Need Strong Verifiers to Self-Correct Reasoning ACL 2024 Learning to Unlearn: Instance-Wise Unlearning for Pre-trained Classifiers AAAI 2024 AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents NIPS 2024 Code Models are Zero-shot Precondition Reasoners NAACL 2024 Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense NAACL 2024 Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents EMNLP 2024 Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning ACL 2024 Learning Compositional Tasks from Language Instructions AAAI 2023 Hierarchical Discriminative Learning Improves Visual Representations of Biomedical Microscopy CVPR 2023 Investigation of Training Mute-Expressive End-to-End Speech Separation Networks for an Unknown Number of Speakers INTERSPEECH 2023 Go Beyond Imagination: Maximizing Episodic Reachability with World Models ICML 2023 Preference Transformer: Modeling Human Preferences using Transformers for RL ICLR 2023 Composing Task Knowledge With Modular Successor Feature Approximators ICLR 2023 Enriched CNN-Transformer Feature Aggregation Networks for Super-Resolution WACV 2023 Combining Behaviors with the Successor Features Keyboard NIPS 2023 CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation NIPS 2023 Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models NIPS 2023 Guide Your Agent with Adaptive Multimodal Rewards NIPS 2023 SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations NIPS 2023 Scalable 3D Captioning with Pretrained Models NIPS 2023 Simple and Effective Synthesis of Indoor 3D Scenes AAAI 2023 Grouping Matrix Based Graph Pooling with Adaptive Number of Clusters AAAI 2023 TOD-Flow: Modeling the Structure of Task-Oriented Dialogues EMNLP 2023 Few-shot Reranking for Multi-hop QA via Language Model Prompting ACL 2023 Unsupervised Task Graph Generation from Instructional Video Transcripts ACL 2023 Fine-grained Text Style Transfer with Diffusion-Based Language Models ACL 2023 Story Visualization by Online Text Augmentation with Context Memory ICCV 2023 GRACE: Discriminator-Guided Chain-of-Thought Reasoning EMNLP 2023 A Picture is Worth a Thousand Words: Language Models Plan from Pixels EMNLP 2023 From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning EMNLP 2023 Merging Generated and Retrieved Knowledge for Open-Domain QA EMNLP 2023 Path-Aware and Structure-Preserving Generation of Synthetically Accessible Molecules ICML 2022 Lipschitz-constrained Unsupervised Skill Discovery ICLR 2022 Few-shot Subgoal Planning with Language Models NAACL 2022 L-Verse: Bidirectional Generation Between Image and Text CVPR 2022 Pure Transformers are Powerful Graph Learners NIPS 2022 Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost NIPS 2022 CEDe: A collection of expert-curated datasets with atom-level entity annotations for Optical Chemical Structure Recognition NIPS 2022 OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology NIPS 2022 Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching NIPS 2022 SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning ICLR 2022 UniCLIP: Unified Framework for Contrastive Language-Image Pre-training NIPS 2022 Fast inference and transfer of compositional task structures for few-shot task generalization UAI 2022 Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks AAAI 2022 Learning Parameterized Task Structure for Generalization to Unseen Entities AAAI 2022 Evolving Reinforcement Learning Algorithms ICLR 2021 Batch Reinforcement Learning Through Continuation Method ICLR 2021 $i$-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning ICLR 2021 Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction ICLR 2021 Pathdreamer: A World Model for Indoor Navigation ICCV 2021 Why Do Better Loss Functions Lead to Less Transferable Features? NIPS 2021 Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning NIPS 2021 Improving Transferability of Representations via Augmentation-Aware Self-Supervision NIPS 2021 Environment Generation for Zero-Shot Compositional Reinforcement Learning NIPS 2021 Improved Consistency Regularization for GANs AAAI 2021 Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment IJCAI 2021 Learning to Weight Imperfect Demonstrations ICML 2021 Cross-Modal Contrastive Learning for Text-to-Image Generation CVPR 2021 Text-to-Image Generation Grounded by Fine-Grained User Attention WACV 2021 Variational Empowerment as Representation Learning for Goal-Conditioned Reinforcement Learning ICML 2021 State Entropy Maximization with Random Encoders for Efficient Exploration ICML 2021 Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks ICML 2021 Efficient Adversarial Training With Transferable Adversarial Examples CVPR 2020 Ode to an ODE NIPS 2020 Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards NIPS 2020 Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning NIPS 2020 Predictive Information Accelerates Learning in RL NIPS 2020 How Should an Agent Practice? AAAI 2020 Distilling Effective Supervision From Severe Label Noise CVPR 2020 SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing ECCV 2020 High-Fidelity Synthesis with Disentangled Representation ECCV 2020 Consistency Regularization for Generative Adversarial Networks ICLR 2020 Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies ICLR 2020 Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning ICLR 2020 Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning ICML 2020 BRPO: Batch Residual Policy Optimization IJCAI 2020 CompressNet: Generative Compression at Extremely Low Bitrates WACV 2020 Adversarial Defense via Learning to Generate Diverse Attacks ICCV 2019 Learning Latent Dynamics for Planning from Pixels ICML 2019 Similarity of Neural Network Representations Revisited ICML 2019 Contingency-Aware Exploration in Reinforcement Learning ICLR 2019 Diversity-Sensitive Conditional Generative Adversarial Networks ICLR 2019 Near-Optimal Representation Learning for Hierarchical Reinforcement Learning ICLR 2019 Zero-Shot Entity Linking by Reading Entity Descriptions ACL 2019 High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks NIPS 2019 Unsupervised learning of object structure and dynamics from videos NIPS 2019 Robust Inference via Generative Classifiers for Handling Noisy Labels ICML 2019 Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild ICCV 2019 An efficient framework for learning sentence representations ICLR 2018 Data-Efficient Hierarchical Reinforcement Learning NIPS 2018 Hierarchical Long-term Video Prediction without Supervision ICML 2018 Content preserving text generation with attribute controls NIPS 2018 A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks NIPS 2018 Unsupervised Discovery of Object Landmarks as Structural Representations CVPR 2018 Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis CVPR 2018 Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples ICLR 2018 Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion NIPS 2018 Neural Kinematic Networks for Unsupervised Motion Retargetting CVPR 2018 MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics ECCV 2018 Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies NIPS 2018 Learning Hierarchical Semantic Image Manipulation through Structured Representations NIPS 2018 Hierarchical Novelty Detection for Visual Object Recognition CVPR 2018 Self-Imitation Learning ICML 2018 Discriminative Bimodal Networks for Visual Localization and Detection With Natural Language Queries CVPR 2017 Value Prediction Network NIPS 2017 Learning to Generate Long-term Future via Hierarchical Prediction ICML 2017 Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning ICML 2017 Towards Understanding the Invertibility of Convolutional Neural Networks IJCAI 2017 Weakly Supervised Semantic Segmentation Using Web-Crawled Videos CVPR 2017 Deep Learning for Reward Design to Improve Monte Carlo Tree Search in ATARI Games IJCAI 2016 Learning Transferrable Knowledge for Semantic Segmentation With Deep Convolutional Neural Network CVPR 2016 Object Contour Detection With a Fully Convolutional Encoder-Decoder Network CVPR 2016 Learning Deep Representations of Fine-Grained Visual Descriptions CVPR 2016 Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification ICML 2016 Generative Adversarial Text to Image Synthesis ICML 2016 Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units ICML 2016 Control of Memory, Active Perception, and Action in Minecraft ICML 2016 Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision NIPS 2016 Learning What and Where to Draw NIPS 2016 Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents NAACL 2016 Improving Object Detection With Deep Convolutional Networks via Bayesian Optimization and Structured Prediction CVPR 2015 Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis NIPS 2015 Action-Conditional Video Prediction using Deep Networks in Atari Games NIPS 2015 Evaluation of Output Embeddings for Fine-Grained Image Classification CVPR 2015 Learning Structured Output Representation using Deep Conditional Generative Models NIPS 2015 Deep Visual Analogy-Making NIPS 2015 Learning to Disentangle Factors of Variation with Manifold Interaction ICML 2014 Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning NIPS 2014 Improved Multimodal Deep Learning with Variation of Information NIPS 2014 Structured Recurrent Temporal Restricted Boltzmann Machines ICML 2014 Adaptive Multi-Column Deep Neural Networks with Application to Robust Image Denoising NIPS 2013 Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling CVPR 2013 Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines ICML 2013 Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines CVPR 2013 Deep Learning for Detecting Robotic Grasps RSS 2013 Online Incremental Feature Learning with Denoising Autoencoders AISTATS 2012 Learning to Align from Scratch NIPS 2012 Efficient Distributed Linear Classification Algorithms via the Alternating Direction Method of Multipliers AISTATS 2012 Efficient and Exact MAP-MRF Inference using Branch and Bound AISTATS 2012 An Analysis of Single-Layer Networks in Unsupervised Feature Learning AISTATS 2011 Measuring Invariances in Deep Networks NIPS 2009 Unsupervised feature learning for audio classification using convolutional deep belief networks NIPS 2009 Sparse deep belief net model for visual area V2 NIPS 2007 Efficient sparse coding algorithms NIPS 2006