Honglak Lee

78

Papers

1,448

Total Citations

Papers (78)

Learning What and Where to Draw

NeurIPS 2016arXiv

Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision

NeurIPS 2016arXiv

MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics

View Selection for 3D Captioning via Diffusion Ranking

Visual Test-time Scaling for GUI Agent Grounding

Unsupervised Object Interaction Learning with Counterfactual Dynamics Models

3D Denoisers Are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation

Object Contour Detection With a Fully Convolutional Encoder-Decoder Network

Learning Transferrable Knowledge for Semantic Segmentation With Deep Convolutional Neural Network

Discriminative Bimodal Networks for Visual Localization and Detection With Natural Language Queries

Weakly Supervised Semantic Segmentation Using Web-Crawled Videos

Hierarchical Novelty Detection for Visual Object Recognition

Unsupervised Discovery of Object Landmarks as Structural Representations

Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis

Neural Kinematic Networks for Unsupervised Motion Retargetting

Efficient Adversarial Training With Transferable Adversarial Examples

Distilling Effective Supervision From Severe Label Noise

Cross-Modal Contrastive Learning for Text-to-Image Generation

L-Verse: Bidirectional Generation Between Image and Text

Hierarchical Discriminative Learning Improves Visual Representations of Biomedical Microscopy

Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild

Adversarial Defense via Learning to Generate Diverse Attacks

Pathdreamer: A World Model for Indoor Navigation

Story Visualization by Online Text Augmentation with Context Memory

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

High-Fidelity Synthesis with Disentangled Representation

Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis

Action-Conditional Video Prediction using Deep Networks in Atari Games

Learning Structured Output Representation using Deep Conditional Generative Models

Deep Visual Analogy-Making

Active Test-time Vision-Language Navigation

Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents

Step-Calibrated Diffusion for Biomedical Optical Image Restoration

Learning to Unlearn: Instance-Wise Unlearning for Pre-trained Classifiers

Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without Degeneration

Improving Object Detection With Deep Convolutional Networks via Bayesian Optimization and Structured Prediction

Evaluation of Output Embeddings for Fine-Grained Image Classification

Learning Deep Representations of Fine-Grained Visual Descriptions

Learning Latent Dynamics for Planning from Pixels

Similarity of Neural Network Representations Revisited

Robust Inference via Generative Classifiers for Handling Noisy Labels

Value Prediction Network

Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies

Learning Hierarchical Semantic Image Manipulation through Structured Representations

Content preserving text generation with attribute controls

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Data-Efficient Hierarchical Reinforcement Learning

Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion

Unsupervised learning of object structure and dynamics from videos

High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks

Ode to an ODE

Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards

Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning

Predictive Information Accelerates Learning in RL

Environment Generation for Zero-Shot Compositional Reinforcement Learning

Improving Transferability of Representations via Augmentation-Aware Self-Supervision

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning

Why Do Better Loss Functions Lead to Less Transferable Features?

UniCLIP: Unified Framework for Contrastive Language-Image Pre-training

NeurIPS 2022arXiv

Pure Transformers are Powerful Graph Learners

Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost

CEDe: A collection of expert-curated datasets with atom-level entity annotations for Optical Chemical Structure Recognition

OpenSRH: optimizing brain tumor surgery using intraoperative stimulated Raman histology

Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching

Combining Behaviors with the Successor Features Keyboard

CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models

Guide Your Agent with Adaptive Multimodal Rewards

SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations

Scalable 3D Captioning with Pretrained Models

Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification

Generative Adversarial Text to Image Synthesis

Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units

Control of Memory, Active Perception, and Action in Minecraft

Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

Learning to Generate Long-term Future via Hierarchical Prediction

Self-Imitation Learning

Hierarchical Long-term Video Prediction without Supervision