Stefano Ermon

CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion ICLR 2025 TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data ICLR 2025 TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation ICLR 2025 Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints ICML 2025 Energy-Based Diffusion Language Models for Text Generation ICLR 2025 ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts ICML 2025 Personalized Preference Fine-tuning of Diffusion Models CVPR 2025 Data Unlearning in Diffusion Models ICLR 2025 TFG-Flow: Training-free Guidance in Multimodal Generative Flow ICLR 2025 Smooth Interpolation for Improved Discrete Graph Generative Models ICML 2025 Scaling Probabilistic Circuits via Monarch Matrices ICML 2025 Inductive Moment Matching ICML 2025 $f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization AISTATS 2025 CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers ICCV 2025 TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning NIPS 2024 Convolutional Differentiable Logic Gate Networks NIPS 2024 Equivariant Graph Neural Operator for Modeling 3D Dynamics ICML 2024 Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data ICML 2024 Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution ICML 2024 Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution AAAI 2024 HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing AAAI 2024 Disentangling Length from Quality in Direct Preference Optimization ACL 2024 Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients AISTATS 2024 Mechanistic Design and Scaling of Hybrid Architectures ICML 2024 State-Free Inference of State-Space Models: The *Transfer Function* Approach ICML 2024 Large Language Models are Geographically Biased ICML 2024 Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs ICML 2024 HIVE: Harnessing Human Feedback for Instructional Visual Editing CVPR 2024 On the Scalability of Diffusion-based Text-to-Image Generation CVPR 2024 DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling CVPR 2024 Diffusion Model Alignment Using Direct Preference Optimization CVPR 2024 Language Model Detectors Are Easily Optimized Against ICLR 2024 SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking ICLR 2024 Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion ICLR 2024 Manifold Preserving Guided Diffusion ICLR 2024 DiffusionSat: A Generative Foundation Model for Satellite Imagery ICLR 2024 Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing ICLR 2024 Denoising Diffusion Bridge Models ICLR 2024 GeoLLM: Extracting Geospatial Knowledge from Large Language Models ICLR 2024 MADiff: Offline Multi-agent Learning with Diffusion Models NIPS 2024 Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations NIPS 2024 PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher NIPS 2024 TFG: Unified Training-Free Guidance for Diffusion Models NIPS 2024 Generative Fractional Diffusion Models NIPS 2024 Geometric Trajectory Diffusion Models NIPS 2024 Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms NIPS 2024 Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization NIPS 2024 Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes NIPS 2024 Segment Any Change NIPS 2024 TrAct: Making First-layer Pre-Activations Trainable NIPS 2024 HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution NIPS 2023 GEO-Bench: Toward Foundation Models for Earth Monitoring NIPS 2023 Direct Preference Optimization: Your Language Model is Secretly a Reward Model NIPS 2023 Holistic Evaluation of Text-to-Image Models NIPS 2023 Generative Modeling Helps Weak Supervision (and Vice Versa) ICLR 2023 But Are You Sure? An Uncertainty-Aware Perspective on Explainable AI AISTATS 2023 Ideal Abstractions for Decision-Focused Learning AISTATS 2023 Long Horizon Temperature Scaling ICML 2023 Scaling Riemannian Diffusion Models NIPS 2023 Geometric Latent Diffusion Models for 3D Molecule Generation ICML 2023 Deep Latent State Space Models for Time-Series Generation ICML 2023 Dual Diffusion Implicit Bridges for Image-to-Image Translation ICLR 2023 CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations ICML 2023 GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration ICML 2023 Hyena Hierarchy: Towards Larger Convolutional Language Models ICML 2023 End-to-End Diffusion Latent Optimization Improves Classifier Guidance ICCV 2023 GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation ICCV 2023 Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching AAAI 2023 FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation ICML 2023 Reflected Diffusion Models ICML 2023 Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation NIPS 2023 Parallel Sampling of Diffusion Models NIPS 2023 On Distillation of Guided Diffusion Models CVPR 2023 Extreme Q-Learning: MaxEnt RL without Entropy ICLR 2023 Understanding and Adopting Rational Behavior by Bellman Score Estimation ICLR 2023 Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions NIPS 2023 Calibration by Distribution Matching: Trainable Kernel Calibration Metrics NIPS 2023 UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild NIPS 2023 SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations ICLR 2022 Solving Inverse Problems in Medical Imaging with Score-Based Generative Models ICLR 2022 Comparing Distributions by Measuring Differences that Affect Decision Making ICLR 2022 GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation ICLR 2022 Local calibration: metrics and recalibration UAI 2022 Experience Replay with Likelihood-free Importance Weights L4DC 2022 SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery NIPS 2022 Training and Inference on Any-Order Autoregressive Models the Right Way NIPS 2022 Transform Once: Efficient Operator Learning in Frequency Domain NIPS 2022 Improving Self-Supervised Learning by Characterizing Idealized Representations NIPS 2022 FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness NIPS 2022 Generalizing Bayesian Optimization with Decision-theoretic Entropies NIPS 2022 LISA: Learning Interpretable Skill Abstractions from Language NIPS 2022 Denoising Diffusion Restoration Models NIPS 2022 Exploration via Planning for Information about the Optimal Trajectory NIPS 2022 Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models NIPS 2022 Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations NIPS 2022 Concrete Score Matching: Generalized Score Matching for Discrete Data NIPS 2022 IS-Count: Large-Scale Object Counting from Satellite Images with Covariate-Based Importance Sampling AAAI 2022 A General Recipe for Likelihood-free Bayesian Optimization ICML 2022 Bit Prioritization in Variational Autoencoders via Progressive Coding ICML 2022 ButterflyFlow: Building Invertible Layers with Butterfly Matrices ICML 2022 Modular Conformal Calibration ICML 2022 Imitation Learning by Estimating Expertise of Demonstrators ICML 2022 Density Ratio Estimation via Infinitesimal Classification AISTATS 2022 An Experimental Design Perspective on Model-Based Reinforcement Learning ICLR 2022 Temporal Predictive Coding For Model-Based Planning In Latent Space ICML 2021 Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving ICML 2021 Predicting Livelihood Indicators from Community-Generated Street-Level Imagery AAAI 2021 Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information ICML 2021 Efficient Poverty Mapping from High Resolution Remote Sensing Images AAAI 2021 Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis NIPS 2021 Improving Compositionality of Neural Networks by Decoding Representations to Inputs NIPS 2021 Estimating High Order Gradients of the Data Distribution by Denoising NIPS 2021 CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation NIPS 2021 Pseudo-Spherical Contrastive Divergence NIPS 2021 Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration NIPS 2021 Geography-Aware Self-Supervised Learning ICCV 2021 PiRank: Scalable Learning To Rank via Differentiable Sorting NIPS 2021 D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation NIPS 2021 HyperSPNs: Compact and Expressive Probabilistic Circuits NIPS 2021 Reward Identification in Inverse Reinforcement Learning ICML 2021 BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery NIPS 2021 Imitation with Neural Density Models NIPS 2021 IQ-Learn: Inverse soft-Q Learning for Imitation NIPS 2021 Reliable Decisions with Threshold Calibration NIPS 2021 Maximum Likelihood Training of Score-Based Diffusion Models NIPS 2021 Featurized density ratio estimation UAI 2021 Negative Data Augmentation ICLR 2021 Evaluating the Disentanglement of Deep Generative Models through Manifold Topology ICLR 2021 On the Critical Role of Conventions in Adaptive Human-AI Collaboration ICLR 2021 Denoising Diffusion Implicit Models ICLR 2021 Anytime Sampling for Autoregressive Models via Ordered Autoencoding ICLR 2021 Improved Autoregressive Modeling with Distribution Smoothing ICLR 2021 Score-Based Generative Modeling through Stochastic Differential Equations ICLR 2021 Right Decisions from Wrong Predictions: A Mechanism Design Alternative to Individual Calibration AISTATS 2021 Efficient Object Detection in Large Images Using Deep Reinforcement Learning WACV 2020 Belief Propagation Neural Networks NIPS 2020 HiPPO: Recurrent Memory with Optimal Polynomial Projections NIPS 2020 Diversity can be Transferred: Output Diversification for White- and Black-box Attacks NIPS 2020 Probabilistic Circuits for Variational Inference in Discrete Graphical Models NIPS 2020 Autoregressive Score Matching NIPS 2020 Multi-label Contrastive Predictive Coding NIPS 2020 Improved Techniques for Training Score-Based Generative Models NIPS 2020 MOPO: Model-based Offline Policy Optimization NIPS 2020 Efficient Learning of Generative Models via Finite-Difference Score Matching NIPS 2020 AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows AAAI 2020 Meta-Amortized Variational Inference and Learning AAAI 2020 Gaussianization Flows AISTATS 2020 Permutation Invariant Graph Generation via Score-Based Generative Modeling AISTATS 2020 A Framework for Sample Efficient Interval Estimation with Control Variates AISTATS 2020 Learning When and Where to Zoom With Deep Reinforcement Learning CVPR 2020 Weakly Supervised Disentanglement with Guarantees ICLR 2020 A Theory of Usable Information under Computational Constraints ICLR 2020 Understanding the Limitations of Variational Mutual Information Estimators ICLR 2020 Fair Generative Modeling via Weak Supervision ICML 2020 Domain Adaptive Imitation Learning ICML 2020 Predictive Coding for Locally-Linear Control ICML 2020 Bridging the Gap Between f-GANs and Wasserstein GANs ICML 2020 Training Deep Energy-Based Models with f-Divergence Minimization ICML 2020 Individual Calibration with Randomized Forecasting ICML 2020 Generating Interpretable Poverty Maps using Object Detection in Satellite Images IJCAI 2020 Flexible Approximate Inference via Stratified Normalizing Flows UAI 2020 Cloud Removal from Satellite Images using Spatiotemporal Generator Networks WACV 2020 Calibrated Model-Based Deep Reinforcement Learning ICML 2019 Adaptive Antithetic Sampling for Variance Reduction ICML 2019 InfoVAE: Balancing Learning and Inference in Variational Autoencoders AAAI 2019 Tile2Vec: Unsupervised Representation Learning for Spatially Distributed Data AAAI 2019 Approximating the Permanent by Sampling from Adaptive Partitions NIPS 2019 Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting NIPS 2019 MintNet: Building Invertible Neural Networks with Masked Convolutions NIPS 2019 Meta-Inverse Reinforcement Learning with Probabilistic Context Variables NIPS 2019 Generative Modeling by Estimating Gradients of the Data Distribution NIPS 2019 Multi-Agent Adversarial Inverse Reinforcement Learning ICML 2019 Reparameterizable Subset Sampling via Continuous Relaxations IJCAI 2019 Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations. NIPS 2019 Adaptive Hashing for Model Counting UAI 2019 Sliced Score Matching: A Scalable Approach to Density and Score Estimation UAI 2019 Stochastic Optimization of Sorting Networks via Continuous Relaxations ICLR 2019 Learning Neural PDE Solvers with Convergence Guarantees ICLR 2019 Neural Joint Source-Channel Coding ICML 2019 Learning to Interpret Satellite Images using Wikipedia IJCAI 2019 Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference AISTATS 2019 Uncertainty Autoencoders: Learning Compressed Representations via Variational Information Maximization AISTATS 2019 Learning Controllable Fair Representations AISTATS 2019 Training Variational Autoencoders with Buffered Stochastic Variational Inference AISTATS 2019 Graphite: Iterative Generative Modeling of Graphs ICML 2019 Multi-Agent Generative Adversarial Imitation Learning NIPS 2018 Accelerating Natural Gradient with Higher-Order Invariance ICML 2018 Adversarial Constraint Learning for Structured Prediction IJCAI 2018 PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples ICLR 2018 A DIRT-T Approach to Unsupervised Domain Adaptation ICLR 2018 End-to-End Learning of Motion Representation for Video Understanding CVPR 2018 Best arm identification in multi-armed bandits with delayed feedback AISTATS 2018 Variational Rejection Sampling AISTATS 2018 Modeling Sparse Deviations for Compressed Sensing using Generative Models ICML 2018 Bias and Generalization in Deep Generative Models: An Empirical Study NIPS 2018 Accurate Uncertainties for Deep Learning Using Calibrated Regression ICML 2018 Amortized Inference Regularization NIPS 2018 Streamlining Variational Inference for Constraint Satisfaction Problems NIPS 2018 Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance NIPS 2018 Constructing Unrestricted Adversarial Examples with Generative Models NIPS 2018 Learning Hierarchical Features from Deep Generative Models ICML 2017 InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations NIPS 2017 A-NICE-MC: Adversarial Training for MCMC NIPS 2017 Neural Variational Inference and Learning in Undirected Graphical Models NIPS 2017 Learning and Inference via Maximum Inner Product Search ICML 2016 Variational Bayes on Monte Carlo Steroids NIPS 2016 Tight Variational Bounds via Random Projections and I-Projections AISTATS 2016 Generative Adversarial Imitation Learning NIPS 2016 Solving Marginal MAP Problems with NP Oracles and Parity Constraints NIPS 2016 Adaptive Concentration Inequalities for Sequential Decision Problems NIPS 2016 Variable Elimination in the Fourier Domain ICML 2016 Beyond Parity Constraints: Fourier Analysis of Hash Functions for Inference ICML 2016 Model-Free Imitation Learning with Policy Optimization ICML 2016 A Hybrid Approach for Probabilistic Inference using Random Projections ICML 2015 Uncovering Hidden Structure through Parallel Problem Decomposition for the Set Basis Problem: Application to Materials Discovery IJCAI 2015 Low-density Parity Constraints for Hashing-Based Discrete Integration ICML 2014 Embed and Project: Discrete Sampling with Universal Hashing NIPS 2013 Taming the Curse of Dimensionality: Discrete Integration by Hashing and Optimization ICML 2013 Density Propagation and Improved Bounds on the Partition Function NIPS 2012 Accelerated Adaptive Markov Chain for Partition Function Computation NIPS 2011