Profiles2020-2026
Stefano Ermon
Department of Computer Science Stanford University
61Papers
39Last author
129Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers61
- Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive ModelsAuthor 2 of 2ICLR 2026
- Training-Free Safe Denoisers for Safe Use of Diffusion ModelsAuthor 4 of 6NeurIPS 2025 · 21 citations
- Data Unlearning in Diffusion ModelsAuthor 4 of 4ICLR 2025 · 2 citations
- Personalized Preference Fine-tuning of Diffusion ModelsAuthor 4 of 5CVPR 2025
- MADiff: Offline Multi-agent Learning with Diffusion ModelsAuthor 7 of 8NeurIPS 2024 · 116 citations
- Diffusion Model Alignment Using Direct Preference OptimizationAuthor 7 of 10CVPR 2024 · 89 citations
- Convolutional Differentiable Logic Gate NetworksAuthor 5 of 5NeurIPS 2024 · 58 citations
- Aligning Target-Aware Molecule Diffusion Models with Exact Energy OptimizationAuthor 9 of 11NeurIPS 2024 · 35 citations
- Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and EditingAuthor 6 of 7ICLR 2024 · 25 citations
- SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with BacktrackingAuthor 2 of 2ICLR 2024 · 17 citations
- Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal IterationsAuthor 3 of 3NeurIPS 2024 · 14 citations
- Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global EvolutionAuthor 4 of 5AAAI 2024 · 8 citations
- Newton Losses: Using Curvature Information for Learning with Differentiable AlgorithmsAuthor 6 of 6NeurIPS 2024 · 3 citations
- TrAct: Making First-layer Pre-Activations TrainableAuthor 3 of 3NeurIPS 2024
- UniControl: A Unified Diffusion Model for Controllable Visual Generation In the WildAuthor 12 of 14NeurIPS 2023 · 250 citations
- Parallel Sampling of Diffusion ModelsAuthor 3 of 5NeurIPS 2023 · 144 citations
- End-to-End Diffusion Latent Optimization Improves Classifier GuidanceAuthor 2 of 3ICCV 2023 · 118 citations
- Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution MatchingAuthor 5 of 5AAAI 2023 · 29 citations
- GlueGen: Plug and Play Multi-modal Encoders for X-to-image GenerationAuthor 6 of 9ICCV 2023 · 27 citations
- Calibration by Distribution Matching: Trainable Kernel Calibration MetricsAuthor 3 of 3NeurIPS 2023 · 21 citations
- Dual Diffusion Implicit Bridges for Image-to-Image TranslationAuthor 4 of 4ICLR 2023 · 13 citations
- Generative Modeling Helps Weak Supervision (and Vice Versa)Author 4 of 6ICLR 2023 · 1 citation
- On Distillation of Guided Diffusion ModelsAuthor 5 of 7CVPR 2023
- Denoising Diffusion Restoration ModelsAuthor 3 of 3NeurIPS 2022 · 1,439 citations
- Solving Inverse Problems in Medical Imaging with Score-Based Generative ModelsAuthor 4 of 4ICLR 2022 · 721 citations
- GeoDiff: A Geometric Diffusion Model for Molecular Conformation GenerationAuthor 5 of 6ICLR 2022 · 695 citations
- Concrete Score Matching: Generalized Score Matching for Discrete DataAuthor 4 of 4NeurIPS 2022 · 168 citations
- Training and Inference on Any-Order Autoregressive Models the Right WayAuthor 3 of 3NeurIPS 2022 · 68 citations
- An Experimental Design Perspective on Model-Based Reinforcement LearningAuthor 4 of 5ICLR 2022 · 24 citations
- Generalizing Bayesian Optimization with Decision-theoretic EntropiesAuthor 5 of 5NeurIPS 2022 · 15 citations
Showing the 30 most recent indexed papers.
