Stefano Ermon

21

Papers

676

Total Citations

Papers (21)

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

HIVE: Harnessing Human Feedback for Instructional Visual Editing

Inductive Moment Matching

Energy-Based Diffusion Language Models for Text Generation

TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling

Personalized Preference Fine-tuning of Diffusion Models

Data Unlearning in Diffusion Models

Smooth Interpolation for Improved Discrete Graph Generative Models

Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution

Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints

CHORDS: Diffusion Sampling Accelerator with Multi-core Hierarchical ODE Solvers

Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

Large Language Models are Geographically Biased

State-Free Inference of State-Space Models: The Transfer Function Approach

Mechanistic Design and Scaling of Hybrid Architectures

Equivariant Graph Neural Operator for Modeling 3D Dynamics

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

On the Scalability of Diffusion-based Text-to-Image Generation

Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data

Diffusion Model Alignment Using Direct Preference Optimization