Stefano Ermon
4 papers · Latest:
One-Step Generative Modeling via Wasserstein Gradient Flows
W-Flow introduces a novel one-step generative model using Wasserstein gradient flows, achieving state-of-the-art image generation 100x faster than diffusion models.
Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics
A new framework uses structure pretraining and diffusion models to generate realistic molecular dynamics trajectories, overcoming data scarcity.
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
This paper introduces Score Entropy, a novel loss function that extends score matching to discrete data, enabling discrete diffusion models that outperform existing language diffusion methods and rival autoregressive models like GPT-2.
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
FlashAttention is an IO-aware exact attention algorithm that significantly speeds up Transformer training and enables longer context lengths by optimizing GPU memory access patterns.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.