2019 · Generative models
Generative Modeling by Estimating Gradients of the Data Distribution
Score-based generation learns directions that move noisy samples toward the distribution of real data.
Paper & contextStefano Ermon
Connecting probabilistic modeling, optimization, and generation.
Ermon’s research connects probabilistic inference, optimization, and generative learning. These papers include score-based models and methods for making learning and inference more efficient, with applications that range across scientific and language tasks.
Selected work
10 papers
2020 · Generative models
Score-Based Generative Modeling through Stochastic Differential Equations
This paper unifies score-based generative methods through a continuous process that adds noise and a learned process that reverses it.
Paper & context2023 · Alignment
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Direct Preference Optimization derives a preference-learning objective that avoids training a separate reward model in the studied setup.
Paper & context2022 · Chips
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
FlashAttention reorganizes attention computation to reduce costly reads and writes between GPU memory levels.
Paper & context2022 · Benchmarks
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench collects a broad set of language-model evaluation tasks to study capabilities and limitations beyond a single benchmark.
Paper & context2026 · Generative models
There and Back Again: Bidirectional Diffusion Bridges for Multimodality Translation
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Generative models
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Generative models
Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Generative models
Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Generative models
Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources