Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences. However, application domains need to exert control over the generated data by steering the generative process - typica...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-10
Hauptverfasser:	Rector-Brooks, Jarrid, Mohsin Hasan, Peng, Zhangzhi, Quinn, Zachary, Liu, Chenghao, Mittal, Sarthak, Dziri, Nouha, Bronstein, Michael, Bengio, Yoshua, Chatterjee, Pranam, Tong, Alexander, Bose, Avishek Joey
Format:	Artikel
Sprache:	eng
Schlagworte:	Autoregressive models Diffusion barriers Modelling Noise reduction Probabilistic inference Proteins Steering
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!