ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space

Published in Advances in Neural Information Processing Systems (NeurIPS), 2026

An earlier version of this work received an oral presentation at the ICML Workshop on Structured Probabilistic Inference and Generative Modeling (SPIGM), 2025.

arXiv:2604.27443

Recommended citation: Gabe Guo, Thanawat Sornwanee, Lutong Hao, Elon Litman, Stefano Ermon, and Jose Blanchet. (2026). "ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space." Advances in Neural Information Processing Systems (NeurIPS).
Download Paper