collaborators

7 papers

cs.LG2026

Support Before Frequency in Discrete Diffusion

Adrian Müller, Antoine Gonon, Zebang Shen +2

Discrete diffusion models are increasingly competitive for language modeling, yet it remains unclear how their denoising objectives organize learning. Although these objectives tar…

cs.LG2026

Manifold Generalization Provably Proceeds Memorization in Diffusion Models

Zebang Shen, Ya-Ping Hsieh, Niao He

Diffusion models often generate novel samples even when the learned score is only \emph{coarse} -- a phenomenon not accounted for by the standard view of diffusion training as dens…

stat.ML2026

When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis

Xiang Li, Zebang Shen, Ya-Ping Hsieh +1

Score-based methods, such as diffusion models and Bayesian inverse problems, are often interpreted as learning the data distribution in the low-noise limit (). In this wor…

cs.LG2026

Verifier-Constrained Flow Expansion for Discovery Beyond the Data

Riccardo De Santi, Kimon Protopapas, Ya-Ping Hsieh +1

Flow and diffusion models are typically pre-trained on limited available data (e.g., molecular samples), covering only a fraction of the valid design space (e.g., the full molecula…

cs.LG2026

A Unified Density Operator View of Flow Control and Merging

Riccardo De Santi, Malte Franke, Ya-Ping Hsieh +1

Recent progress in large-scale flow and diffusion models raised two fundamental algorithmic challenges: (i) control-based reward adaptation of pre-trained flows, and (ii) integrati…

cs.LG2025

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

Riccardo De Santi, Marin Vlastelica, Ya-Ping Hsieh +3

Adapting large-scale foundation flow and diffusion generative models to optimize task-specific objectives while preserving prior information is crucial for real-world applications…