activity
20242026
most citedAdjoint-Based Aerodynamic Shape Optimization with a Manifold Constraint Learned by Diffusion Models

1 citations · 3 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

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…

cs.LG2026

A Schrödinger Eigenfunction Method for Long-Horizon Stochastic Optimal Control

Louis Claeys, Artur Goldman, Zebang Shen +1

High-dimensional stochastic optimal control (SOC) becomes harder with longer planning horizons: existing methods scale linearly in the horizon , with performance often deteriora…

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…

cs.LG2025

Landing with the Score: Riemannian Optimization through Denoising

Andrey Kharitenko, Zebang Shen, Riccardo de Santi +2

Under the data manifold hypothesis, high-dimensional data are concentrated near a low-dimensional manifold. We study the problem of Riemannian optimization over such manifolds when…

cs.LG2025★ 1 cited

Provable Maximum Entropy Manifold Exploration via Diffusion Models

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

Exploration is critical for solving real-world decision-making problems such as scientific discovery, where the objective is to generate truly novel designs rather than mimic exist…