activity
20242026
collaborators

12 papers

math.DG2026

Stable Free Boundary Minimal Hypersurfaces in and

Han Hong, Yujie Wu

In this paper, we prove that there is no complete two-sided stable immersed free boundary minimal hypersurface in the closed Euclidean unit ball for .

cs.CV2026

Generative Manifold Distillation: Aligning Restoration Trajectories with Natural Image Prior

Yuyang Hu, Mojtaba Sahraee-Ardakan, Arpit Bansal +4

Pre-trained image restoration models often fail on out-of-distribution (OOD) real-world degradations. Adapting to these domains is challenging as real-world data lacks paired groun…

cs.LG2026

The Geometry of Noise: Why Diffusion Models Don't Need Noise Conditioning

Mojtaba Sahraee-Ardakan, Mauricio Delbracio, Peyman Milanfar

Autonomous (noise-agnostic) generative models, such as Equilibrium Matching and blind diffusion, challenge the standard paradigm by learning a single, time-invariant vector field t…

cs.CV2025

Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration

Yuyang Hu, Kangfu Mei, Mojtaba Sahraee-Ardakan +3

Diffusion models show promise for image restoration, but existing methods often struggle with inconsistent fidelity and undesirable artifacts. To address this, we introduce Kernel…

cs.LG2025

Learn to Guide Your Diffusion Model

Alexandre Galashov, Ashwini Pokle, Arnaud Doucet +3

Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining condi…

cs.CV2025

UniRes: Universal Image Restoration for Complex Degradations

Mo Zhou, Keren Ye, Mauricio Delbracio +3

Real-world image restoration is hampered by diverse degradations stemming from varying capture conditions, capture devices and post-processing pipelines. Existing works make improv…