activity
20242026
collaborators

5 papers

cs.LG2026

Rethinking the Diffusion Model from a Langevin Perspective

Candi Zheng, Yuan Lan

Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically demanding mathematics that ca…

eess.IV2025

LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling

Candi Zheng, Yuan Lan, Yang Wang

Diffusion models excel at joint pixel sampling for image generation but lack efficient training-free methods for partial conditional sampling (e.g., inpainting with known pixels).…

physics.flu-dyn2025

Learning the Optimal Hydrodynamic Closure

Florian Kogelbauer, Candi Zheng, Ilya Karlin

We present the optimal hydrodynamic model for rarefied gas flows relative to a given kinetic model by combining the recent theory of slow spectral closure with machine learning tec…

cs.LG2024

Early Risk Assessment Model for ICA Timing Strategy in Unstable Angina Patients Using Multi-Modal Machine Learning

Candi Zheng, Kun Liu, Yang Wang +2

Background: Invasive coronary arteriography (ICA) is recognized as the gold standard for diagnosing cardiovascular diseases, including unstable angina (UA). The challenge lies in d…

cs.CV2024

Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale

Candi Zheng, Yuan Lan

Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this a…