energy-based models 1image classification 1random bond ising model 1sparse graphs 1spectral embedding 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification
V. S. Usatyuk, D. A. Sapozhnikov, S. I. Egorov
The paper proposes Kohn‑Sham Spectral Embedding (KSSE), a physics‑inspired, sparse‑graph spectral method that replaces dense CNN classifiers with a regularized Laplacian evaluated…
cs.LG2026
Diffusion-Guided Feature Selection via Nishimori Temperature: Noise-Based Spectral Embedding
Vasiliy S. Usatyuk, Denis A. Sapozhnikov, Sergey I. Egorov
We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without greedy search. NBSE constructs…
cs.CV2025
Synthetic Image Detection via Spectral Gaps of QC-RBIM Nishimori Bethe-Hessian Operators
V. S. Usatyuk, D. A. Sapozhnikov, S. I. Egorov
The rapid advance of deep generative models such as GANs and diffusion networks now produces images that are virtually indistinguishable from genuine photographs, undermining media…