Statistical Physics Meets Machine Learning II
ORAL · MAR-M63 · ID: MAR-M63
Presentations
-
Statistical Mechanics of Function Vectors
Oral-In-person
–
Presenters
-
Ravin Raj
- Princeton University
Authors
-
Ravin Raj
- Princeton University
-
Gautam Reddy
- Princeton University
-
-
Adaptively Guided Latent Diffusion for Time-Varying Inverse Problems in Particle Accelerators
Oral-In-person
–
Publication: A. Scheinker and A. Williams. "Latent diffusion can map beam loss to two-dimensional phase-space projections." Physical Review Accelerators and Beams 28.9 (2025): 094602. https://doi.org/10.1103/rqg9-g3dp
Presenters
-
Alexander Scheinker
- Los Alamos National Laboratory (LANL)
Authors
-
Alexander Scheinker
- Los Alamos National Laboratory (LANL)
-
-
Universality of LLM mechanisms across scale and diversity
Oral-In-person
–
Presenters
-
Lindsay Smith
- Princeton University
Authors
-
Lindsay Smith
- Princeton University
-
Gautam Reddy
- Princeton University
-
David Schwab
- The Graduate Center, City University of New York
-
-
Conditioning generative models without retraining: How to make a horse into a car
Oral-In-person
–
Presenters
-
Huan Souza
- Boston University
Authors
-
Huan Souza
- Boston University
-
Pankaj Mehta
- Boston University
-
-
Machine learning topological defect formation
Oral-In-person
–
Publication: arXiv:2508.20347
Presenters
-
Fumika Suzuki
- University of Tokyo ICEPP
Authors
-
Fumika Suzuki
- University of Tokyo ICEPP
-
Ying Wai Li
- Los Alamos National Laboratory
-
Wojciech Zurek
- Los Alamos Natl Lab
-
-
Inferring Low-rank Energy-based Models and the Renormalization Group
Oral-In-person
–
Presenters
-
Cheyne Weis
- University of Chicago
Authors
-
Cheyne Weis
- University of Chicago
-
Kyle Bojanek
- University of Chicago
-
Stephanie Palmer
- University of Chicago
-
Peter Littlewood
- University of Chicago
-
-
Bidirectional Nonlinear Optical Tomography: Unbiased Characterization of Off- and On-Chip Coupling Efficiencies
Oral-In-person
–
Publication: arXiv:2510.13110
Presenters
-
Bo-Han Wu
- University of Hawaii at Manoa
Authors
-
Bo-Han Wu
- University of Hawaii at Manoa
-
Mahmoud Jalali Mehrabad
-
Dirk Englund
-
-
Is Grokking a Computational Glass Relaxation?
Oral-In-person
–
Publication: [1] Yang, E., Zhang, X., Shang, Y., & Zhang, G. (2025). High-entropy Advantage in Neural Networks' Generalizability. arXiv:2503.13145. In Revision.
[2] Zhang, X., Shang, Y., Yang, E., & Zhang, G. (2025). Is Grokking a Computational Glass Relaxation? arXiv:2505.11411. Advances in Neural Information Processing Systems, 2025. (Accepted as Spotlight)Presenters
-
Entao Yang
- Air Liquide USA
Authors
-
Entao Yang
- Air Liquide USA
-
Xiaotian Zhang
-
Yue Shang
- University of Pennsylvania
-
Ge Zhang
- City Univ of Hong Kong
-
-
Statistical analysis of neural network structures for the Iris dataset
Oral-In-person
–
Presenters
-
Xiguang Yang
- University of Georgia
Authors
-
Xiguang Yang
- University of Georgia
-
Michael Bachmann
-
-
Exact solution of the frustrated Potts model with next-nearest-neighbor interactions in one dimension via AI bootstrapping
Oral-In-person
–
Publication: Weiguo Yin, Phys. Rev. B 112, 094424 (2025). DOI: https://doi.org/10.1103/y5vc-3t6q
Presenters
-
Weiguo Yin
- Brookhaven National Laboratory (BNL)
Authors
-
Weiguo Yin
- Brookhaven National Laboratory (BNL)
-
-
Semantic Chunking and the Entropy of Natural Language
Oral-In-person
–
Presenters
-
Weishun Zhong
- Institute for Advanced Study
Authors
-
Weishun Zhong
- Institute for Advanced Study
-
Tankut Can
-
Mikhail Katkov
-
Misha Tsodyks
-
-
Stochastic Resetting of Reinforcement Learning Agents
Oral-In-person
–
Presenters
-
Jello Zhou
- Stanford University
Authors
-
Jello Zhou
- Stanford University
-
David Schwab
- The Graduate Center, City University of New York
-
Wave Ngampruetikorn
-
-
Expressivity of first-order phase transitions
Oral-In-person
–
Presenters
-
Aditya Gandotra
- University of Chicago
Authors
-
Aditya Gandotra
- University of Chicago
-
Mason Rouches
- University of Chicago
-
Constantine Evans
-
Arvind Murugan
- University of Chicago
-
-
Learning Order: Can Neural Networks Discover Phase Transitions Without Symmetry Functions?
Oral-In-person
–
Publication: [1] Carina Karner "Variational autoencoders can detect phase signatures from raw trajectory data", in preparation, 2026
Presenters
-
Carina Karner
- Vienna University of Technology
Authors
-
Carina Karner
- Vienna University of Technology
-
-
Machine-Learning Characterization of Coarsening Dynamics in Fingerprint Labyrinthine Patterns
Oral-In-person · Withdrawn
–
Presenters
-
Supriyo Ghosh
Authors
-
Gia-Wei Chern
- University of Virginia
-
Supriyo Ghosh
-
Kotaro Shimizu
- The Univ. of Tokyo
-
Bellave Shivaram
- University of Virginia
-
Vinicius Okubo
-
Hae Kim
-