Statistical Physics Meets Machine Learning I
ORAL · MAR-L63 · ID: 3995647
Presentations
-
Evolution of Language Statistics under Renormalization Group Flow
ORAL
–
Presenters
-
Roberto E Avalos
- Emory University
Authors
-
Roberto E Avalos
- Emory University
-
Tankut Can
- Emory University
-
-
Compression in Neural Networks via Weight Coupling
ORAL
–
Publication: Quantization and the Bottom of the Loss Landscape (ICML workshop paper); Neural Network Quantization via Weight-Weight Coupling (planned paper)
Presenters
-
Daniel T Bernstein
- Princeton University
Authors
-
Daniel T Bernstein
- Princeton University
-
Luca Di Carlo
- Princeton University
-
David J Schwab
- The Graduate Center, City University of New York
-
-
Building effective shallow generative models through side information
ORAL
–
Presenters
-
Kyle Bojanek
- University of Chicago
Authors
-
Kyle Bojanek
- University of Chicago
-
Stephanie E Palmer
- University of Chicago
-
-
Implementation of Kolmogorov Flow Matching in a GFlowNet Learning Model
ORAL
–
Presenters
-
Sergio Cuadra
- University of Massachusetts Boston
Authors
-
Sergio Cuadra
- University of Massachusetts Boston
-
Sho Inaba
- Department of Physics, Universtiy of Massachusetts Boston
- University of Massachusetts Boston
-
Jacob Adamczyk
- University of Massachusetts Boston
-
Rahul V Kulkarni
- Department of Physics, University of Massachusetts Boston
- University of Massachusetts Boston
-
-
Combinatorial Reasoning: Using physics-inspired methods to improve reasoning on generative language models
ORAL
–
Publication: [1] M. Esencan et al., "Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization," arXiv:2407.00071 (2024)
Presenters
-
Mert Esencan
- Icosa Computing
Authors
-
Mert Esencan
- Icosa Computing
-
Davide Venturelli
- USRA and NASA Ames Research Center
-
Can Unlu
- Icosa Computing
-
Tarun Advaith Kumar
- Icosa Computing
-
Alan Ho
- Icosa Computing
-
-
The geometry and dynamics of annealed optimization in the coherent Ising machine with hidden and planted solutions
ORAL
–
Presenters
-
Federico Ghimenti
- Stanford University
Authors
-
Federico Ghimenti
- Stanford University
-
Adithya Sriram
- Stanford University
-
Atsushi Yamamura
- Stanford University
-
Hideo Mabuchi
- Stanford University
-
Surya Ganguli
- Stanford University
-
-
Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
ORAL
–
Publication: Submitted to ICLR 2026
Presenters
-
Chase W Goddard
- Princeton University
Authors
-
Chase W Goddard
- Princeton University
-
Luca Di Carlo
- Princeton University
-
David J Schwab
- The Graduate Center, City University of New York
-
-
Tokenization gauge symmetry in language modeling
ORAL
–
Presenters
-
Kanishk Jain
- Emory University
Authors
-
Kanishk Jain
- Emory University
-
Matthew Day
- Emory University
-
Tankut Can
- Emory University
-
-
EVE: EigenVector-Based Exploration
ORAL
–
Publication: EVE: EigenVector-Based Exploration (paper)
Presenters
-
Adam Kamoski
- University of Massachusetts Boston
Authors
-
Adam Kamoski
- University of Massachusetts Boston
-
Rahul V Kulkarni
- Department of Physics, University of Massachusetts Boston
- University of Massachusetts Boston
-
Sho Inaba
- Department of Physics, Universtiy of Massachusetts Boston
- University of Massachusetts Boston
-
Jacob Adamczyk
- University of Massachusetts Boston
-
-
Scattering-based Optical Computing
ORAL
–
Presenters
-
Wolfgang Losert
- University of Maryland College Park
Authors
-
Eunji Ko
- University of Maryland College Park
-
Wolfgang Losert
- University of Maryland College Park
-
-
Abstract Withdrawn
ORAL · Withdrawn
–
-
Local Diffusion Models and Phases of Data Distributions
ORAL
–
Publication: Preprint: arXiv:2508.06614
Presenters
-
Guangkuo Liu
- JILA
Authors
-
Guangkuo Liu
- JILA
-
Fangjun Hu
- QuEra Computing Inc.
- QuEra Computing
-
Yifan (Frank) Zhang
- Princeton University
-
Xun Gao
- University of Colorado
- JILA
- University of Colorado Boulder
-
-
Large Language Models Think in Curved Space
ORAL
–
Presenters
-
Toni Jianbang Liu
- Cornell University
Authors
-
Toni Jianbang Liu
- Cornell University
-
Raphael Sarfati
- University of Colorado, Boulder
-
Nicolas Boulle
- Imperial College London
-
Christopher Earls
- Cornell University
-
-
Data coarse graining can improve model performance
ORAL
–
Publication: A. Nguyen, D. J. Schwab, and V. Ngampruetikorn, arXiv:2509.14498 [cond-mat.stat-mech]
Presenters
-
Vudtiwat Ngampruetikorn
- The University of Sydney
Authors
-
Alex Nguyen
- Princeton University
-
David J Schwab
- The Graduate Center, City University of New York
-
Vudtiwat Ngampruetikorn
- The University of Sydney
-
-
Variational Inference with Heavy-Tailed Distributions using the Coupled Free Energy
ORAL
–
Publication: Nelson, K., Oliveira, I., Al-Najafi, A., Zhang, F., & Ng, H. K. T. (2025, July 25). Variational inference optimized using the curved geometry of coupled free energy (arXiv:2506.09091). arXiv. https://doi.org/10.48550/arXiv.2506.09091
Nelson, K. P. (2025, August 9). Coupled entropy: A Goldilocks generalization for complex systems (arXiv:2506.17229). arXiv. https://arxiv.org/abs/2506.17229Presenters
-
Igor Gomes Oliveira
- Photrek
Authors
-
Igor Gomes Oliveira
- Photrek
-
Kenric P Nelson
- Photrek
-
Amenah A Najaf
- Department of Mathematics, University of Kufa, 299G, Najaf, Iraq
-