Research map / Probabilistic and scientific modeling / Dynamical systems
JEPAWG: Interpretable Hypernetworks for Weight-Space Physics
Tobias Göbel, Julian R Ebelt, Zier Mensch, Mathis Gerdes, Miranda Cheng
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes JEPAWG, an interpretable hypernetwork approach for weight-space physics on lattice field theory, using only the abstract's framing.
Problem
Lattice field theory coupling constants are weak predictors of physical observables, and extracting physics usually requires extensive simulation.
Approach
Uses interpretable hypernetworks operating in weight space to map bare coupling constants to physical observables, as suggested by the title; full method details are unavailable beyond the abstract.
Closest papers by meaning
- A Machine Learning Approach to Duality in Statistical Physics (ICML 2025 · similarity 0.85)
- From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability (NeurIPS 2026 · similarity 0.84)
- Learning the Electronic Hamiltonian of Large Atomic Structures (ICML 2025 · similarity 0.84)
- Cascade of phase transitions in the training of energy-based models (NeurIPS 2024 · similarity 0.84)
- From Neurons to Neutrons: A Case Study in Interpretability (ICML 2024 · similarity 0.83)
- Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
