arXiv Machine Learning October 8, 2026 By Yi Fan, Vishnu Jejjala, Yang Lei

Machine learning modularity

Read the original on arXiv Machine Learning →

The paper introduces a transformer‑based sequence‑to‑sequence model with dynamic batching that automatically simplifies complex expressions involving multiple elliptic Gamma functions. It learns to apply algebraic identities, especially SL(2,ℤ) and SL(3,ℤ) modular transformations, to reduce scrambled expressions to canonical forms. Experiments show over 99% accuracy on in‑distribution tests and more than 90% accuracy under significant extrapolation, indicating the model internalizes the underlying algebraic rules rather than merely memorizing patterns.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Jun 2

BRo-JEPA: Learning Modular Arithmetic in Latent Space

arXiv:2606. 01372v1 Announce Type: cross Abstract: Can neural networks learn abstract algebraic rules, or do they merely memorize training patterns?

By Divyansh Jha, Yuanfang Xie, Varan Mehra, Brennen Yu

rag diffusion

arXiv AI

Aug 19

BRo-JEPA: Learning Modular Transformations in Latent Space

The paper introduces BRo-JEPA, a world model that learns modular arithmetic operations as rotations in latent space. Using MNIST and EMNIST datasets, BRo-JEPA achieves near-perfect zero‑shot generalization to unseen operations, outperforming standard supervised and JEPA baselines by a large margin. The model demonstrates that latent transformations can encode underlying algebraic structures, enabling strict zero‑shot operation generalization.

By Divyansh Jha, Yuanfang Xie, Brennen Yu, Varan Mehra

rag diffusion

arXiv Machine Learning

Jun 15

IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings

arXiv:2603. 05556v2 Announce Type: replace Abstract: Integer sequences in the OEIS span values from single-digit constants to astronomical factorials and exponentials, making prediction challenging for standard tokenised models that cannot handle out-of-vocabulary values or exploit periodic arithmetic structure.

By Kazuhisa Nakasho

llms rag benchmarks

arXiv AI

Jul 9

Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits

arXiv:2607. 07066v1 Announce Type: cross Abstract: Transformers have demonstrated a remarkable ability to learn algorithmic reasoning, yet mechanistic analyses have mostly focused on globally invertible operations such as cyclic addition and group composition.

By Zitong Andrew Chen, Junaid Hasan, Akhil Srinivasan, Hemkesh Bandi, Jarod Alper

llms rag

arXiv Machine Learning

Aug 13

A Theoretical Framework for Modular Learning of Robust Generative Models

arXiv:2602. 17554v3 Announce Type: replace Abstract: Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting.

By Corinna Cortes, Mehryar Mohri, Yutao Zhong

llms efficiency

arXiv Machine Learning

Jun 8

Discovering Multiscale Deep Formulas in Complex Systems via Neural-Guided Lambda Calculus

arXiv:2606. 07426v1 Announce Type: new Abstract: A fundamental problem in science is identifying underlying patterns of complex systems in the form of concise mathematical formulas.

By Hanqiao Yu, Shusen Yang, Xuebin Ren, Cong Zhao

benchmarks

One email a morning, machine-written

Related stories

BRo-JEPA: Learning Modular Arithmetic in Latent Space

BRo-JEPA: Learning Modular Transformations in Latent Space

IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings

Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits

A Theoretical Framework for Modular Learning of Robust Generative Models

Discovering Multiscale Deep Formulas in Complex Systems via Neural-Guided Lambda Calculus