arXiv Machine Learning June 15, 2026 By Kazuhisa Nakasho

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

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 17

The Discrete-Log Clock: How a Transformer Learns Modular Multiplication

arXiv:2606. 17399v1 Announce Type: cross Abstract: When small transformers grok modular multiplication, prior work reports that the learned embedding has a "dense" Fourier spectrum requiring all frequencies.

By Huu Danh Nguyen (Stanford University)

llms rag

arXiv Machine Learning

Jul 9

FPTQuant: Function-Preserving Transforms for LLM Quantization

arXiv:2506. 04985v2 Announce Type: replace Abstract: Large language models (LLMs) require substantial compute, and thus energy, at inference time.

By Boris van Breugel, Yelysei Bondarenko, Paul Whatmough, Markus Nagel

llms efficiency benchmarks

arXiv AI

Jun 18

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

arXiv:2604. 13082v2 Announce Type: replace-cross Abstract: Grokking in transformers trained on algorithmic tasks is characterized by a long delay between training-set fit and abrupt generalization, but the source of that delay remains poorly understood.

By Laura Gomezjurado Gonzalez

llms safety

arXiv AI

Jul 15

Prime Fourier Embeddings: A Principled Basis for Modular Arithmetic

arXiv:2606. 23044v2 Announce Type: replace-cross Abstract: Numbers have algebraic structure that standard neural embeddings often fail to expose.

By Hyunsang Hwang, Suhyun Bae, Donghun Lee

rag benchmarks

arXiv Machine Learning

6d ago

CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models

arXiv:2608. 10010v2 Announce Type: replace Abstract: Low-precision formats usually optimize scalar fidelity while inheriting conventional product arithmetic.

By Ye Qiao

llms

arXiv Machine Learning

Jun 24

LLMs are Bayesian, In Expectation, Not in Realization

arXiv:2507. 11768v3 Announce Type: replace-cross Abstract: Bayesian accounts of in-context learning face a direct objection: exact posterior predictives for exchangeable data are invariant to task-preserving order, yet transformers change next-token probabilities when the same examples are serialized differently.

By Leon Chlon, Fatima Sheaib, Zein Khamis, Maggie Chlon, Mahdi El Zein, MarcAntonio M. Awada

llms benchmarks

Related stories

The Discrete-Log Clock: How a Transformer Learns Modular Multiplication

FPTQuant: Function-Preserving Transforms for LLM Quantization

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

Prime Fourier Embeddings: A Principled Basis for Modular Arithmetic

CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models

LLMs are Bayesian, In Expectation, Not in Realization