arXiv Machine Learning By Yusuke Matsui, Tatsuya Yokota

Broadcast Product: Redefining Shape-aligned Element-wise Multiplication and Beyond

Read the original on arXiv Machine Learning →

arXiv:2409. 17502v2 Announce Type: replace Abstract: Broadcast operations are widely used in scientific computing libraries, yet their mathematical formulation is often implicit and inconsistently represented in machine learning literature.

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

arXiv AI
Jul 10

Multi-agent Autoformalization of Tensor Network Theory

arXiv:2607. 07857v1 Announce Type: cross Abstract: We build a team of specialized large language-model agents and present an agent-driven workflow for research-level formalization in theoretical physics, with the autoformalization of the fundamental theorem of matrix-product states as a demonstration.

By Sirui Lu, Erickson Tjoa, J. Ignacio Cirac