Pub-AI.AI in Science
Search Pub-AIStart Here

Publication Radar · Source metadata

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak

Publication record

Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.

First public release: 2025-10-06 · Indexed by Pub-AI: 2026-10-25 UTC

conferenceInternational Conference on Machine Learning2025 · main

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models

Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak

Published online: 2025-10-06 · Original record ↗

  1. Proceedings published

    Source date: 2025-10-06 · First detected: 2026-10-25 UTC · Historical baseline

    Source evidence (1)

Browse publicationsSource coverageMatching and dates

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models | Pub-AI Radar