scalable-learning

Tag

Cards List
#scalable-learning

@ms_aifrontiers: Fara1.5 is here! The tech report just landed on arXiv. New SOTA for computer use agents of its size, and it competes wi…

X AI KOLs Following · 2026-06-24 Cached

Fara1.5 is a family of native computer use agents trained using the FaraGen1.5 scalable data pipeline. The models achieve new state-of-the-art results on browser-use benchmarks, competing with much larger frontier models.

0 favorites 0 likes
#scalable-learning

PE-MHL: Physics-Encoded Modular Hybrid Layers for Scalable Learning of Complex Systems

arXiv cs.LG · 2026-06-04

This paper proposes PE-MHL, a Physics-Encoded Modular Hybrid Layer framework that incrementally refines a physics-based model with data-driven sub-models, providing theoretical convergence guarantees and outperforming monolithic networks on control benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback