learned-execution

Tag

Cards List
#learned-execution

A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution

arXiv cs.AI · 2026-07-14 Cached

This paper introduces a trace-supervised symbolic neural CPU architecture that combines recurrent control, an explicit operation router, and masked register writeback to enable auditable, interpretable program execution, with quantization-simulated writeback preserving symbolic operation paths.

0 favorites 0 likes
← Back to home

Submit Feedback