Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning

First seen · 7/4/2026, 03:29 AMLatest activity · 7/4/2026, 03:29 AM

This paper introduces the Native Differentiable Virtual Machine (NDVM), a runtime representation for differentiating executable programs without compiling every candidate into a separate graph. Symbolic elements such as tags, environments, and control flow remain native runtime data, while numeric state is stored in dense batched buffers. Exact reverse-mode gradients are recorded along the realized execution trace. The authors report forward and gradient equivalence to a reference backend, roughly 60x per-lane batch amortization, near-linear multicore scaling, and approximately 24x faster attainment of high-quality solutions in fixed-budget co-search with LLM-proposed programs.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorarXiv7/4, 03:29 AMnot independentRepresentative
    Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning