Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions

Geonho Hwang, Yeachan Park, Wonyeol Lee, Sejun Park
2/14/2026

No confident code implementation found for this paper. 1 possible match can be shown below.

Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Enhancing Human-AI Collaboration Through Logic-Guided Reasoning

100% match2026

Energy-Efficient Gaussian Processes Using Low-Precision Arithmetic

100% match2026

Complete-Tree Space Favors Data-Efficient Link Prediction

99% match2026

Reliable Spatial-Temporal Voxels For Multi-Modal Test-Time Adaptation

99% match1 repo192026

Speech Self-Supervised Learning Using Diffusion Model Synthetic Data

99% match2026

Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds

99% match1 repo72026

Cite this paper

@article{hwang2026floatingpoint,
  title  = {Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions},
  author = {Geonho Hwang and Yeachan Park and Wonyeol Lee and Sejun Park},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:59d890534118e1210f6ef0ad7535c38e70df44f5},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/59d890534118e1210f6ef0ad7535c38e70df44f5.svg)](https://codeofpaper.com/paper/59d890534118e1210f6ef0ad7535c38e70df44f5)

Discussion