Pith. sign in

Siamese siren: Audio compression with implicit neural representations

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

What Cohort INRs Encode and Where to Freeze Them

cs.LG · 2026-05-08 · unverdicted · novelty 7.0

Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.

Implicit Neural Representations: A Signal Processing Perspective

cs.CV · 2026-04-16 · unverdicted · novelty 3.0

INRs parameterize signals as neural networks to enable continuous representations, analytical differentiation, and adaptive approximation spaces that address spectral bias through specialized activations and structured encodings.

citing papers explorer

Showing 2 of 2 citing papers.

  • What Cohort INRs Encode and Where to Freeze Them cs.LG · 2026-05-08 · unverdicted · none · ref 32

    Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.

  • Implicit Neural Representations: A Signal Processing Perspective cs.CV · 2026-04-16 · unverdicted · none · ref 29

    INRs parameterize signals as neural networks to enable continuous representations, analytical differentiation, and adaptive approximation spaces that address spectral bias through specialized activations and structured encodings.