Paper Detail

OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning

Md Khairul Islam, Zeyu Xia, Adam S. Bolton, Judy Fox

huggingface Score 4.5

Published 2026-10-23 · First seen 2026-10-29

General AI

Abstract

Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed across heterogeneous instruments. We identify this coordinate mismatch as a structural limitation in cross-instrument representation learning, and propose OmniSpectra, a wavelength-native foundation model for spectral representation learning: a continuous-coordinate masked autoencoder that discards the integer pixel indexing of sequence modeling. Mapping physical coordinates to a logarithmic basis turns the multiplicative scaling induced by cosmological redshift into a uniform additive shift. In continuous rotary position embeddings, this shared shift cancels from relative token distances rather than producing grid-dependent positional distortion. We further counter the spectral bias inherent to implicit neural decoders with a physics-grounded, resolution-gated Fourier decoder that provides anti-aliasing. Pretrained on eight surveys and benchmarked against seven baselines, our model reaches state-of-the-art performance with only 12.2M parameters while outperforming substantially larger models, indicating that encoding physical structure can substitute for parameter scale.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{islam2026omnispectra,
  title = {OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning},
  author = {Md Khairul Islam and Zeyu Xia and Adam S. Bolton and Judy Fox},
  year = {2026},
  abstract = {Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed across heterogeneous instruments. We identify this coordinate mismatch as a structural limitation in cross-instrument representation learning, and propose OmniSpectra, a wavelength-native foundation model for spectral representation learning: a continuous-coordinate masked autoencoder that discards t},
  url = {https://huggingface.co/papers/2601.15351},
  keywords = {masked autoencoder, continuous-coordinate, rotary position embeddings, Fourier decoder, anti-aliasing, cosmological redshift, cross-instrument representation learning, spectral representation learning, huggingface daily},
  eprint = {2601.15351},
  archiveprefix = {arXiv},
}

Metadata

{}