{
  "abstract": "Token aggregation converts token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original token space. We introduce Frequency-Domain Latent-attention Gated Pooling (FLaG), a plug-in aggregation module that re-expresses encoder outputs in the Fourier domain before final pooling. FLaG represents the nonredundant rFFT spectrum through concatenated real and imaginary components, summarizes spectral tokens with learnable latent queries, derives a sample-conditioned channel gate, and reconstructs modulated token representations for downstream aggregation. We evaluate the same architecture across ESM2-based antimicrobial peptide (AMP) activity prediction, ResNet18 image classification on CIFAR-10 and CIFAR-100, and three RoBERTa-based language tasks. FLaG achieves the best macro-averaged Spearman correlation coefficient, RMSE, and Recall@50 across four AMP backbone-species settings and the highest top-1 accuracy on CIFAR 10. It also achieves the best mean results on five of seven language metrics, although mean pooling remains strongest on STSBenchmark. AMP-side mechanistic analyses reveal low-frequency prediction sensitivity across most encoder layers, with increased relative high-frequency sensitivity in the final layer, and pronounced peptide-specific positional responses. The residual gate broadly amplifies spectral channels while preserving the low-frequency-dominated energy profile, whereas latent cross-attention exhibits sample- and species-specific spectral allocation. Overall, FLaG provides a transferable frequency-domain aggregation bias across protein, visual, and textual representations, with benefits that depend on the backbone and downstream task. Supplementary materials, source code, and data are available at https://www.healthinformaticslab.org/supp/ and https://github.com/Kewei2023/AMPCliff/tree/FLaG.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.00831",
  "author_total": 9,
  "authors": [
    {
      "name": "Kewei Li"
    },
    {
      "name": "Rongying Zhang"
    },
    {
      "name": "Xueli Wang"
    },
    {
      "name": "Xiwen Gong"
    },
    {
      "name": "Zhongjian Wang"
    },
    {
      "name": "Qiuchen Zhao"
    },
    {
      "name": "Lan Huang"
    },
    {
      "name": "Ruochi Zhang"
    },
    {
      "name": "Fengfeng Zhou"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/35fe8jtavv66x.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.00831",
  "fulltext_url": null,
  "id": "35fe8jtavv66x",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.00831",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ],
    [
      "openalex",
      "2404|Antimicrobial Peptides and Activities"
    ]
  ],
  "openalex": "W7206151835",
  "pdf_url": "https://arxiv.org/pdf/2609.00831",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/35fe8jtavv66x.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:05Z",
      "native_id": "2609.00831",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.00831"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    }
  ],
  "title": "FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation",
  "title_text": "FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:05Z",
  "url": "https://research.draconitic.com/paper/35fe8jtavv66x",
  "venue": "arXiv",
  "versions": []
}