paper-with-me

홈 › Papers

Kathleen: Oscillator-Based Byte-Level Text Classification Without Tokenization or Attention

2026-04-09 · George Fountzoulas arxiv

We present Kathleen, a text classification architecture that operates directly on raw UTF-8 bytes using frequency-domain processing -- requiring no tokenizer, no attention mechanism, and under 470K parameters. Kathleen introduces several novel components: (1) RecurrentOscillatorBanks -- damped sinusoid convolutions with temporal memory for O(L) sequence processing; (2) an FFT-Rotate Wavetable Encoder that maps all 256 byte values using a single learnable vector (256 floats); (3) PhaseHarmonics -- a sinusoidal non-linearity with just 6 learnable phase parameters (+2.6% accuracy, <0.001% of model parameters); (4) Content-Dependent Reverb with Positional Decay Modulation -- a temporal memory mechanism whose decay rate is jointly conditioned on input content and a learned position-indexed bias vector; (5) Token-Level Module Sequencer with consonance and dissonance interference channels. Through iterative architecture evolution from an initial 733K-parameter baseline (Kathleen-Clean) to the current Kathleen-V9 (469K parameters), we demonstrate that pretraining can be entirely eliminated while improving accuracy. Kathleen-V9 achieves 88.5% +/- 0.2% on IMDB, 92.4% +/- 0.2% on AG News, and 85.8% +/- 0.5% on SST-2 (3-seed averages) -- matching or exceeding the pretrained baseline on all benchmarks with 36% fewer parameters. On SST-2, the improvement is +2.5% absolute over the pretrained predecessor. Kathleen processes sequences in O(L) time and memory.

📄 PDF Abstract BibTeX arXiv:2604.07969

Code (0)

등록된 구현이 없습니다.

Tasks

Text Classification

Results from the Paper

RankTaskDatasetModelMetrics
#4 Classification SST-2 Kathleen Test Accuracy: 85.8
#2 Text Classification SST-2 Kathleen Accuracy: 92.4

Similar Papers 제목 키워드 기반

Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention

2026-08-31 · George Fountzoulas arxiv

Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the past. We add to the Kathleen trunk a second memory layer -- a "notebook…

byteSteady: Fast Classification Using Byte-Level n-Gram Embeddings

2021-06-24 · Xiang Zhang, Alexandre Drouin, Raymond Li

This article introduces byteSteady -- a fast model for classification using byte-level n-gram embeddings. byteSteady assumes that each input comes as a sequence of bytes. A representation vector is produced using the ave…

Classificationtext-classificationText Classification

ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives

2024-10-28 · Wenyang Liu, Kejun Wu, Tianyi Liu, Yi Wang 외

Multimedia file fragment classification (MFFC) aims to identify file fragment types, e.g., image/video, audio, and text without system metadata. It is of vital importance in multimedia storage and communication. Existing…

Which Encoding is the Best for Text Classification in Chinese, English, Japanese and Korean?

2017-08-08 · Xiang Zhang, Yann Lecun

This article offers an empirical study on the different ways of encoding Chinese, Japanese, Korean (CJK) and English languages for text classification. Different encoding levels are studied, including UTF-8 bytes, charac…

General ClassificationText Classification

MambaNetBurst: Direct Byte-level Network Traffic Classification without Tokenization or Pretraining

2026-05-11 · Gayan K. Kulatilleke, Siamak Layeghy, Mahsa Baktashmotlagh, Marius Portmann arxiv

We present MambaNetBurst, a compact tokenizer-free byte-level sequence classifier for network burst classification based on a Mamba-2 backbone. In contrast to most recent strong traffic-classification and intrusion-detec…