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

arXiv:2608.30376 · cs.CL, cs.LG · Submitted 2026-08-31 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: 12 pages, 3 figures. Paper 4 of the Kathleen series. Mechanism covered by U.S. Provisional Patent Application No. 64/140,260

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Transformer — 13× in this paper · explained in 2 episodes
• Provenance — 10× in this paper · explained in 4 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Generalization — 3× in this paper · explained in 13 episodes
• Associative Memory — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
• Neural Turing Machines
• Titans: Learning to Memorize at Test Time
• Memory Layers at Scale
• Kathleen: Oscillator-Based Byte-Level Text Classification Without Tokenization or Attention
• Kathleen Writes: Autoregressive Generation and Data Scaling Without Attention

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering