Paper

Memory by Design: Probabilistic Sequence Layers

Unreadunread

AI summary

arXiv:2605. 31163v1 Announce Type: new Abstract: We introduce the design-model framework: a way to derive efficient recurrent sequence maps from explicit assumptions about memory.

Reading status

Priority

About this paper

Authors: Matthew Dowling, Hyungju Jeon, Cristina Savin, Il Memming Park
Released: 2026-06-01 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because Memory by Design: Probabilistic Sequence Layers overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, rect, under, eval, line, control, propagate, trained. Source: arxiv stat.ML (Machine Learning).
arXiv: 2605.31163

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Memory by Design: Probabilistic Sequence Layers. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.