Paper

PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift

Unreadunread

AI summary

arXiv:2605. 16351v1 Announce Type: new Abstract: Scientific foundation models are expected to reuse representations under changes in dataset, acquisition protocol, and deployment domain, yet many sequence backbones treat scientific temporal structure as an unconstrained pattern to be fitted.

Reading status

Priority

About this paper

Authors: Sangyoon Bae, Shinjae Yoo, Jiook Cha
Released: 2026-05-19 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift 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, under, alignment, source, project, without, trained, model. Source: arxiv cs.LG (Machine Learning).
arXiv: 2605.16351

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.