Paper

Two-Layer Linear Auto-Regressive Models Estimate Latent States

Unreadunread

AI summary

arXiv:2606. 12691v1 Announce Type: cross Abstract: Auto-regressive models have emerged as powerful tools for sequential data, from language to video.

Reading status

Priority

About this paper

Authors: Yahya Sattar, Sunmook Choi, Leo Maynard-Zhang, Yassir Jedra, Maryam Fazel, Sarah Dean
Released: 2026-06-12 (27d ago)
Topic: Related to current project
Relation to my work: Read next because Two-Layer Linear Auto-Regressive Models Estimate Latent States overlaps with 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)", clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)", experiment "Follow-up to #354: cascading chunk-binding — does A→B, B→C, C→D propagate the full chain on a recipient trained only to emit A?". Matching terms: under, line, rate, trained, language, model. Source: arxiv stat.ML (Machine Learning).
arXiv: 2606.12691

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Two-Layer Linear Auto-Regressive Models Estimate Latent States. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.