Signals 4 · free daily AI digest

The (Butter)fly Dream: Linear Separability of World-Model Rollouts in a Connectome-Constrained Visual Model

Paper recorded by Signals 4 on 2026-11-01 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-11-01 on arXiv · recorded by Signals 4 on 2026-11-03

Category: cs.LG · 机器学习 · first seen 2026-11-03

Abstract

Zhuangzi dreamt he was a butterfly and, on waking, could not tell which was the dream. We ask a version of his question of a model of the fly brain: placed inside a world generated by a world model, can a fixed brain tell that the world is a dream? We treat it as a question about what a connectome-constrained model trained on one task makes available beyond that task: do its responses make the def

Read on arXiv →

#40 most recent of 703 cs.LG papers we have recorded · ↑ newer: A Self-Generated Floor on Adam's $\varepsilon$: Evidence from Power-La · ↓ older: Quantizing Recurrent Language Models Is Easier Than You Think
Cite this page: The (Butter)fly Dream: Linear Separability of World-Model Rollouts in a Connectome-Constrained Visual Model: the #40 most recent of 703 cs.LG papers we have recorded (as of 2026-11-01). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/the-butter-fly-dream-linear-separability-of-world-model-rollouts-in-a-connectome.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions