English(EN) Readable Is Not Steerable: Pre-Registered Tests of Physical Structure in Learned Fluid Representations

AI模型难以将潜在表示与物理控制联系起来

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

一篇新的研究论文探讨了自监督世界模型是否能有效地围绕物理量组织其潜在表示，并专门针对二维衰减的Navier-Stokes流进行了测试。研究发现，虽然一些模型能够表示涡量等流体量，但通过引导方向控制这些表示的能力有限，并且常常与其潜在内容脱节。该研究采用了预注册测试，并公开了所有代码和数据。 AI

影响探讨了AI在表示和控制物理现象方面的基本局限性，可能影响未来的模型开发。

排序理由研究论文，详细介绍了对AI模型表示的实验测试。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 26 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了对AI模型表示的实验测试。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Manvendra Modgil · 2026-11-05 05:00

可读性不等于可控性：学习到的流体表示中的物理结构预注册测试

arXiv:2611.05577v1 Announce Type: cross Abstract: Self-supervised world models are often said to organize their latents around physical quantities. We test this on 2D decaying Navier-Stokes flow in three pre-registered studies, each tested once on held-out data. In Study 1, a joi…