arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

2026-08-03 至 2026-08-03 共收录 92 信号源:cs.CL, cs.AI, cs.LG

1. 其他推理 16 篇

2603.06828 2026-08-03 cs.CV cs.AI 版本更新 57%

Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models

步级视觉 grounding 信念预测长视界视觉语言模型的分布外泛化

Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin, Abdullah Ibne Hanif Arean, Juena Ahmed Noshin

机构 * The KOW Company(KOW公司) University of Dhaka(达卡大学) American International University - Bangladesh (AIUB)(孟加拉国美国国际大学)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

AI总结 研究发现长视界视觉语言模型中,步级视觉接地信念预测分布外泛化能力,揭示了模型中间推理与视觉状态的一致性对鲁棒性的影响。

Comments Following the initial submission, we conducted additional experiments that materially changed our understanding of the problem. These new results do not support the central claim of the current manuscript. To avoid disseminating conclusions that we no longer consider adequately supported, we are withdrawing this version while we reassess the findings and prepare a substantially revised manuscript

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.03414 2026-08-03 q-bio.NC 版本更新 50%

Cognitive Dark Matter: Measuring What AI Misses

认知暗物质:测量AI所缺失的东西

Patrick J. Mineault, Thomas L. Griffiths, Sean Escola

专题命中 其他推理 :reasoning(abstract)

AI总结 本文提出认知暗物质概念,旨在通过测量AI缺失的认知功能提升模型的通用智能,同时促进对人类智能的理解。

Comments 15 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏