arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2607.08196cs.AIcs.CLcs.LG

慢思考与主动感知的第一性原理理论

A First-Principles Theory of Slow Thinking and Active Perception

MemTensor (Shanghai) Technology Co., Ltd.(忆张量(上海)科技有限公司);Institute for Advanced Algorithms Research, Shanghai(上海高等算法研究院);Shanghai JiaoTong University(上海交通大学);Peking University(北京大学)

Hongkang Yang, Zhi-Qin John Xu, Feiyu Xiong, Weinan E

AI总结:

本文旨在为思维和感知提供数学公式,提出“主动提升”理论,推导慢思考相关内容,涵盖其设计、训练和推理,得出大设计空间及相关层次,还包括推理过程、训练目标等,有诸多技术副产品。

摘要:

作为认知功能第一性原理建模系列的一部分,本文尝试为思维和感知提供数学公式。正式推导了慢思考或更广义的主动感知,涵盖慢思考大语言模型的设计、训练和推理。从概率分布在可观测和潜在空间的提升与投影出发,提出“主动提升”理论,基于潜在序列采样和以最大速率降低不确定性的内在驱动力。得出一个大的设计空间,包含慢思考模型,这些模型可在静态理论诱导的表示层次和采样层次上定位并升级。还推导了带有内部时间轴的推理过程和类似最小长度编码及语言发明的训练目标,刻画了感知的能动性,包括慢思考形式的出现。该理论的技术副产品包括改进慢思考模型的三阶段途径、构建所有数据模态的编码器和生成模型的统一方法、类人视觉表征的先验形成以及政策崩溃的可能解决方案。

英文摘要:

As part of a series on first-principles modeling of cognitive functions, this paper attempts to provide a mathematical formulation of thinking and perception. It formally derives slow thinking or more generally, active perception, and encompasses the design, training and inference of slow thinking large language models. Our starting point is the lifting and projection of probability distributions on the observable and latent spaces, with the objective of representing complex data distributions by simple function families such as neural networks. A theory called "active lifting" is proposed, based on the sampling of latent sequences and an intrinsic drive to reduce uncertainty with maximum rate. It derives a large design space, containing the slow thinking models in a subspace that we call the static theory. These models are positioned on the representation hierarchy and sampler hierarchy induced by the static theory, and can be upgraded by climbing the two hierarchies. Active lifting further derives an inference process with an internal time axis, and a training objective that resembles minimum-length coding as well as the invention of languages. Thus, it characterizes the agency of perception, including the emergence of the slow thinking formats. Technical by-products of this theory include a three-stage pathway for improving slow thinking models, a unified approach to constructing encoders and generative models for all data modalities, a priori formation of human-like visual representations, and a possible solution to policy collapse.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑