思维语言假说（Language of Thought Hypothesis）认为，人类认知基于一套结构化的、类语言的心理表征系统运作。虽然神经语言模型可以天然地从语言数据中内在且明确表达的组合结构中获益，但从非语言的一般观测（如图像）中学习此类表征仍是一项挑战。在本研究中，我们提出了思维模型的神经语言（Neural Language of Thought Model，NLoTM），这是一种受LoTH启发的无监督表征学习与生成新方法。NLoTM包含两个核心组件：（1）语义向量量化变分自编码器（Semantic Vector-Quantized Variational Autoencoder），用于学习与物体及其属性对齐的分层、可组合离散表征；（2）自回归LoT先验（Autoregressive LoT Prior），这是一种自回归transformer，学习以组合方式生成语义概念token，捕捉底层数据分布。我们在多个2D和3D图像数据集上评估了NLoTM，结果表明，与基于patch的VQ-VAE和连续的以物体为中心的表征相比，NLoTM在下游任务、分布外泛化和图像生成质量方面表现更优。本研究通过开发类LoT的表征，朝着构建具备更类人理解能力的神经网络迈出了重要一步，也为认知科学与机器学习的交叉领域提供了洞见。
英文摘要：
The Language of Thought Hypothesis suggests that human cognition operates on a structured, language-like system of mental representations. While neural language models can naturally benefit from the compositional structure inherently and explicitly expressed in language data, learning such representations from non-linguistic general observations, like images, remains a challenge. In this work, we introduce the Neural Language of Thought Model (NLoTM), a novel approach for unsupervised learning of LoTH-inspired representation and generation. NLoTM comprises two key components: (1) the Semantic Vector-Quantized Variational Autoencoder, which learns hierarchical, composable discrete representations aligned with objects and their properties, and (2) the Autoregressive LoT Prior, an autoregressive transformer that learns to generate semantic concept tokens compositionally, capturing the underlying data distribution. We evaluate NLoTM on several 2D and 3D image datasets, demonstrating superior performance in downstream tasks, out-of-distribution generalization, and image generation quality compared to patch-based VQ-VAE and continuous object-centric representations. Our work presents a significant step towards creating neural networks exhibiting more human-like understanding by developing LoT-like representations and offers insights into the intersection of cognitive science and machine learning.
Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models
John F Kennedy High school Fremont, USA（约翰·F·肯尼迪高中弗里蒙特分校）；Queensland Academy for Science Mathematics and Technology（昆士兰科学数学与技术学院）；Research Spark Hub Inc（Research Spark Hub公司）
On the Thinking-Language Modeling Gap in Large Language Models
Hong Kong Baptist University（香港 Baptist 大学）；MBZUAI Carnegie Mellon University（MBZUAI 美国卡内基梅隆大学）；The University of Sydney（悉尼大学）；The Chinese University of Hong Kong（香港中文大学）
School of Civil and Environmental Engineering（土木与环境工程学院）；Cornell University（康奈尔大学）；Department of Physics（物理系）；Department of Mathematics（数学系）；Imperial College London（伦敦帝国理工学院）；Center for Applied Mathematics（应用数学中心）
