Jianqiu Zhang

Concepts are central to cognition, yet existing theories remain divided on the problem of concept reference—how concepts connect to the entities they represent. Externalist accounts secure stability through causal-historical links but underplay context sensitivity and the role of reasoning. Inferentialist accounts explain flexibility through inferential roles but struggle with acquisition, holism, and maintaining identity across change. Prototype theories capture gradedness and typicality but fail to explain how reference remains stable as features shift or how concepts support pluralistic uses. This paper proposes the Inferential-Connection Mediated (ICM) model, which reconceives concepts as structured systems of inferential connections organized into two layers: referential anchors (RAs)—stored sets of connections that stabilize reference—and a broader inferential network that carries context-varying content. From the organizing principles of RAs, ICM derives a taxonomy of concept types (observational, anthropic, utilitarian, pure theoretical, hybrid theoretical) and a structural account of conceptual evolution, distinguishing changes to RAs (shifts, merges, splits, paradigm changes, dissolutions) from changes in the inferential network (enrichment, revision, category restructuring). By integrating stability and flexibility, ICM explains how concepts form, maintain identity, and evolve. It also offers a framework for situating and reconciling insights from existing theories while opening new directions in cognitive science, philosophy of science, and conceptual engineering.

Sora from Open AI has shown exceptional performance, yet it faces scrutiny over whether its technological prowess equates to an authentic comprehension of reality. Critics contend that it lacks a foundational grasp of the world, a deficiency V-JEPA from Meta aims to amend with its joint embedding approach. This debate is vital for steering the future direction of Artificial General Intelligence(AGI). We enrich this debate by developing a theory of productive imagination that generates a coherent world model based on Kantian philosophy. We identify three indispensable components in the coherent world model that enable genuine world understanding: latent representations of isolated objects, an a priori law of change across space and time, and Kantian categories. Our analysis reveals that Sora is limited because of its oversight of the a priori law of change and Kantian categories, flaws that are not rectifiable through scaling up the training. V-JEPA learns the context-dependent aspect of the a priori law of change. Yet it fails to fully comprehend Kantian categories and incorporate experience, leading us to conclude that neither system currently achieves a comprehensive world understanding. Nevertheless, each system has developed components essential to advancing an integrated AI productive imagination-understanding engine. Finally, we propose an innovative training framework for an AI productive imagination-understanding engine, centered around a joint embedding system designed to transform disordered perceptual input into a structured, coherent world model. Our philosophical analysis pinpoints critical challenges within contemporary video AI technologies and a pathway toward achieving an AI system capable of genuine world understanding, such that it can be applied for reasoning and planning in the future.

An accurate personality model is crucial to many research fields. Most personality models have been constructed using linear factor analysis. In this paper, we investigate if an effective deep learning tool for factor extraction, the Variational Autoencoder, can be applied to explore the factor structure of a set of personality variables. To compare VAE with LFA, we applied VAE to an International Personality Item Pool Big 5 dataset and an IPIP HEXACO dataset. We found that LFA tends to break factors into ever smaller, yet still significant fractions, when the number of assumed latent factors increases, leading to the need to organize personality variables at the factor level and then the facet level. On the other hand, the factor structure returned by VAE is very stable and VAE only adds noise-like factors after significant factors are found as the number of assumed latent factors increases. VAE reported more stable factors by elevating some facets in the HEXACO scale to the factor level. Since this is a data-driven process that exhausts all stable and significant factors that can be found, it is not necessary to further conduct facet level analysis and it is anticipated that VAE will have broad applications in exploratory factor analysis in personality research.