8 papers
Rational Communication Shapes Morphological Composition
Fengyuan Yang, Yongqian Peng, Yuxi Ma +2
Human languages expand vocabularies by combining existing morphemes rather than inventing arbitrary forms. Communicative efficiency shapes lexical systems at multiple levels (Gibso…
Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
Yuxi Ma, Jieming Cui, Muyang Li +6
How people narrate their experiences offers a window into how the mind organizes them. Computational approaches to therapeutic writing have evolved from lexical counting to neural…
Grounding Before Generalizing: How AI Differs from Humans in Causal Transfer
Liangru Xiang, Yuxi Ma, Zhihao Cao +2
Extracting abstract causal structures and applying them to novel situations is a hallmark of human intelligence. While Large Language Models (LLMs) and Vision Language Models (VLMs…
NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation
Yuxi Ma, Yongqian Peng, Fengyuan Yang +5
Large Language Models show promise for AI-assisted storytelling, yet current tools often generate predictable, unoriginal narratives. To address this limitation, we present Narrati…
A simulation-heuristics dual-process model for intuitive physics
Shiqian Li, Yuxi Ma, Jiajun Yan +4
The role of mental simulation in human physical reasoning is widely acknowledged, but whether it is employed across scenarios with varying simulation costs and where its boundary l…
Probing and Inducing Combinational Creativity in Vision-Language Models
Yongqian Peng, Yuxi Ma, Mengmeng Wang +5
The ability to combine existing concepts into novel ideas stands as a fundamental hallmark of human intelligence. Recent advances in Vision-Language Models (VLMs) like GPT-4V and D…