activity
20242026
collaborators

8 papers

cs.CL2026

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…

cs.CL2026

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…

cs.AI2026

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…

cs.HC2026

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…

physics.ed-ph2025

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…

cs.CV2025

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…