arXiv AI
1d ago
Where did the ambiguity go? Examining how multimodal models interpret polysemous words
arXiv:2608. 00410v2 Announce Type: replace Abstract: Human language is highly polysemous.
Billions of Sketches Reveal Hidden Cultural Variation in Human Concepts
Claims about the universality of human concepts have been predominantly assessed through linguistic similarity across languages and cultures. However, words are effective as communication devices because they compress rich experiential variation into shared conventions, potentially obscuring hidden individual and cultural differences in how concepts are mentally represented.
Related stories
arXiv AI
Jul 3
Psychological Imagination Networks Show Cross-Population Centrality and Clustering Alignment in Humans That Large Language Models Fail to Replicate
arXiv:2510. 04391v5 Announce Type: replace Abstract: Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relational structure across human and synthetic large language model (LLM) populations remains unknown.
arXiv AI
Jul 20
CAMMAR: Culture-Aware Matryoshka for Metaphorical Arabic Representations
arXiv:2607. 15847v1 Announce Type: cross Abstract: Metaphor in Arabic is a culturally grounded mechanism for constructing meaning, encoding cultural knowledge that shapes interpretation.
arXiv AI
Jul 21
What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?
arXiv:2607. 16214v1 Announce Type: cross Abstract: Image descriptions represented with language models (LMs) predict human brain responses to naturalistic images in high-level visual regions, but the factors driving this predictivity remain unclear.
arXiv AI
Jun 11
MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
arXiv:2602. 02465v2 Announce Type: replace Abstract: Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interleaved generation.
OpenAI Blog
Mar 4, 2021
Multimodal neurons in artificial neural networks
We’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step toward understanding the associations and biases that CLIP and similar models learn.
arXiv AI
Jun 12
LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
arXiv:2602. 00462v4 Announce Type: replace-cross Abstract: Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM.
arXiv AI
Aug 3
Seeing Differently: Modeling Interpretive Perspectives in Computational Creativity using a Four-World Framework
arXiv:2607. 28644v1 Announce Type: cross Abstract: Creativity in computational systems is often evaluated as an objective property of artifacts, with existing Computational Creativity (CC) frameworks assessing creative merit at the level of outputs or systems rather than interpretive context.
arXiv AI
Aug 5
Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models
arXiv:2603. 19087v2 Announce Type: replace Abstract: Creativity is the ability to come up with novel ideas, a capacity crucial for human development and flourishing.
arXiv AI
Jul 28
Embodied GPT-5.1: Evidence of a World Model?
arXiv:2607. 23899v1 Announce Type: cross Abstract: This exploratory study examines whether a large multimodal language model, GPT-5.
arXiv AI
Jul 14
Context-Dependent Affordance Computation in Vision-Language Models
arXiv:2603. 04419v2 Announce Type: replace-cross Abstract: We characterize the phenomenon of context-dependent affordance computation in vision-language models (VLMs).
arXiv AI
Jun 3
Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
arXiv:2604. 18572v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.