K. Cui

collaborators

2 papers

cs.CV2026

The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models

Kelly Cui, Nikhil Prakash, Shoval Messica +4

Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations. Ye…

math.CO2020

Ulam Sets in New Settings

Tej Bade, Kelly Cui, Antoine Labelle +1

The classical Ulam sequence is defined recursively as follows: $a_{1} = 1$ , $a_{2} = 2$ , and $a_{n}$ , for $n > 2$ , is the smallest integer not already in the sequence that can be written uni…