Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Contour Integration Underlies Human-Like Vision
Ben Lonnqvist, Elsa Scialom, Abdulkadir Gokce +3
Despite the tremendous success of deep learning in computer vision, models still fall behind humans in generalizing to new input distributions. Existing benchmarks do not investiga…
cs.CV2024
Dreaming Out Loud: A Self-Synthesis Approach For Training Vision-Language Models With Developmentally Plausible Data
Badr AlKhamissi, Yingtian Tang, Abdülkadir Gökce +2
While today's large language models exhibit impressive abilities in generating human-like text, they require massive amounts of data during training. We here take inspiration from…