4 papers
Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation
Maan Qraitem, Kate Saenko, Bryan A. Plummer
Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underexplored. We identify two alignmen…
Web Artifact Attacks Disrupt Vision Language Models
Maan Qraitem, Piotr Teterwak, Kate Saenko +1
Vision-language models (VLMs) (e.g. CLIP, LLaVA) are trained on large-scale, lightly curated web datasets, leading them to learn unintended correlations between semantic concepts a…
KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models
Eunice Yiu, Maan Qraitem, Anisa Noor Majhi +5
This paper investigates visual analogical reasoning in large multimodal models (LMMs) compared to human adults and children. A "visual analogy" is an abstract rule inferred from on…
SLANT: Spurious Logo ANalysis Toolkit
Maan Qraitem, Piotr Teterwak, Kate Saenko +1
Online content is filled with logos, from ads and social media posts to website branding and product placements. Consequently, these logos are prevalent in the extensive web-scrape…