Lisa Dunlap

5

Papers

392

Total Citations

Papers (5)

From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline

Describing Differences in Image Sets with Natural Language

VisionArena: 230k Real World User-VLM Conversations with Preference Labels

Discovering Divergent Representations between Text-to-Image Models

See Say and Segment: Teaching LMMs to Overcome False Premises