Aligned but Stereotypical? The Hidden Influence of System Prompts on Social Bias in LVLM-Based Text-to-Image Models Paper • 2512.04981 • Published Dec 4, 2025 • 8
Multi-Objective Task-Aware Predictor for Image-Text Alignment Paper • 2510.00766 • Published Oct 1, 2025 • 2
World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models Paper • 2511.22787 • Published Nov 27, 2025 • 10
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning Paper • 2504.17192 • Published Apr 24, 2025 • 123
Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions Paper • 2503.13369 • Published Mar 17, 2025 • 7
ORPO: Monolithic Preference Optimization without Reference Model Paper • 2403.07691 • Published Mar 12, 2024 • 71
