view article Article NEO-unify: Building Native Multimodal Unified Models End to End 17 days ago • 102
CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding Paper • 2601.21262 • Published Jan 29
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 • 9
Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey Paper • 2412.02104 • Published Dec 3, 2024
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning Paper • 2502.02871 • Published Feb 5, 2025