Aesthetic Alignment Risks Assimilation: How Image Generation and Reward Models Reinforce Beauty Bias and Ideological "Censorship" Paper • 2512.11883 • Published 17 days ago • 6
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models Paper • 2504.10479 • Published Apr 14 • 306
Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference Paper • 2508.04586 • Published Aug 6 • 12
TIIF-Bench: How Does Your T2I Model Follow Your Instructions? Paper • 2506.02161 • Published Jun 2 • 13
TIIF-Bench: How Does Your T2I Model Follow Your Instructions? Paper • 2506.02161 • Published Jun 2 • 13