Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation Paper • 2609.02864 • Published Sep 2 • 2
ChronoVision: Temporal Reasoning via Latent State Reconstruction Paper • 2608.05631 • Published Aug 6 • 40
Toward Cognitive Supersensing in Multimodal Large Language Model Paper • 2602.01541 • Published Feb 2 • 15