PEARL: Personalized Streaming Video Understanding Model Paper • 2603.20422 • Published 5 days ago • 36
Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs Paper • 2510.24514 • Published Oct 28, 2025 • 22
Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks Paper • 2510.19195 • Published Oct 22, 2025 • 11