CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving Paper • 2510.07944 • Published 11 days ago • 23
Trace Anything: Representing Any Video in 4D via Trajectory Fields Paper • 2510.13802 • Published 5 days ago • 30
PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts Paper • 2508.09848 • Published Aug 13 • 66
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding Paper • 2502.08946 • Published Feb 13 • 194