Phantom: Subject-consistent video generation via cross-modal alignment Paper • 2502.11079 • Published 4 days ago • 44
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU Paper • 2502.08910 • Published 7 days ago • 136
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding Paper • 2502.08946 • Published 7 days ago • 179