TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment Paper • 2604.12012 • Published Apr 13 • 16
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents Paper • 2607.20709 • Published Jul 22 • 35
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Paper • 2607.21553 • Published Jul 23 • 39