Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning Paper • 2410.12621 • Published Oct 16, 2024
LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation Paper • 2510.05367 • Published Oct 6 • 6
LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation Paper • 2510.05367 • Published Oct 6 • 6
DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 371