view article Article DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models 2 days ago • 30
reproducing-cross-encoders Collection A set of cross-encoders trained from various backbones and losses for equal comparison • 55 items • Updated Mar 5 • 4
TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation Paper • 2307.05134 • Published Jul 11, 2023 • 4