Skip to main content
Search

Kunyu Zhang

1 related articles

Subscribe to updates
  1. arXiv

    Three-modality contrastive learning swaps its negatives: CHORD gains 21.2 points over the strongest baseline on samples that need all three modalities

    Higher-order objectives for three-modality contrastive learning are meant to capture information that appears only when all three modalities are seen together, but ordinary negatives are built by swapping modalities, so a single pairwise check rejects them and the higher-order term receives almost no gradient. CHORD instead draws decoy negatives from a calibrated pairwise model, negatives that model itself finds plausible, and trains a residual to separate them. On M3-Mix, where one in ten training samples needs all three modalities, CHORD improves accuracy on those samples by 21.2 percentage points over the strongest of eight baselines.

You’re all caught up