AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

TeMo: Temperature Modulation for Multimodal Contrastive Learning

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Contrastive learning approaches achieve strong performance by training models to bring similar samples closer while pushing dissimilar samples apart. A crucial component of contrastive learning is the temperature hyperparameter $τ$, which controls the penalty strength applied to negative samples. However, most existing methods either fix this hyperparameter or learn a global value during training. In this paper, we introduce TeMo, Temperature Modulation framework, a similarity-based modulation approach that adaptively adjusts the temperature for each positive-negative pair according to their s

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-20T20:32:20.942Z. This is not the publication date.