SOURCE-LINKED INTELLIGENCE

TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Prompt learning adapts vision-language models, such as CLIP, by adjusting a small set of context tokens. However, under few-shot supervision, even moderate label noise can disrupt prompt optimization. To address this issue, we propose TecoPrompt, a closed-loop robust prompt-learning framework that revisits optimal transport (OT) pseudo-labeling from a temporal perspective. TecoPrompt employs an entropic OT plan in the CLIP semantic space to obtain globally consistent label candidates. It verifies the reliability of these candidates by examining trajectory stability: a noisy label is only rewri

Read original source ↗ Open in workspace

recordType

paper

region

Global