Text-Only Inputs

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models

Vision-language models (VLMs) experience significant accuracy drops and severe miscalibration when operating with text-only inputs, even with preserved semantic information. The Latent Imagination Module (LIM) is proposed to predict imagined latent embeddings from text, improving accuracy and reducing calibration error in missing-image scenarios.