← Search

Jaebyeong Jeon

2 accepted papers

2026

Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining

CVPR 2026

Test-time prompt tuning (TPT) has emerged as a promising technique for enhancing the adaptability of vision-language models by optimizing textual prompts using unlabeled test data. However, prior studies have observed that TPT often produces poorly calibrated models, raising concerns about the relia

Cited by 1SourcecodeScholar
2025

Soft Task-Aware Routing of Experts for Equivariant Representation Learning

NeurIPS 2025poster

Equivariant representation learning aims to capture variations induced by input transformations in the representation space, whereas invariant representation learning encodes semantic information by disregarding such transformations. Recent studies have shown that jointly learning both types of repr…

Cited by 0SourcecodeScholar