Test-Time Prompt Tuning
PulseAugur coverage of Test-Time Prompt Tuning — every cluster mentioning Test-Time Prompt Tuning across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New method CoTS improves AI model calibration without sacrificing accuracy
Researchers have developed CoTS, a new post-hoc calibration method for test-time prompt tuning (TPT) that aims to improve accuracy without sacrificing calibration. CoTS applies temperature scaling to reduce the confiden…
-
New TPT Method Improves AI Model Calibration and Accuracy
Researchers have identified a limitation in test-time prompt tuning (TPT) methods that rely on entropy minimization, noting that these approaches can lead to overconfident predictions and degraded model calibration. To …
-
New framework unifies self-ensembling for test-time prompt tuning
Researchers have introduced USE, a unified self-ensembling framework designed to enhance test-time adaptation for vision-language models like CLIP. This framework interprets test-time prompt tuning as learning from self…