Adaptive gates in CLIP-style few-shot prompt learning often collapse due to gradient magnitude imbalance and gate degradation, failing to beat fixed prompts.
In response to reviewer concerns about training horizon, we additionally extended representative runs up to 10 epochs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Adaptation Fails: A Gradient-Based Diagnosis of Collapsed Gating in Vision-Language Prompt Learning
Adaptive gates in CLIP-style few-shot prompt learning often collapse due to gradient magnitude imbalance and gate degradation, failing to beat fixed prompts.