ULPT optimizes prompts in ultra-low dimensions with frozen random up-projection to cut training parameters by 98% while matching vanilla prompt tuning performance on NLP tasks.
In: Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Earth embeddings from satellite images predict neighborhood-level urban indicators with higher accuracy for built-environment outcomes than for behavior-driven ones, showing city-specific variation but year-to-year stability.
citing papers explorer
-
Ultra-Low-Dimensional Prompt Tuning via Random Projection
ULPT optimizes prompts in ultra-low dimensions with frozen random up-projection to cut training parameters by 98% while matching vanilla prompt tuning performance on NLP tasks.
-
Earth Embeddings Reveal Diverse Urban Signals from Space
Earth embeddings from satellite images predict neighborhood-level urban indicators with higher accuracy for built-environment outcomes than for behavior-driven ones, showing city-specific variation but year-to-year stability.