Multiscreen replaces softmax attention with screening to provide absolute query-key relevance, resulting in models with 30% fewer parameters that maintain stable performance at long contexts.
Attention is all you need
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2roles
background 1polarities
background 1representative citing papers
A transformer meta-trained on a novel continuous-treatment data-generating prior reconstructs individual treatment-response curves from observational data via in-context learning and reports SOTA versus task-specific causal models.
citing papers explorer
-
Screening Is Enough
Multiscreen replaces softmax attention with screening to provide absolute query-key relevance, resulting in models with 30% fewer parameters that maintain stable performance at long contexts.
-
Causal Foundation Models with Continuous Treatments
A transformer meta-trained on a novel continuous-treatment data-generating prior reconstructs individual treatment-response curves from observational data via in-context learning and reports SOTA versus task-specific causal models.