MapFormers learn cognitive maps via input-dependent Lie-algebra positional encodings and achieve near-perfect OOD generalization on cognitive tasks where standard transformers fail.
Right for the wrong reasons: Diagnosing syn- tactic heuristics in natural language inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MapFormer: Self-Supervised Learning of Cognitive Maps with Input-Dependent Positional Embeddings
MapFormers learn cognitive maps via input-dependent Lie-algebra positional encodings and achieve near-perfect OOD generalization on cognitive tasks where standard transformers fail.