Softmax Transformers implement in-context RL through equivalence to weighted softmax TD updates, with error decay under contraction and parameters as global minimizers of pretraining loss.
Advances in neural information processing systems , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Random team assignments in a professional firm reveal that indirect ties strongly increase new direct tie formation, while effects of degree and local density are smaller and less robust.
citing papers explorer
-
Beyond Linear Attention: Softmax Transformers Implement In-Context Reinforcement Learning
Softmax Transformers implement in-context RL through equivalence to weighted softmax TD updates, with error decay under contraction and parameters as global minimizers of pretraining loss.
-
Causal inference for social network formation
Random team assignments in a professional firm reveal that indirect ties strongly increase new direct tie formation, while effects of degree and local density are smaller and less robust.