A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention

Oct-10-2025, 00:21:36 GMT–Neural Information Processing Systems

Such investigations have demonstrated that attention layers are able to implement a wide range of different algorithms, even for the same task, using both positional and semantic attributes of the inputs.

artificial intelligence, machine learning, natural language, (17 more...)

Neural Information Processing Systems

Oct-10-2025, 00:21:36 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Israel (0.04)
- Europe > Switzerland
  - Vaud > Lausanne (0.04)
- North America > United States (0.28)

Genre:
- Research Report > Experimental Study (0.92)

Industry:
- Government > Regional Government > North America Government (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks (1.00)
    - Statistical Learning (0.93)
  - Natural Language (1.00)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention

Similar Docs Excel Report more

Title	Similarity	Source
None found