Luna: Linear Unified Nested Attention Xuezhe Ma

Oct-2-2025, 11:46:20 GMT–Neural Information Processing Systems

The quadratic computational and memory complexities of the Transformer's attention mechanism have limited its scalability for modeling long sequences.

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

Neural Information Processing Systems

Oct-2-2025, 11:46:20 GMT

Conferences PDF

Country:
- North America > United States
  - Pennsylvania > Allegheny County > Pittsburgh (0.04)
- South America > Chile
  - Santiago Metropolitan Region > Santiago Province > Santiago (0.04)

Industry:
- Government (0.47)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning
      - Neural Networks (0.68)
      - Statistical Learning (0.47)
    - Natural Language (1.00)
    - Representation & Reasoning (0.67)
  - Communications > Social Media (0.68)

Duplicate Docs Excel Report

Title
Luna: LinearUnifiedNestedAttention

Similar Docs Excel Report more

Title	Similarity	Source
None found