Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing

Feb-17-2026, 20:01:18 GMT–Neural Information Processing Systems

Due to their size, the capability of these networks has increased tremendously, but this has come at the cost of a significant increase in necessary compute.

large language model, machine learning, natural language, (17 more...)

Neural Information Processing Systems

Feb-17-2026, 20:01:18 GMT

Conferences PDF

Country:
- Asia
  - China > Hong Kong (0.04)
  - Middle East
    - Israel (0.04)
    - Jordan (0.04)
- Europe
  - Belgium > Brussels-Capital Region
    - Brussels (0.04)
  - Italy > Tuscany
    - Florence (0.04)
  - Netherlands > North Holland
    - Amsterdam (0.04)
- North America
  - Dominican Republic (0.04)
  - United States > Minnesota
    - Hennepin County > Minneapolis (0.14)

Genre:
- Research Report (0.46)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning > Neural Networks
    - Deep Learning (1.00)
  - Natural Language > Large Language Model (1.00)
  - Vision (0.69)

Duplicate Docs Excel Report

Title
Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing Y elysei Bondarenko, Markus Nagel, Tijmen Blankevoort Qualcomm AI Research Amsterdam, The Netherlands

Similar Docs Excel Report more

Title	Similarity	Source
None found