SpecTr: Fast Speculative Decoding via Optimal Transport

Feb-12-2026, 14:06:02 GMT–Neural Information Processing Systems

However, autoregressive sampling generates tokens one at a time making it slow, and even prohibitive in certain tasks.

large language model, machine learning, natural language, (18 more...)

Neural Information Processing Systems

Feb-12-2026, 14:06:02 GMT

Conferences PDF

Country:
- Asia > Russia (0.04)
- Europe > Russia (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning (1.00)
  - Natural Language > Large Language Model (0.68)
  - Representation & Reasoning (0.95)

Duplicate Docs Excel Report

Title
6034a661584af6c28fd97a6f23e56c0a-Paper-Conference.pdf

Similar Docs Excel Report more

Title	Similarity	Source
None found