Year: 2025
Type: article
Abstract: As the scaling of pretraining is reaching a plateau of diminishing returns, model inference is quickly becoming an important driver for model performance. Today, test-time compute scaling offers a new, exciting avenue to increase model performance beyond what can be achieved with training, and test-time compute techniques cover a fertile area for many more breakthroughs in AI. Innovations using ensemble methods, iterative refinement, repeated sampling, retrieval augmentation, chain-of-thought reasoning, search, and agentic ensembles are already yielding improvements in model quality performance and offer additional opportunities for future growth.
Source: Queue
DOI: 10.1145/3733701
Author: Michael Gschwind
Institutions: Nvidia (United Kingdom), Nvidia (United States)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Meta
OpenAlex ID: W4410711613