Work

Instant: Compressing Gradients and Activations for Resource-efficient Training

Year: 2026

Type: conference-paper

Abstract: International audience

Source: HAL (Le Centre pour la Communication Scientifique Directe)

Authors: Doan, Tuan-Kiet, Tran, Trung-Hieu, Tartaglione, Enzo, Simidjievski, Nikola, Nguyen, Van-Tam

Institutions: Télécom Paris, Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Award: ENFIELD: European Lighthouse to Manifest Trustworthy and Green AI

OpenAlex ID: W7135158372

FWCI:

Cites:

Cited by:

Related to: