Skip to main content
GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling
- Item #:
- 085713-0450
- UPC:
Details
-
DOI:
https://doi.org/10.52202/085713-0450
-
Author(s):
Tianhao Chen, Xin Xu, Zijing Liu, Pengxiang Li, Xinyuan Song, AJAY JAISWAL, Fan Zhang, Jishan Hu, Yang Wang, Hao CHEN, Shizhe Diao, Shiwei Liu, Yu Li, Lu Yin, Can Yang
-
Pages:
14950-14975 (26 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 38
-
Date/Location:
Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
-
Series:
Advances in Neural Information Processing Systems 38
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
-
DOI:
https://doi.org/10.52202/085713-0450
-
Author(s):
Tianhao Chen, Xin Xu, Zijing Liu, Pengxiang Li, Xinyuan Song, AJAY JAISWAL, Fan Zhang, Jishan Hu, Yang Wang, Hao CHEN, Shizhe Diao, Shiwei Liu, Yu Li, Lu Yin, Can Yang
-
Pages:
14950-14975 (26 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 38
-
Date/Location:
Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
-
Series:
Advances in Neural Information Processing Systems 38
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)