◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Di He

2 papers hereh-index 111 citations3 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author1
  • middle author1

Across the 2 of 2 papers where every author was matched, so the position is known.

fields
  • cs.CL1
  • cs.LG1
same name
  • Di He — 11 papers, h 8
  • Di He — 6 papers, h 2
  • Di He — 5 papers, h 5
  • Di He — 4 papers, h 5
  • Di He — 3 papers, h 3
  • Di He — 2 papers, h 2

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

works on
large language model training 1matrix representations 1momentum methods 1optimizer geometry 1stochastic convergence 1

From the 1 of 2 linked papers with an AI index.

collaborators

2 papers

cs.LG2026

Muse: Representation Geometry of Muon Beyond Normalized Momentum

Da Chang, Qiankun Shi, Lvgang Zhang +4

The paper investigates how the choice of matrix representation influences Muon-style optimizers, proposes the Muse family of optimizers that keep the same momentum and Newton–Schul…

cs.CL2025

AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs

Di He, Songjun Tu, Ajay Jaiswal +4

Weight decay is a standard regularization technique for training large language models (LLMs). While it is common to assign a uniform decay rate to every layer, this approach overl…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.