◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Di He

61 papers hereh-index 419.8k citations91 works total

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

author position
  • first author2
  • middle author50
  • last author4

Across the 56 of 61 papers where every author was matched, so the position is known.

fields
  • cs.LG32
  • cs.CL19
  • cs.CV4
  • eess.AS2
  • cs.PL1
  • eess.IV1
same name
  • Di He — 14 papers, h 8
  • Di He — 7 papers, h 5
  • Di He — 7 papers, h 5
  • Di He — 6 papers, h 2
  • Di He — 4 papers, h 8
  • Di He — 4 papers, h 5

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

activity
20132023
most citedDual Learning for Machine Translation

597 citations · 1.4k across the 38 of their papers we have counts for

collaborators
Showing 2020 · cs.LGShow all

4 papers · 2 filters

cs.LG2020

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

Tianle Cai, Shengjie Luo, Keyulu Xu +3

Normalization is known to help the optimization of deep neural networks. Curiously, different architectures require specialized normalization methods. In this paper, we study what…

cs.LG2020★ 6 cited

Transferred Discrepancy: Quantifying the Difference Between Representations

Yunzhen Feng, Runtian Zhai, Di He +2

Understanding what information neural networks capture is an essential problem in deep learning, and studying whether different models capture similar features is an initial step t…

cs.LG2020

On Layer Normalization in the Transformer Architecture

Ruibin Xiong, Yunchang Yang, Di He +7

The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is sh…

cs.LG2020

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

Runtian Zhai, Chen Dan, Di He +5

Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which le…

◍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.