◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Junxian He

15 papers hereh-index 214.8k citations32 works total

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

author position
  • first author4
  • middle author8

Across the 12 of 15 papers where every author was matched, so the position is known.

fields
  • cs.CL11
  • cs.LG4
same name
  • Junxian He — 13 papers, h 10
  • Junxian He — 9 papers, h 10
  • Junxian He — 8 papers, h 6
  • Junxian He — 8 papers, h 5
  • Junxian He — 7 papers, h 8
  • Junxian He — 5 papers, h 6

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
20172023
most citedLagging Inference Networks and Posterior Collapse in Variational Autoencoders

128 citations · 186 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

4 papers · 1 filter

cs.LG2019

A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text

Bohan Li, Junxian He, Graham Neubig +2

When trained effectively, the Variational Autoencoder (VAE) is both a powerful language model and an effective representation learning framework. In practice, however, VAEs are tra…

cs.LG2019

Revisiting Self-Training for Neural Sequence Generation

Junxian He, Jiatao Gu, Jiajun Shen +1

Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's predi…

cs.LG2019★ 128 cited

Lagging Inference Networks and Posterior Collapse in Variational Autoencoders

Junxian He, Daniel Spokoyny, Graham Neubig +1

The variational autoencoder (VAE) is a popular combination of deep latent variable model and accompanying variational learning technique. By using a neural inference network to app…

cs.LG2017

Efficient Correlated Topic Modeling with Topic Embedding

Junxian He, Zhiting Hu, Taylor Berg-Kirkpatrick +2

Correlated topic modeling has been limited to small model and problem sizes due to their high computational cost and poor scaling. In this paper, we propose a new model which learn…

◍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.