◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Peng Xu

4 papers hereh-index 7338 citations9 works total

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

author position
  • middle author4

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.LG3
  • cs.CV1
same name
  • Peng Xu — 24 papers, h 16
  • Peng Xu — 23 papers, h 20
  • Peng Xu — 19 papers, h 17
  • Peng Xu — 18 papers, h 4
  • Peng Xu — 15 papers, h 17
  • Peng Xu — 14 papers, h 9

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
20162023
most citedDiffRate : Differentiable Compression Rate for Efficient Vision Transformers

3 citations · 5 across the 2 of their papers we have counts for

collaborators

4 papers

cs.CV2023★ 3 cited

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

Mengzhao Chen, Wenqi Shao, Peng Xu +6

Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent adv…

cs.LG2022★ 2 cited

CowClip: Reducing CTR Prediction Model Training Time from 12 hours to 10 minutes on 1 GPU

Zangwei Zheng, Pengtai Xu, Xuan Zou +12

The click-through rate (CTR) prediction task is to predict whether a user will click on the recommended item. As mind-boggling amounts of data are produced online daily, accelerati…

cs.LG2018

Trust Region Based Adversarial Attack on Neural Networks

Zhewei Yao, Amir Gholami, Peng Xu +2

Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tu…

cs.LG2016

Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data

Paroma Varma, Bryan He, Dan Iter +4

A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision so…

◍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.