◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Bai Li

9 papers hereh-index 11952 citations16 works total

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

author position
  • first author5
  • middle author4

Across the 9 of 9 papers where every author was matched, so the position is known.

fields
  • cs.LG5
  • stat.ML2
  • cs.CL1
  • eess.IV1
same name
  • Bai Li — 11 papers, h 6
  • Bai Li — 3 papers
  • Bai Li — 3 papers, h 27
  • Bai Li — 3 papers, h 15
  • Bai Li — 1 paper
  • Bai Li — 1 paper, 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

activity
20172020
most citedTowards Understanding Fast Adversarial Training

24 citations · 61 across the 6 of their papers we have counts for

collaborators
Showing 2019Show all

4 papers · 1 filter

eess.IV2019★ 9 cited

Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction

Yantao Lu, Yunhan Jia, Jianyu Wang +4

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they remain adversarial even against other m…

cs.LG2019★ 1 cited

Graph-Driven Generative Models for Heterogeneous Multi-Task Learning

Wenlin Wang, Hongteng Xu, Zhe Gan +6

We propose a novel graph-driven generative model, that unifies multiple heterogeneous learning tasks into the same framework. The proposed model is based on the fact that heterogen…

cs.LG2019★ 2 cited

On Norm-Agnostic Robustness of Adversarial Training

Bai Li, Changyou Chen, Wenlin Wang +1

Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where ad…

cs.CL2019★ 23 cited

Improving Sequence-to-Sequence Learning via Optimal Transport

Liqun Chen, Yizhe Zhang, Ruiyi Zhang +7

Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE). However, standard MLE training considers a word-level objective, predicting the next word…

◍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.