◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Jinyuan Jia

18 papers hereh-index 10528 citations22 works total

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

author position
  • middle author9
  • last author8

Across the 17 of 18 papers where every author was matched, so the position is known.

fields
  • cs.CR14
  • cs.CV2
  • cs.CL1
  • cs.LG1
same name
  • Jinyuan Jia — 26 papers, h 22
  • Jinyuan Jia — 16 papers, h 9
  • Jinyuan Jia — 14 papers, h 20
  • Jinyuan Jia — 8 papers, h 9
  • Jinyuan Jia — 4 papers, h 3
  • Jinyuan Jia — 4 papers, h 3

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
20242026
most citedPoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

12 citations · 18 across the 18 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2024

Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation

Yuan Xiao, Shiqing Ma, Juan Zhai +3

The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, withi…

cs.CV2024

MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models

Yanting Wang, Hongye Fu, Wei Zou +1

Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D poi…

◍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.