Workshop 1
Summary:
This
workshop
focuses
on
data,
knowledge,
and
AI
driven
smart
design
and
manufacturing
systems,
aiming
to
explore
how
the
new
generation
of
intelligent
technologies
(such
as
big
data,
knowledge
graphs,
artificial
intelligence,
large
model,
AI
agent,
etc.)
can
reconstruct
the
design
and
manufacturing
systems
of
industrial
enterprises,
achieve
digital
and
intelligent
development
and
transformation
of
industrial
enterprises,
and
research
the
theory,
methods,
technologies,
systems,
platforms,
applications,
verification,
etc.
of
digital
and
intelligent
transformation.
Original researches are welcome in this workshop. Research areas may include (but not limited to) the following:
Original researches are welcome in this workshop. Research areas may include (but not limited to) the following:
- Enterprise digital transformation
- Smart manufacturing system
- Computer integrated manufacturing system
- Industrial big data analysis and decision-making in design and manufacturing systems
- Industrial knowledge automation technology in design and manufacturing systems
- Industrial data space technology in design and manufacturing systems
- Industrial artificial intelligence technology in design and manufacturing systems
- Industrial large model technology in design and manufacturing systems
- Industrial AI intelligent agent technology in design and manufacturing systems
- Industrial intelligent internet technology in design and manufacturing system
- Intelligent middle platform for business, data, technology and knowledge
Keywords: Smart manufacturing, Digitalization transformation, Industrial Artificial Intelligence, Industrial Large Model, Industrial intelligent agent
Dr.
Xianyu
Zhang,
Ph.D,
Assistant
Professor,
Master's
Supervisor,
graduated
with
a
Ph.D.
from
Shanghai
Jiao
Tong
University.
He
mainly
engages
in
research
in
the
fields
of
intelligent
manufacturing,
industrial
intelligence
(industrial
internet,
industrial
big
data,
industrial
artificial
intelligence),
mass
personalization,
and
enterprise
digital
transformation.
He
has
published
more
than
70
papers
in
international
SCI
journals
and
academic
conferences,
and
has
published
6
monographs.
He
has
undertaken
or
participated
in
more
than
30
national
natural
science
foundation
projects,
national
intelligent
manufacturing
projects,
national
green
manufacturing
projects,
Shanghai
industrial
internet
projects,
Shanghai
industrial
big
data
projects,
Shanghai
industrial
artificial
intelligence
projects
and
other
industry
university
research
cooperation
projects.
Xinguo
Ming
is
a
professor
of
School
of
Mechanical
Engineering,
Shanghai
Jiao
Tong
University.
His
research
interests
include
Industrial
Artificial
Intelligence,
Industrial
Internet,
Smart
Manufacturing
Systems,
Smart
Product
Innovation
Ecosystem,
Service-oriented
Manufacturing
(Smart
Product
Service
Ecosystem),
Green
Design
and
Supply
Chain,
Lean
Enterprise
and
Management,
etc.
Prof.
Ming
has
published
over
100
scientific
papers
and
10
books
(in
Chinese).
He
was
a
member
of
the
editorial
board
of
Concurrent
Engineering:
Research
and
Applications,
Business
Process
Management
Journal,
etc.
He
undertakes
and
participates
in
a
number
of
Industrial-Academic-Research
cooperative
projects
funded
by
national
and
Shanghai
government.
Dr.
Zhiwen
Liu,
Ph.D,
graduated
with
a
Ph.D.
from
Shanghai
Jiao
Tong
University,
Head
of
the
discipline
of
Intelligent
Manufacturing
Engineering,
He
mainly
engages
in
research
fields
that
focus
on
the
transformation
and
upgrading
of
modern
electronic
information
manufacturing
industry,
including
industrial
intelligent
equipment,
smart
product-service
systems,
and
digital
service
systems.
He
has
published
more
than
20
papers
in
international
SCI
journals
and
academic
conferences.
He
is
currently
serving
as
the
consultant
for
several
industrial
enterprise,
and
has
undertaken
a
number
of
research
projects
related
to
intelligent
manufacturing
in
electronic
information
industry.
Jianzhao
Wu,
Associate
Professor,
Master's
Supervisor,
Joint
PhD
of
Huazhong
University
of
Science
and
Technology
and
National
University
of
Singapore,
Fujian
Province
Research
Talent
Introduction
Program,
Fujian
Province
High-Level
Talent
,
Senior
Member
of
the
Chinese
Society
of
Mechanical
Engineering.
His
research
focuses
on
modeling
and
optimization
of
laser-based
low-carbon
manufacturing,
as
well
as
state
diagnosis
and
energy
efficiency
optimization
of
manufacturing
systems
using
intelligent
algorithms.
He
has
published
over
40
papers
in
domestic
and
international
journals,
including
over
10
as
the
first
author,
and
holds
over
10
authorized
patents/software
copyrights.
He
has
led
or
participated
in
over
10
projects
at
the
national,
provincial,
and
municipal
levels.
He
serves
as
a
guest
editor
for
special
issues
of
international
journals
such
as
the
Journal
of
Materials
Informatics,
a
young
editorial
board
member
for
EI-indexed
journals
like
Chinese
Surface
Engineering,
and
a
reviewer
for
several
renowned
SCI
journals.
Xiaobin
Li,
Associate
Professor,
Doctoral
Supervisor,
graduated
with
a
Ph.D.
from
Chongqing
University.
His
research
focuses
on
intelligent
manufacturing,
networked
collaborative
manufacturing,
and
Artificial
Intelligence
application
in
manufacturing
services.
He
has
presided
over
more
than
20
national
and
provincial-level
research
projects,
achieved
some
scientific
research
results,
including
over
50
SCI
papers,
more
than
20
national
invention
patents,
and
five
provincial-level
awards.
Tao Zhang received the Ph.D. degree in control science and engineering from Shanghai Jiao Tong University, Shanghai, China, in 2019. From 2017 to 2018, he was with the Department of Geoinformatics, KTH Royal Institute of Technology, Stockholm, Sweden, as a joint Ph.D. Student. From 2019 to 2021, he held a post-doctoral position at the Department of Electronics, Tsinghua University, Beijing, China. He is currently an Associate Professor with the Shanghai Key Laboratory of Intelligent Sensing and Recognition, Shanghai Jiao Tong University. His research interests include image processing, object recognition, and machine learning. He has published over 100 papers in international journals.
Workshop 2
Summary:
Real-world
data,
such
as
images,
networks,
and
text,
inherently
possess
multi-granularity
structural
characteristics.
Inspired
by
human
multi-granularity
cognitive
thinking,
multi-granularity
cognitive
computing
has
emerged
as
an
advanced
computational
paradigm
that
enables
modeling
and
solving
complex
problems
at
different
granularities
and
scales.
By
integrating
multi-granularity
analysis
and
cognitive
computing,
it
is
possible
to
overcome
the
limitations
of
traditional
data
mining
and
achieve
more
intelligent
and
efficient
mining.
Additionally, current machine learning models often present as "black boxes," lacking interpretability and understandability, which limits their controllability and widespread deployment in real-world applications. Although multi-granularity cognitive computing models have demonstrated powerful modeling and problem-solving capabilities, their complexity may pose challenges in terms of interpretability. Moreover, the inherent fuzziness and uncertainty in multi-granularity cognitive computing models can further complicate their interpretability and reliability. Therefore, investigating ways to enhance the interpretability of models, address their fuzziness and uncertainty, and make their decision-making processes more transparent and understandable is crucial for developing trustworthy and reliable artificial intelligence.
This workshop aims to bring together researchers, practitioners, and industry experts to discuss the latest developments, challenges, and future directions of multi-granularity cognitive computing in data mining. We invite submissions of original research papers, and position papers that address the following topics, but are not limited to:
Additionally, current machine learning models often present as "black boxes," lacking interpretability and understandability, which limits their controllability and widespread deployment in real-world applications. Although multi-granularity cognitive computing models have demonstrated powerful modeling and problem-solving capabilities, their complexity may pose challenges in terms of interpretability. Moreover, the inherent fuzziness and uncertainty in multi-granularity cognitive computing models can further complicate their interpretability and reliability. Therefore, investigating ways to enhance the interpretability of models, address their fuzziness and uncertainty, and make their decision-making processes more transparent and understandable is crucial for developing trustworthy and reliable artificial intelligence.
This workshop aims to bring together researchers, practitioners, and industry experts to discuss the latest developments, challenges, and future directions of multi-granularity cognitive computing in data mining. We invite submissions of original research papers, and position papers that address the following topics, but are not limited to:
- Algorithms and models for multi-granularity cognitive computing in data mining.
- Interpretability, understandability, and robustness of multi-granularity cognitive computing models
- Multi-granularity representation learning and feature extraction methods.
- Integration of domain knowledge and cognitive mechanisms in data mining to handle fuzziness and uncertainty
- Applications of multi-granularity cognitive computing in graph data mining, natural language processing, computer vision, healthcare, social network analysis, and other domains.
- Evaluation metrics and benchmarks for assessing the interpretability, robustness, and reliability of models under fuzziness and uncertainty.
Keywords: Multi-granularity cognitive computing, Data mining, Model interpretability, Fuzziness and uncertainty, Representation learning, Domain knowledge integration, Evaluation metrics and benchmarks, , Natural language processing, Graph neural networks, Computer vision.
Research
interests:
Data
Mining,
Knowledge
Graph,
Graph
Neural
Networks,
Model
Explainability.
2019-present: Associate Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2021-2023: Post-Doc at Hong Kong Baptist University supported by the HK Scholar Programme.
2016-2019: Assistant Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2012-2016: Beijing Institute of Technology, PhD in Engineering
2019-present: Associate Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2021-2023: Post-Doc at Hong Kong Baptist University supported by the HK Scholar Programme.
2016-2019: Assistant Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2012-2016: Beijing Institute of Technology, PhD in Engineering
Research
interests:
Uncertainty
Data
Mining,
Knowledge
Graph,
Graph
Neural
Networks,
Model
Explainability.
2009-present: Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2003-2009: Associate Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2005-2008: Chongqing University, PhD in Computer Science
2009-present: Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2003-2009: Associate Professor, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China
2005-2008: Chongqing University, PhD in Computer Science
Workshop 3
Summary:
Mining
operations
constitute
a
complex
production
complex
system
characterized
by
human-natural
environment
coupling,
where
AI
has
demonstrated
significant
potential
to
enhance
traditional
operations,
especially
in
the
fields
of
image
perception,
time-series
data
monitoring,
multi,
source
heterogeneous
data
joint
prediction,
and
intelligent
system
optimization.
As
AI
come
into
the
deep
learning
era,
mining
is
concurrently
entering
a
deep-mining
age,
expanding
into
increasingly
challenging
environments
including
deep
underground,
deep
sea
and
deep
space
domains.
This workshop focuses on applying AI technologies to pioneer intelligent mining innovations in extreme environments such as deep-sea, space, and mega scale mine. We will examine how AI can empower the complete mining value chain: from exploration and sensing to management and decision-making to achieve smarter and more advanced production systems.
Key Topics:
We invite contributions from experts across systems science, artificial intelligence, and mining engineering to collectively drive intelligent transformation of these complex systems and develop innovative solutions for extreme-environment resource development.
This workshop focuses on applying AI technologies to pioneer intelligent mining innovations in extreme environments such as deep-sea, space, and mega scale mine. We will examine how AI can empower the complete mining value chain: from exploration and sensing to management and decision-making to achieve smarter and more advanced production systems.
Key Topics:
- Multimodal Data Fusion for Oceanic Mineral Exploration and Reserve Estimation
- Intelligent Sensing and Monitoring for Deep-sea Environments
- Underwater Intelligent Perception, Communication Equipment and Technologies
- Smart Mining Models and System Optimization for Polymetallic Nodules
- Health Monitoring Systems for Deep-sea Resource Development Equipment
- Intelligent Mining Models and System Optimization for Space Mining
- Space-based Intelligent Perception and Communication Technologies
- Intelligent Mining Management and Optimization for Large-scale Terrestrial Mining Systems
We invite contributions from experts across systems science, artificial intelligence, and mining engineering to collectively drive intelligent transformation of these complex systems and develop innovative solutions for extreme-environment resource development.
Keywords: Deep-Tech Mining; Multimodal Data Fusion; Intelligent Sensing; AI-Driven Mining; Extreme-environment Resource Development
Jiang
Song,
Professor,
Doctoral
Supervisor,
Vice
Dean
of
the
School
of
Resource
Engineering
at
Xi'an
University
of
Architecture
and
Technology,
Deputy
Secretary
General
of
the
Open
pit
Mining
and
Slope
Engineering
Committee
of
the
Chinese
Society
of
Rock
Mechanics
and
Engineering,
Outstanding
Young
Science
and
Technology
Talent
Award
in
the
National
University
Mining,
Petroleum
and
Safety
Engineering
Field,
Shaanxi
Province
Youth
Top
notch
Talent,
Shaanxi
Province
Youth
Science
and
Technology
New
Star
Talent
Plan,
Jiangsu
Province
"Double
Innovation
Plan"
Science
and
Technology
Talent,
Outstanding
Young
Talent
in
Xi'an
City,
mainly
focuses
on
the
field
of
mining
intelligence
and
safety,
with
a
focus
on
research
in
mining
slope
monitoring
and
early
warning,
mining
computer
vision
and
other
directions.
He
proposed
the
"Geological
Body
Equipment
Group"
bidirectional
coupling
perception
theory.
I
have
successively
presided
over
2
projects
funded
by
the
National
Natural
Science
Foundation
of
China,
1
project
specially
supported
by
the
China
Postdoctoral
Fund
(in
station),
1
general
project
funded
by
the
China
Postdoctoral
Fund,
7
other
provincial
and
ministerial
level
funds,
2
departmental
and
bureau
level
projects,
and
edited
1
textbook
on
"Mining
Computer
Vision".
Has
6
utility
model
patents,
3
invention
patents,
10
software
copyrights,
participated
in
the
compilation
of
the
group
standard
"T/SXSAE
004-2022
Overall
Technical
Specification
for
Unmanned
Transport
Vehicles
in
Open
pit
Mines",
and
published
more
than
70
academic
papers,
including
more
than
30
SSCI/SCI
search
papers.
The
research
results
have
won
awards
such
as
the
first
prize
of
China
Metallurgical
Mining
Science
and
Technology,
the
first
prize
of
China
Nonferrous
Metals
Industry
Association,
and
the
first
prize
of
Innovation
Award
of
China
Invention
Association
Invention
and
Entrepreneurship
Award.
Served
as
a
guest
editor
and
young
editorial
board
member
for
over
10
Chinese
and
English
journals,
as
a
peer
review
expert
for
the
National
Natural
Science
Foundation
of
China,
and
as
a
thesis
review
expert
for
the
Degree
Center
of
the
Ministry
of
Education.
Li
Guo,
Ph.D.
in
Management,
Master's
Supervisor.
She
has
presided
over
multiple
research
projects,
including
the
General
Program
of
the
National
Natural
Science
Foundation
of
China,
the
General
Program
of
the
Shaanxi
Natural
Science
Foundation,
and
the
Special
Fund
of
the
Department
of
Education,
among
other
horizontal
and
vertical
projects.
Her
achievements
include
the
Third
Prize
of
the
Shaanxi
Science
and
Technology
Award,
the
First
Prize
of
the
2nd
National
Safety
Science
and
Technology
Progress
Award,
the
Second
Prize
of
the
Outstanding
Scientific
Research
Achievement
Award
for
Shaanxi
Higher
Education
Institutions,
and
six
other
research
and
teaching
awards.
She
has
published
over
20
academic
papers.
Her
research
focuses
on:
Big
Data
Management
and
Applications
in
Resources,
Intelligent
Science
and
Engineering
in
Mining,
Safety
Monitoring
and
Control.
Workshop 4
Summary:
The
explosive
growth
of
applications
with
various
requirements
is
pushing
computation
and
decision-making
to
the
edge
network,
which
creates
unprecedented
demands
on
the
underlying
infrastructure.
Novel
research
is
urgently
needed
to
develop
intelligent,
adaptive,
and
efficient
techniques
for
edge
networks.
In
this
workshop,
we
invite
researcher,
engineers,
and
practitioners
to
submit
original
contributions
on
all
aspects
on
edge
network
optimization.
This
workshop
aims
to
bring
together
the
latest
research,
innovative
solutions,
and
practical
experiences
to
address
these
complex
challenges
and
advance
the
state-of-the-art
in
optimizing
performance,
efficiency,
and
reliability
in
edge
environments.
Topics of interest include, but are not limited to:
Topics of interest include, but are not limited to:
- Architectures & Frameworks: novel edge network architectures, distributed edge-cloud frameworks, MEC integration, edge computing models;
- Resource Management: dynamic resource provisioning & scheduling, workload placement/offloading, energy-efficient operation;
- Network Optimization Techniques: traffic engineering, QoS/QoE aware routing, congestion control, latency reduction, bandwidth optimization;
- Content Delivery & Caching: proactive caching strategies, in-network computing, efficient content distribution, collaborative caching;
- AI for Optimization: predictive resource allocation, intelligent traffic management, decision-making via ML/DL/RL/LLM;
- Virtualization & Programmability: NFV at the edge, SDN for edge control, service chain, lightweight containerization;
- Mobility & Dynamics: optimization for mobile edge nodes, handling device mobility, dynamic topology management;
- Scalability & Reliability: scaling edge networks efficiently, fault tolerance, resilience strategies, traffic load balancing;
- Security-aware Optimization: privacy protection, confidential approach;
- Performance Measurement & Modeling: benchmarking, simulation platforms, analytical models, monitoring techniques;
- User Cases & Applications: Optimization for vehicular networks, IoT, AR/VR, real-time video analytics, industrial automation, smart cities, and other demanding edge applications.
Keywords: Multi-access Edge Computing, Edge Network, Network Optimization
Chuanfen
Feng
received
the
B.E.
degree
from
Ludong
University,
Yantai,
China,
in
2002,
and
the
Ph.D.
degrees
from
Beijing
University
of
Posts
and
Telecommunications,
Beijing,
China,
in
2007.
He
is
currently
a
professorate
senior
engineer
with
the
School
of
Information
Science
and
Engineering,
Shandong
Normal
University.
His
current
research
interests
include
mobile
network
planning,
mobile
edge
computing
and
internet
of
things.
Yantong
Wang
received
the
BE
degree
in
Internet
of
Things
from
Shandong
University,
China,
in
2014,
the
MEng
degree
in
Electronics
and
Communication
from
Tsinghua
University,
China,
in
2017,
and
the
PhD
degree
in
telecommunications
from
King's
College
London,
UK,
in
2022.
He
is
currently
a
lecturer
at
the
School
of
Information
Science
and
Engineering,
Shandong
Normal
University,
China.
His
research
interests
include
proactive
caching,
edge
network
optimization,
mathematical
programming,
and
next-generation
network
technologies.
Workshop 5
Summary:
Today,
big
data
has
become
a
kind
of
capital.
The
world’s
largest
technology
companies
are
all
based
on
big
data,
which
they
continuously
analyze
to
improve
operational
efficiency
and
develop
new
products.
Although
it
has
been
around
for
a
long
time,
the
utilization
of
big
data
is
just
beginning.
The
value
of
big
data
lies
in
its
application.
It
can
help
people
understand
data
more
intuitively
and
conveniently,
and
can
further
mine
other
valuable
data.
The aim of this workshop is to bring together the latest research results in the field of Big Data Application provided by researchers from academia and the industry. We encourage prospective authors to submit related distinguished research papers on the following topics. Please name the title of the submission email with “paper title_workshop title”.
The aim of this workshop is to bring together the latest research results in the field of Big Data Application provided by researchers from academia and the industry. We encourage prospective authors to submit related distinguished research papers on the following topics. Please name the title of the submission email with “paper title_workshop title”.
- Big Data Applications and Software in Science, Engineering, Healthcare,
- Finance, Business, Transportation, Telecommunications, etc.
- Finance, Business, Transportation, Telecommunications, etc.
- Big Data Industry Standards.
- Development and Deployment Experiences with Big Data Systems.
Keywords: big data application, big data analysis, big data industry standard, big data system
Jianjun
Zhang, received
a
Ph.D.
degree
in
Computer
Science
and
Technology
from
Hunan
University.
He
worked
as
an
associate
professor
at
the
College
of
Engineering
and
Design,
Hunan
Normal
University.
His
research
interests
include
Big
Data
Application
and
Information
Security.
Workshop 6
Summary:
As
AI
technologies
rapidly
evolve,
their
integration
into
healthcare
settings
heralds
a
transformative
era
with
the
potential
to
significantly
improve
patient
outcomes,
streamline
operations,
and
amplify
the
capabilities
of
healthcare
professionals.
This
workshop
is
dedicated
to
exploring
the
cutting-edge
AI
technologies
that
are
reshaping
healthcare
by
enhancing
patient
care,
optimizing
operations,
and
empowering
healthcare
professionals.
We invite leading researchers, practitioners, and policymakers to join us in examining the theoretical advancements, practical applications, and promising future of AI in the healthcare sector. The workshop will cover the following key themes (but is not limited to them):
We look forward to engaging discussions, collaborative opportunities, and shared insights that will shape the future of AI in healthcare.
We invite leading researchers, practitioners, and policymakers to join us in examining the theoretical advancements, practical applications, and promising future of AI in the healthcare sector. The workshop will cover the following key themes (but is not limited to them):
- Future of AI in Healthcare: Participants will explore state-of-the-art research and trends shaping healthcare's future. Discussions will focus on AI's role in diagnosing diseases earlier, optimizing treatment plans, predicting patient outcomes, and its implications for healthcare delivery.
- Trustworthy AI for Healthcare: This segment will delve into the ethical considerations, importance of data privacy, and strategies for ensuring transparency and accountability. It is crucial for building reliable, ethical AI systems that align with public health goals and maintain patient trust.
- Explainable AI in Healthcare and Medicine: Explainability is vital for clinical acceptance. This theme will cover the importance of developing AI systems whose actions are interpretable by human experts, enhancing transparency and fostering trust among healthcare providers.
- Novel AI Methods and Practices for Healthcare: This new theme will highlight cutting-edge AI methodologies and their current applications within healthcare. It will showcase innovative practices and how they are being implemented to address complex medical challenges, with a focus on emerging technologies such as deep learning, natural language processing, and robotics.
We look forward to engaging discussions, collaborative opportunities, and shared insights that will shape the future of AI in healthcare.
Keywords: Artificial Intelligence in Healthcare, Medical Imaging, Biomedical Data Analysis, Explainable AI, Healthcare Innovation
Prof.
Haoxi
Zhang
is
an
Associate
Professor
at
Chengdu
University
of
Information
Technology,
China.
He
holds
a
Ph.D.
in
Knowledge
Engineering
from
the
University
of
Newcastle,
Australia
(2013),
and
a
Master’s
in
Software
Engineering
from
the
University
of
Electronic
Science
and
Technology
of
China.
Prof.
Zhang's
research
intricately
melds
artificial
intelligence
with
healthcare,
focusing
on
the
development
of
advanced
computational
models
and
machine
learning
algorithms
for
biomedical
data
analysis,
particularly
medical
imaging
and
AIoT
for
healthcare,
to
enhance
medical
decision-making.
His
work
emphasizes
developing
multimodal
learning
algorithms
to
integrate
multi-scale
biomedical
data
for
comprehensive
disease
management,
constructing
real-world
learning
systems
for
creating
robust,
trustworthy
representations
from
imperfect
medical
data,
and
innovating
causality-driven
learning
algorithms
to
boost
interpretability
and
safety
in
healthcare
applications.
Prof.
Zhang
has
published
over
40
refereed
papers
in
leading
journals
and
conferences.
Edward Szczerbicki received the PhD (1983) and D.Sc. (1993) degrees in data and information science. He has had very extensive experience in intelligent systems development over an uninterrupted 45-year period, 35 years of which he spent in top systems research centres in the United States, U.K., Germany, and Australia. In this area, he contributed to the understanding of information and knowledge management and engineering in systems operating in environments characterized by informational uncertainties. He has published close to 450 refereed papers with over four thousand citations and h-index 35. His academic experience includes ongoing positions with Gdansk University of Technology, Gdansk, Poland; Strathclyde University, Glasgow, Scotland; the University of Iowa, Iowa City, IA, USA; the University of California at Berkeley, Berkeley, CA, USA; and the University of Newcastle, Callaghan, NSW, Australia. He has given numerous invited presentations and addresses at universities in Europe, USA, Asia, Australia and at international conferences. In 2006 he received the Title of Professor awarded by the President of Poland for his international published contributions. Prof. Szczerbicki serves as an International Board Member of Knowledge Engineering Systems, and a Member of Berkeley Initiative in Soft Computing Special Interest Group in Intelligent Manufacturing. He is a Member of the Editorial Board/Associated Editor of eight international journals. He chaired/co-chaired and functioned as a committee member for close to one hundred international conferences.
Workshop 7
Summary:
In
many
scenarios
such
as
target
recognition
and
tracking,
defect
detection,
image
and
text
generation,
intelligence
analysis,
and
intelligent
Q&A,
it
is
difficult
to
ensure
the
accuracy
of
recognition,
detection,
or
answering
using
a
single
modal
data
modeling
due
to
complex
and
variable
environments,
strong
background
noise,
and
insufficient
information.
To
improve
the
modeling
effect,
it
is
necessary
to
fully
utilize
the
complementary
advantages
of
multi-modal
data,
integrate
data
from
various
modalities
such
as
RGB
images,
infrared
images,
ultrasound,
text,
and
electromagnetic
signals,
and
construct
a
unified
feature
representation
model.
This
workshop
will
focus
on
several
academic
issues
in
multi-modal
fusion
in
artificial
intelligence,
including
but
not
limited
to:
object
recognition
and
tracking,
defect
detection,
image
and
text
generation,
intelligence
analysis,
intelligent
Q&A,
RAG,
and
other
aspects.
Keywords: Multi-modal fusion, Artificial intelligence, Feature representation, Large models, RAG
As
the
project
leader
or
main
participant,
Professor
Chen
participated
in
many
projects
such
as
863,
NSFC.
In
recent
years,
He
has
published
more
than
120
academic
papers
in
many
important
academic
journals
or
international
conferences
such
as
Physics
Report,
Knowledge
Based
Systems,
Scientific
Data
and
Information
Sciences.
He
Received
the
second
prize
of
the
Natural
Science
Award
of
the
CCF
in
2014
and
the
third
prize
of
the
Sichuan
Provincial
Science
and
Technology
Progress
Award
in
2022.
Workshop 8
Summary:
While
the
convergence
of
Big
Data
and
Artificial
Intelligence
has
fueled
unprecedented
advancements,
it
also
introduced
profound
challenges
to
security
and
privacy.
The
scale
and
sensitivity
of
datasets,
coupled
with
the
inherent
complexity
of
modern
AI
models,
create
significant
vulnerabilities,
novel
attack
surfaces,
and
fundamental
issues
of
trust
and
accountability.
This workshop provides a forum for researchers and practitioners to address the critical interplay between these domains. We invite contributions on the fundamental principles and novel techniques for developing secure, transparent, and privacy-preserving intelligent systems.
This workshop provides a forum for researchers and practitioners to address the critical interplay between these domains. We invite contributions on the fundamental principles and novel techniques for developing secure, transparent, and privacy-preserving intelligent systems.
Keywords: Privacy, Security, Artificial Intelligence, Distributed System
Prof.
Zhou
holds
dual
Ph.D.
degrees
from
Xi'an
Jiaotong
University
and
University
of
Massachusetts
Amherst.
His
primary
research
interests
include
distributed
computing,
machine
learning,
and
privacy
protection.
He
has
published
over
ten
academic
papers
in
top-tier
journals
and
conferences
such
as
WWW,
TPDS,
ICDCS,
and
BigData,
including
a
Best
Paper
Runner-up
Award
at
IEEE
IC2E
2021.
He
also
serves
as
a
reviewer
and
committee
member
for
multiple
international
journals
and
conferences,
including
TPDS,
IEEE
Network,
TrustCom
and
so
on.
Linkang
Du
is
an
Assistant
Professor
at
Xi’an
Jiaotong
University,
specializing
in
trustworthy
artificial
intelligence.
His
research
focuses
on
data
security,
privacy
protection,
and
dataset
copyright
auditing
in
AI
systems.
He
received
his
Ph.D.
from
Zhejiang
University,
with
additional
research
experience
at
CISPA
Helmholtz
Center
for
Information
Security
in
Germany
and
the
Singapore
University
of
Technology
and
Design.
His
work
has
been
published
at
top
venues
such
as
IEEE
S&P,
NDSS,
ACM
CCS,
USENIX
Security,
and
ACM
WWW.
Dr.
Du
is
committed
to
safeguarding
data
rights
in
the
era
of
widespread
AI
adoption.
Workshop 9
Summary:
In
the
burgeoning
field
of
artificial
intelligence,
Approximate
Nearest
Neighbor
(ANN)
algorithms
have
become
indispensable
for
high-dimensional
similarity
search
across
applications
like
computer
vision,
NLP,
and
recommendation
systems.
With
the
ever-growing
volume
of
data,
the
quest
for
efficient
and
reliable
ANN
algorithms
is
more
critical
than
ever.
This workshop is dedicated to the exploration and advancement of ANN algorithms, focusing on their efficiency, scalability, and integration with emerging technologies. We will delve into the latest innovations, theoretical developments, and practical implementations that enhance the performance of ANN search systems.
Our goal is to foster a collaborative environment where researchers and practitioners can share breakthroughs, discuss challenges, and showcase their work in the field of ANN. We are particularly interested in submissions that address the following themes:
Join us for a dynamic event that brings together the brightest minds to drive the future of ANN research. We welcome contributions from academia and industry alike, encouraging an open exchange of ideas and fostering the development of the next generation of ANN solutions.
This workshop is dedicated to the exploration and advancement of ANN algorithms, focusing on their efficiency, scalability, and integration with emerging technologies. We will delve into the latest innovations, theoretical developments, and practical implementations that enhance the performance of ANN search systems.
Our goal is to foster a collaborative environment where researchers and practitioners can share breakthroughs, discuss challenges, and showcase their work in the field of ANN. We are particularly interested in submissions that address the following themes:
- Novel ANN algorithms and their theoretical underpinnings.
- The synergy of ANN with cutting-edge hardware like GPUs and TPUs.
- Interdisciplinary approaches that combine ANN with other AI technologies.
Join us for a dynamic event that brings together the brightest minds to drive the future of ANN research. We welcome contributions from academia and industry alike, encouraging an open exchange of ideas and fostering the development of the next generation of ANN solutions.
Keywords: Vector index, similarity search, Approximate Nearest Neighbors
Ruini
Xue,
received
his
master
and
Ph.D.
degrees
in
computer
science
and
technology
from
Tsinghua
University.
He
worked
as
an
associated
professor
at
the
School
of
Computer
Science
and
Engineering,
University
of
Electronic
Science
and
Technology
of
China.
His
research
interests
include
graph
computing,
distributed
database
and
system
architecture.
He
participated
in
the
National
Natural
Science
Foundation
and
Chinese
National
Programs
for
High
Technology
Research
and
Development,
etc.
He
published
more
than
30
papers
and
about
20
patents
have
been
granted.
Workshop 10
Summary:
This
workshop
aims
to
bridge
the
gap
between
cutting-edge
LLM
research
and
real-world
industry
applications.
We
focus
on
exploring
actionable
strategies
to
leverage
large
language
models
for
solving
business
challenges,
optimizing
operations,
and
driving
innovation.
We
will
address
key
opportunities—automating
workflows,
enhancing
decision-making,
personalizing
user
interactions—while
tackling
critical
challenges:
cost
control,
data
privacy
and
integration
complexity
in
various
industry
fields.
Keywords: Large Language Models, Industry Intelligence, Artificial Intelligence
Ruini
Xue,
received
his
master
and
Ph.D.
degrees
in
computer
science
and
technology
from
Tsinghua
University.
He
worked
as
an
associated
professor
at
the
School
of
Computer
Science
and
Engineering,
University
of
Electronic
Science
and
Technology
of
China.
His
research
interests
include
graph
computing,
distributed
database
and
system
architecture.
He
participated
in
the
National
Natural
Science
Foundation
and
Chinese
National
Programs
for
High
Technology
Research
and
Development,
etc.
He
published
more
than
30
papers
and
about
20
patents
have
been
granted.
Workshop 11
Summary:
The
rapid
advancement
of
AI
has
propelled
industrial
automation
into
an
advanced
phase,
revolutionizing
manufacturing
through
integration
with
sensors,
machine
vision,
and
adaptive
decision-making
systems.
This
workshop
is
looking
for
some
advanced
AI
solutions
for
intelligent
manufacturing.
Potential
topics
include,
but
are
not
limited
to:
Each topic includes accessible theoretical overviews and practical examples, fostering discussions on current limitations and future directions. This workshop targets researchers, engineers, and industry professionals seeking to bridge AI innovation with manufacturing efficiency.
- (1) AI for job shop scheduling problems (JSSP), including advanced deep learning techniques for optimizing production workflows, reducing lead times, and minimizing manual intervention.
- (2) AI for Time Series Forecasting: Focusing on both univariate and multivariate time series forecasting (UTSF/TSF), such as advanced strategies and modeling methods to enhance predictive accuracy in production metrics, resource allocation, and demand planning.
- (3) AI for Fault Diagnosis (FD): Exploring deep learning-driven FD, with a focus on small-sample scenarios, cross-domain adaptability, and precise fault localization, to improve equipment reliability and reduce downtime.
Each topic includes accessible theoretical overviews and practical examples, fostering discussions on current limitations and future directions. This workshop targets researchers, engineers, and industry professionals seeking to bridge AI innovation with manufacturing efficiency.
Keywords: Deep learning, job shop scheduling, time series forecasting, time series forecasting, fault diagnosis
Shao
Xiaorui,
the
Special
Post
Professor,
Associate
Professor,
Master
Supervisor
at
Guizhou
university.
He
serves
as
a
reviewer
for
more
than
20
SCI
journals,
including
TCYB,
TGRS,
RESS,
ESWA,
EAAI,
AIR
and
CMC.
His
research
interests
mainly
include
deep
learning,
artificial
intelligence,
time-series
feature
mining,
fault
identification,
scheduling
optimization,
and
numerical
large
models.
In
the
past
five
years,
he
has
presided
over
or
participated
in
six
projects
funded
by
the
National
Research
Foundation
(NRF)
of
South
Korea,
and
Guizhou
provience.
He
has
published
sixteen
SCI-indexed
papers
as
the
first
author,
such
as
INS,
KBS,
ESWA,
and
JIMS.
He
received
awards
such
as
the
Excellent
Paper
Award
at
KSII
ICONI
2019
and
2020.
He
also
gave
an
invited
talk
at
the
Gyeongsang
Doctoral
Association
of
South
Korea.
Moreover,
he
serves
as
a
Guest
Editor
for
Algorithms,
a
journal
indexed
by
ESCI
and
EI.
Workshop 12
Summary:
The
rapid
integration
of
renewable
energy
sources,
electric
vehicles,
and
distributed
generation
into
modern
power
systems
has
introduced
unprecedented
complexity
and
uncertainty
in
grid
operation
and
planning.
Statistical
Relational
Artificial
Intelligence
(Statistical
Relational
AI,
or
SR-AI)
offers
a
promising
paradigm
for
modeling,
reasoning,
and
decision-making
in
such
complex
environments
by
combining
the
expressive
power
of
relational
representations
with
the
robustness
of
statistical
learning.
This symposium aims to bring together researchers, engineers, and practitioners to explore recent advances, methodologies, and applications of SR-AI in smart grid domains, including renewable energy forecasting, fault diagnosis, demand response optimization, and resilience enhancement under extreme weather events. We invite original contributions that address theoretical developments, algorithm design, system integration, and real-world deployment of SR-AI technologies in power systems.
This symposium aims to bring together researchers, engineers, and practitioners to explore recent advances, methodologies, and applications of SR-AI in smart grid domains, including renewable energy forecasting, fault diagnosis, demand response optimization, and resilience enhancement under extreme weather events. We invite original contributions that address theoretical developments, algorithm design, system integration, and real-world deployment of SR-AI technologies in power systems.
Keywords: Statistical Relational Artificial Intelligence; Smart Grid; Extreme Weather Events; Data-Driven Decision-Making
Xueqian
Fu
(Senior
Member,
IEEE)
is
the
Vice
President
of
the
IEEE
Smart
Village-China
Committee,
and
an
active
member
of
IEEE
Young
Professionals.
He
is
currently
an
Associate
Professor
at
China
Agricultural
University.
He
has
been
recognized
as
one
of
the
Stanford/Elsevier
Top
2%
Scientists
in
the
field
of
energy
for
both
the
2023
and
2024
rankings.
Prof.
Fu
received
his
B.S.
and
M.S.
degrees
from
North
China
Electric
Power
University
in
2008
and
2011,
respectively,
and
his
Ph.D.
degree
from
South
China
University
of
Technology
in
2015.
From
2015
to
2017,
he
was
a
Postdoctoral
Researcher
at
Tsinghua
University.
His
current
research
interests
include
statistical
machine
learning,
agricultural
energy
internet,
and
PV
system
integration.
He
serves
as
the
Deputy
Editor-in-Chief
for
Information
Processing
in
Agriculture
and
is
also
the
founding
chair
of
the
2025
IEEE
International
Symposium
on
the
Application
of
Artificial
Intelligence
in
Electrical
Engineering.
Xiurong
Zhang
received
the
B.E.
and
M.S.
degrees
from
Guangdong
University
of
Technology
and
Guangxi
Normal
University
in
2012
and
2016,
respectively,
and
the
Ph.D.
degree
from
Beihang
University,
Beijing,
China,
in
2023.
From
2023
to
2025,
she
was
a
Postdoctoral
Research
Fellow
with
the
College
of
Information
and
Electrical
Engineering,
China
Agricultural
University,
Beijing,
China.
In
2025,
she
joined
Beijing
City
University,
Beijing,
China,
where
she
is
currently
a
faculty
member.
Her
research
interests
include
wireless
communications
theory,
wireless
communication
systems,
and
cooperative
networks.
Workshop 13
Summary:
Artificial Intelligence of Things (AIoT) has emerged as a new paradigm of deep integration between artificial intelligence (AI) and the Internet of Things (IoT) to support intelligent services. Benefiting from recent advancements in deep neural networks (DNNs), AIoT networks are expected to facilitate various applications, including smart agriculture, intelligent transportation, and smart cities. Despite the potential of DNN models, running them directly on AIoT devices presents challenges due to their limited computation, storage, and energy resources, which hinder the deployment of large-scale DNN models for high-precision task inference. To address the limitations of devices, device-edge collaborative DNN inference (CDI) has been envisioned as one of the forefront technologies for completing task inference. CDI involves segmenting a DNN model into two parts with initial layers processed by devices and subsequent layers handled by edge servers. Using this approach, the core idea of CDI is to transmit intermediate feature data (IFD) extracted from raw task data instead of transmitting the raw data of inference tasks. This workshop aims to establish a platform for disseminating cutting-edge research findings in device-edge CDI. Authors are welcome to submit original papers on topics including, but not limited to:
- Fundamental theory and performance analysis for device-edge CDI
- Network architectures for device-edge CDI
- Model partitioning and resource allocation for device-edge CDI
- Digital twin and metaverse for device-edge CDI
- Security and privacy issues in device-edge CDI
- Performance trade-off for device-edge CDI
- Device-edge CDI for drones and vehicular networks
- Experimental demonstrations and prototypes
Keywords: Collaborative inference, computation offloading, covert communication, resource allocation, model partitioning.
Mengru Wu received the Ph.D. degree in communication and information systems from Northeastern University, Shenyang, China, in 2022. She is currently with the College of Information Engineering, Zhejiang University of Technology, Hangzhou, China. From 2021 to 2022, she was a Visiting Scholar with the School of Electrical Engineering, Korea University, Seoul, South Korea. Her current research interests include edge intelligence, UAV communications, and deep reinforcement learning for wireless communications. She serves as an Associate Editor for IEEE Transactions on Vehicular Technology and a TPC member for several conferences.
Bo Zhou received his B.E. degree in electronic engineering from South China University of Technology, China, in 2011 and his Ph.D degree from Shanghai Jiao Tong University, China, in 2017. He is currently a professor at the College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China. He was a postdoctoral associate at the Bradley Department of Electrical and Computer Engineering at Virginia Tech from Jan. 2018 to July 2021. His current research interests include age of information, spectrum sensing, and radio map. He received the best paper awards at IEEE GLOBECOM in 2018 and IFIP NTMS in 2019. He was recognized as an exemplary reviewer for IEEE Transactions on Communications in 2019 and 2020. He serves as an Associate Editor of IEEE Transactions on Machine Learning in Communications and Networking.
Dr. Huimei Han is an Associate Professor at the College of Information Engineering, Zhejiang University of Technology, P. R. China. She has been selected into the “Zhejiang Provincial Youth Talent Support Program” and the “Zhejiang University of Technology Youth Talent Program”. Huimei Han obtained her Ph.D. degree in telecommunication engineering from Xidian University, Xi‘an, P. R. China in 2019. From 2017 to 2018, she was with Florida Atlantic University (FAU), USA, as an exchange Ph.D. student. From 2021 to 2022, she was with School of Computer Science and Engineering, Nanyang Technological University(NTU), Singapore, as a Research Fellow. Her research interests include intelligent communications and multi-user access in wireless communication systems. She has published more than 20 papers in leading journals and conferences such as IEEE Transactions on Wireless Communications, IEEE Transactions on Communications, IEEE Transactions on Vehicular Technology, and IEEE Internet of Things Journal, and has received two best conference paper awards. She has presided over the Youth Project of the National Natural Science Foundation of China, the Project of the Zhejiang Provincial Natural Science Foundation, and the sub-project of the Key Project of the National Natural Science Foundation of China; participated in a number of General Projects of the National Natural Science Foundation of China; and taken part in compiling the White Paper on Intelligent Optimization and Operation of 5G/5G Private Networks.
Bo Xu received his B.S. degree in communication engineering and Ph.D. degree in communication and information systems from Nanjing University of Posts and Telecommunications in 2018 and 2022. He is currently with the faculty of the Jiangsu Key Laboratory of Wireless Communications, College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications. He won the Second Prize of Science and Technology of the China Communications Society in 2024. His research interests include distributed learning and space-air-ground integrated communication networks.
Biqian Feng received the B.S. degree in the school of electronic and information engineering from Soochow University, Suzhou, China, in Jun. 2017, and the Ph.D. degree in the department of electronic engineering, Shanghai Jiao Tong University, Shanghai, China, in Sep. 2023. He is currently a postdoctoral researcher at the department of mathematics and information technology, The Education University of Hong Kong, Hong Kong. He is a co-recipient of the IEEE ICC’2025 Best Paper Award. He served as a TPC member at IEEE Globecom, IEEE ICC, IEEE VTC, IEEE ICCC, IEEE ICCT. His research interests include optimization techniques and AI for wireless communications, reconfigurable intelligent surface, movable antenna, fluid antenna, semantic communication, vehicle-to-everything (V2X) communications, and edge intelligence.
Workshop 14
Summary:
The field of artificial intelligence is undergoing a profound shift, moving from static, disembodied models towards adaptive agents that learn through continuous interaction within their environments. This special issue aims to explore the crucial pathway from reinforcement learning (RL)—a framework for learning from trial-and-error and long-term reward maximization—to the emergence of genuine embodied intelligence.
We seek to investigate how RL agents can evolve from solving narrow tasks to becoming lifelong learners that acquire rich, adaptive, and robust skills. The core theme is the symbiotic relationship between an agent's learning algorithm (the "brain") and its physical or simulated embodiment (the "body"). We are particularly interested in how lifelong learning processes are shaped and accelerated by the physical constraints and opportunities provided by embodiment. Conversely, we welcome research on how embodiment presents unique challenges for RL, such as sample efficiency, safety, and credit assignment over extended timescales.
Topics of Interest:
We seek to investigate how RL agents can evolve from solving narrow tasks to becoming lifelong learners that acquire rich, adaptive, and robust skills. The core theme is the symbiotic relationship between an agent's learning algorithm (the "brain") and its physical or simulated embodiment (the "body"). We are particularly interested in how lifelong learning processes are shaped and accelerated by the physical constraints and opportunities provided by embodiment. Conversely, we welcome research on how embodiment presents unique challenges for RL, such as sample efficiency, safety, and credit assignment over extended timescales.
Topics of Interest:
- Advanced RL for Embodied Agents:Novel RL algorithms (e.g., hierarchical RL, meta-RL, inverse RL) tailored for long-term learning in physical systems.
- Sample Efficiency and Sim-to-Real Transfer:Techniques to drastically reduce the real-world interaction time needed for learning, including simulation, domain randomization, and world models.
- Lifelong and Continual Learning:Strategies for embodied agents to continuously acquire new skills without catastrophic forgetting, adapting to changing environments and goals over extended periods.
- The Role of Morphology:Research exploring how agent design (body shape, sensor placement, actuator properties) facilitates or constraints the learning of complex behaviors.
- Emergent Behaviors and Intelligence:Studies demonstrating how complex intelligent behaviors emerge from the synergy of RL
Keywords: Reinforcement learning, Lifelong learning, Embodied intelligence
Jinwei Zhao received the Master degree in Computer Software and Theory from Northwest University, China,
and the Ph.D. degree in Computer Software and Theory from Xi'an Jiaotong University, China, in 2007 and 2012, respectively.
In 2012 he joined Xi’an University of Technology, where he is currently associate professor in Computer
Science and Technology at the Faculty of Computer Science and Engineering.
His current research activity is on machine Learning, with the main focus on deep neural network and graph neural network. In particular, he is interested in the lifelong learning and the logical interpretation method and the physical interpretation method of deep neural network and graph neural network. From an applicative point of view, he focuses on data mining, pattern recognition, fault diagnosis and computer vision.
He has been a senior member of the China Computer Society and the member of the China Artificial Intelligence Society.
His current research activity is on machine Learning, with the main focus on deep neural network and graph neural network. In particular, he is interested in the lifelong learning and the logical interpretation method and the physical interpretation method of deep neural network and graph neural network. From an applicative point of view, he focuses on data mining, pattern recognition, fault diagnosis and computer vision.
He has been a senior member of the China Computer Society and the member of the China Artificial Intelligence Society.
Bo Fu obtained his Bachelor's degree in Mathematics in 2005 and Master's degree in Electric Engineering in 2008, both from Shaanxi Normal University. In 2015, he earned his Ph.D. in Computer Science from the University of Kentucky, USA. He currently serves as an Associate Professor in the School of Computer Science and Engineering at Xi'an University of Technology. During his professional career in both the United States and China, he has led and participated in numerous scientific research projects, resulting in several issued patents. His research interests lie in intelligent robots and computer vision. He has authored over thirty papers in international journals and conferences.
Workshop 15
Summary:
Artificial intelligence (AI) is transforming next-generation intelligent transportation systems (ITS), enabling smarter perception, analysis, and management of complex transportation infrastructures. This workshop focuses on AI-driven solutions that leverage advanced data integration techniques, including multi-modal and multi-view approaches, to enhance traffic safety, infrastructure reliability, and operational efficiency. We invite contributions on novel AI methodologies, intelligent sensing, and practical applications in ITS, highlighting both theoretical innovations and real-world deployments.
Keywords: Artificial Intelligence (AI);Intelligent Transportation Systems (ITS);Multi-Modal / Multi-View Approaches;Intelligent Sensing;Data Integration；Infrastructure Monitoring
Prof. Li Wei is Associate Dean of the Institute of Data Science and Artificial Intelligence at Chang’an University. His research focuses on intelligent sensing for transportation infrastructure, including AI-driven large models, multi-modal and multi-object tracking, intelligent instrument development, and 3D imaging and reconstruction. He serves on the Interdisciplinary Committee of the World Transport Congress, is a council member of the China Highway Society’s Maintenance and Management Division, and a lifetime member of the Chinese Association for Artificial Intelligence. Dr. Li has published over 300 high-quality papers, reviews for top international AI journals, and has been recognized as a Top 5% Highly Cited Scholar in China and a High-Contributing Author in Wiley China Open Science.
Prof. Han-Ye Liu is Associate Dean at the School of Information Engineering, Yulin University.His research focuses on 3D particle characterization and artificial intelligence applications. He serves as Vice Chair of the Computer Vision Committee of the Shaanxi Computer Society, and as a committee member of the Technical Committee on Machine Vision of the China Society of Image and Graphics（CSIG） and Pattern Recognition Committee on the Chinese Association for Artificial Intelligence(CAAI), respectively.
Workshop 16
Summary:
With the rapid development of intelligent manufacturing, visual inspection software,
as a core technology of automated production lines, faces multiple challenges including
complex industrial scenarios, mechanical aging, computational resource consumption, and cybersecurity.
Although deep learning models have demonstrated advantages in detection accuracy and robustness,
their adaptability in dynamic industrial scenarios still needs to be enhanced. The iterative development
of visual inspection technology, from traditional image processing to deep learning models, and the
evolution of software architecture towards networking and cloud-based solutions, bring both opportunities
and challenges to this field. Researching adaptive enhancement methods for visual inspection models,
optimizing software architecture, and improving their timeliness and security are of great significance
for enhancing the intelligence level of manufacturing and promoting the development of advanced
manufacturing industry chains. In addition, developing security testing and defense strategies for deep
learning models, as well as visual inspection software for high-speed production lines, are current hot
research topics. Moreover, strengthening the research on key technologies of visual inspection software
can provide technical support for the intelligent transformation and upgrading of manufacturing, enhance
the competitiveness of the visual inspection industry, and promote the construction of a modernized
industrial system. This field is in urgent need of in-depth exploration to meet the demands of high
precision, high efficiency, and high security in industrial production and to promote the sustainable
development of manufacturing.
Keywords: Adaptive Enhancement, Visual Inspection Models, Industrial Scenarios
Xin Nie holds a Ph.D. in Computer Software and Theory from Wuhan University.
He is currently an Associate Professor at the School of Computer Science and Engineering,
Wuhan Institute of Technology, focusing on cutting-edge research in Software Engineering
and Artificial Intelligence. He has extensive experience in software R&D, particularly in
the field of integrated electronic information systems. He has published numerous high-quality
academic papers and holds several patents and software copyrights. He is actively involved in
academic organizations such as IEEE, CCF, and CAAI, and serves on the editorial boards and committees
of various international conferences and journals. His research interests include Intelligent
Optimization Algorithms, Evolutionary Computation, Cloud Computing, Machine Learning, and Deep
Learning.
Ms. Yifei Wang, a Researcher at the University of Pennsylvania’s School of
Design in the United States and a master’s graduate in Integrated Product Design
and Human-Computer Interaction, has made significant strides in the interdisciplinary
realm of design and computer science. Her research, which explores human-computer
interaction, intelligent system interfaces, IoT interaction experiences, AI-assisted
design, and future product systems, is distinguished by its innovative approach and
practical applications. Ms. Wang’s work has been recognized with prestigious
international awards, including the Red Dot Award and MUSE Award, and has been
showcased in numerous global design exhibitions. She has worked with multiple Fortune
500 companies and high-tech startups, contributing to projects across diverse fields
including fintech, new energy, B2B2C SaaS, and smart IoT. These accolades underscore
her contributions to advancing the integration of design and technology, positioning
her as a leading figure in the development of intelligent interaction solutions.
Workshop 17
Summary:
The convergence of AI, computer vision, and robotics is revolutionizing manufacturing, giving rise to the Industrial Metaverse—a digital twin of the physical production world. This workshop explores the critical role of computer vision as the enabling technology for this transformation. We will focus on how visual perception allows embodied AI agents (robots) to understand, interact with, and optimize complex physical processes in real-time. Key topics include vision for robotic manipulation and assembly, anomaly detection in quality control, 3D reconstruction of dynamic environments for digital twins, and human-robot collaboration through visual understanding. The goal is to bridge the gap between cutting-edge computer vision research and the demanding, real-world requirements of next-generation (Smart Manufacturing).
Keywords: computer vision, robotics, Smart Manufacturing, AI
Guoqiang Han is an Associate Professor at Fuzhou University and a recognized Fujian Provincial High-Level Talent (Category C). His research interests span computational imaging, deep learning, intelligent sensing systems, and artificial intelligence applications in robotics and industrial IoT. He received his Ph.D. in Instrument Science and Technology from Xi’an Jiaotong University, conducted postdoctoral research at the Chinese Academy of Sciences Haixi Institute, and was a visiting scholar at the Boston University Photonics Center, USA. Dr. Han has led several national and provincial projects and published extensively in SCI-indexed journals, including multiple papers in top-tier Q1 journals. With interdisciplinary expertise across mechanical engineering, instrumentation, materials science, and computer science, he has made significant contributions to image reconstruction, compressed sensing, and the integration of deep learning with imaging and signal processing. His work emphasizes bridging theoretical methods with practical applications, providing a solid foundation for advancing intelligent technologies.
Workshop 18
Summary:
Accurately predicting crowd flow is vital in urban computing but challenging due to complex spatio-temporal dependencies and external factors like weather and POIs. We propose DHSTNet, a dynamic deep spatio-temporal neural network that integrates CNNs and LSTMs for fine-grained, region-level forecasting. DHSTNet models recent, daily, weekly, and external patterns, adaptively weighting them to generate robust predictions. Experiments demonstrate its effectiveness in capturing diverse temporal features and external influences for real-time urban crowd flow prediction.
Keywords: Intelligent Transportation Systems, Traffic Flow Prediction, Spatio-Temporal Data Mining, Machine Learning, Deep Learning
Ahmad Ali received the Ph.D. degree from Shanghai Jiao Tong University, China,
and is currently a Postdoctoral Researcher with the Department of Computer Science and Engineering,
Shenzhen University, China. His research interests include deep learning, big data analytics, data mining,
urban computing, cloud computing, and fog computing. He has served as a Technical Program Committee member for
many international conferences, including the 31st International Conference on Parallel and Distributed Systems
(ICPADS 2025), and as a Guest Editor for MDPI journals (2025–present). He is also an active reviewer, having evaluated
more than 1,470 research articles for leading SCI-indexed journals such as Information Sciences, Multimedia Tools and
Applications, Neural Computing and Applications, IEEE Access, IEEE Internet of Things Magazine, and the Journal of
Healthcare Engineering.
Workshop 19
Summary:
Security and privacy protection in big data are of paramount importance in today’s
digital landscape. As organizations increasingly rely on vast amounts of data for
decision-making and innovation, the potential risks associated with data breaches
and privacy violations have grown significantly. Protecting sensitive information
not only safeguards individual privacy rights but also maintains trust in data-driven
systems and ensures compliance with regulatory requirements.
The main research directions in this field include: data encryption techniques that enable secure processing of encrypted data; privacy-preserving data mining and machine learning methods that extract valuable insights without compromising individual privacy; differential privacy frameworks that provide mathematical guarantees of privacy protection; secure multi-party computation protocols that allow collaborative analysis while maintaining data confidentiality; and blockchain-based solutions for decentralized and tamper-resistant data management. Additionally, research on regulatory compliance frameworks and ethical guidelines for big data usage continues to evolve, addressing the growing need for responsible data governance in an increasingly connected world.
The main research directions in this field include: data encryption techniques that enable secure processing of encrypted data; privacy-preserving data mining and machine learning methods that extract valuable insights without compromising individual privacy; differential privacy frameworks that provide mathematical guarantees of privacy protection; secure multi-party computation protocols that allow collaborative analysis while maintaining data confidentiality; and blockchain-based solutions for decentralized and tamper-resistant data management. Additionally, research on regulatory compliance frameworks and ethical guidelines for big data usage continues to evolve, addressing the growing need for responsible data governance in an increasingly connected world.
Keywords: privacy protection；data encryption techniques；blockchain
Deng Xiaohong, Ph.D., Professor, Master’s Supervisor, and Senior Member of CCF. He is
recognized as a Leading Young and Middle-aged Academic (Professional) in Jiangxi Province’s higher
education institutions and was named among the Top 1% of Highly Cited Scholars by CNKI in 2024. His
main research directions include network and information security and blockchain. He has led and completed
over 10 projects at or above the provincial and ministerial level (including one project from the National
Natural Science Foundation of China and two from the Provincial Natural Science Foundation). As the first or
corresponding author, he has published over 20 papers (10 indexed by SCI/EI/CSSCI), one monograph, and edited
three textbooks. He holds seven patents and software copyrights. Under his guidance, students have won more than
20 awards in various academic competitions at or above the provincial level (including one national first prize).
He has long served as a reviewer for high-level domestic and international journals such as “Blockchain: Research
and Applications,” “Computer Engineering and Science,” and “Computer Applications,” and currently serves as an e
ditorial board member of “Computer Application Research.”
Workshop 20
Summary:
The rapid evolution of artificial intelligence has revealed the limitations of single-modal
visual detection under complex real-world conditions, including low illumination, adverse weather,
occlusion, and cross-domain variations. Multi-modal object detection has emerged as a promising
solution, leveraging RGB, infrared, LiDAR, and other heterogeneous sensing data to achieve higher
accuracy, robustness, and adaptability. This workshop aims to explore the next generation of
multi-modal perception techniques, focusing on four key aspects: cross-modal feature collaboration,
robust fusion mechanisms, modality adaptation, and lightweight design. By bridging theoretical
breakthroughs with real-world deployment, the workshop will provide a platform for researchers
and practitioners to exchange insights, discuss challenges, and present novel methodologies.
Application domains of particular interest include autonomous driving, smart agriculture, and
intelligent security, where robust perception is essential for safety and reliability.
The workshop ultimately seeks to promote multi-modal object detection as a fundamental paradigm
for future visual intelligence.
Keywords: Multi-Modal Object Detection; Cross-Modal Learning; Robust Fusion Mechanisms; Modality Adaptation; Lightweight Models; Visual Perception; Autonomous Driving; Intelligent Security;
Gao Pan, male, Ph.D. graduate student, professor, Ph.D./M.S. supervisor, deputy dean of
College of Information Science and Technology, member of China Computer Society, member
of China Artificial Intelligence Society, technical committee member of IEEE IES China Intelligent
Farming and Forestry, and board member of Xinjiang Society of Colleges and Universities Computer Education.
He is the backbone talent of Corps' scientific and technological innovation, and the leading disciplinarian
of Shihezi University. He has presided over 10 projects at provincial and ministerial levels and above, and
10 projects at divisional and departmental levels; published 45 papers as the first and corresponding author;
obtained 28 intellectual property rights such as invention patents, utility model patents, and softwritings;
and was awarded 20 teaching and scientific and technological awards, including the first prize for scientific
and technological progress of the Corps, and the second prize for the teaching achievements of the Autonomous
Region.
Workshop 21
Summary:
Complex industrial systems, such as steel manufacturing, semiconductor fabrication,
aerospace assembly, and port transportation, are characterized by high-dimensional interactions, dynamic uncertainties,
and heterogeneous data structures. Traditional approaches often struggle to balance accuracy, interpretability, and computational
efficiency in such scenarios. This workshop aims to bridge the gap by exploring cutting-edge data-driven methodologies that integrate
machine learning, causal inference, and optimization
theories to address the modeling, control, and decision-making challenges in complex systems. Key topics will include:
- (1) Adaptive modeling for dynamic industrial processes
- (2) Real-time optimization under uncertainty
- (3) Causal intelligence for interpretable decision-making
- (4) Operations research for the optimization of complex systems
- (5) Innovative applications of generative AI for complex manufacturing systems
Keywords: Data-Driven Modeling; Complex Systems Optimization; Causal Inference in Industry
Wei Qin is the Associate Chair of the Department of Industrial Engineering and Management
at Shanghai Jiao Tong University. His research primarily focuses on complex systems and machine intelligence.
His contributions have earned him prestigious awards such as the Special Prize for Scientific and Technological Progress
from the China Ports & Harbors Association and the First Prize of Shanghai Science and Technology Progress Award. With over
50 SCI-indexed papers published as the first or corresponding author, he serves as an Associate Editor for Journal of
Intelligent Manufacturing (JIM, an SCI Q1 TOP journal by the Chinese Academy of Sciences) and Cleaner Engineering and
Technology (CLET, a JCR Q1 journal), as well as an editorial board member for multiple other journals. He has authored
several textbooks and monographs, including Big Data Analytics in Production and Service Systems and Machine Intelligence
Theories and Methods for Smart Manufacturing.
Yan-Ning Sun is a Lecturer and Master's Supervisor at the School of Mechatronics
Engineering and Automation, Shanghai University. His research focuses on quality consistency
control in complex manufacturing systems, health assessment of large-scale industrial equipment,
and applications of machine learning, complex networks, causal analysis, and AI large language
models in manufacturing. He has led 5 research projects including the National Natural Science
Foundation and Shanghai Young Talents Initiative, and contributed to 8 key national and
provincial-level projects. With over 40 academic publications, he has authored 15
first/corresponding-author papers in top journals like Engineering, Journal of Manufacturing
Systems, and Engineering Applications of Artificial Intelligence. His achievements include
5 national invention patents, 7 software copyrights, and the First Prize of Shanghai
Science and Technology Progress Award.
Jin-Hua Hu is a Lecturer at the School of Construction Machinery, Chang’an University.
Her research focuses on network modeling, assembly schedule monitoring, and intelligent workshop
scheduling methods for aircraft final assembly in the context of intelligent manufacturing. As a key
technical contributor, she has participated in multiple projects on aircraft final assembly scheduling
optimization. She has published five papers in leading journals, including the Journal of Manufacturing
Systems (JCR Q1, IF:12.1), Advanced Engineering Informatics (JCR Q1, IF:8.0), and Computers & Industrial
Engineering (JCR Q1, IF:6.7).
Workshop 22
Summary:
Effectively understanding and forecasting spatiotemporal dynamics is crucial for advancing
scientific discovery, decision-making, and sustainable development across diverse domains.
This workshop explores the next generation of methods and applications at the intersection of
spatiotemporal data science and AI, with three central themes:
- Spatiotemporal Data Modeling: Novel frameworks for representing and forecasting complex systems, leveraging transfer learning, transformer architectures, diffusion models, and emerging foundation models.
- Interpretable Deep Learning: Approaches that move beyond predictive accuracy to incorporate model-driven neural networks and deliver white-box insightsfor domain-specific applications.
- Multimodal Large Language Models: Advances in LLMs that fuse diverse modalities such as text, imagery, and remote sensing, enabling spatiotemporal understanding and supporting a wide range of domain applications.
Keywords: Spatiotemporal Data Modeling, Interpretable Deep Learning, Multimodal LLMs
Dr. Wenwu Gong is a Postdoctoral Researcher in the Department of Statistics and Data
Science at Southern University of Science and Technology (SUSTech), supported by the
prestigious SUSTech Presidential Postdoctoral Fellowship. His research focuses on Interpretable
Neural Networks and Spatiotemporal LLMs. Dr. Gong has led multiple research projects, including grants
from the China Postdoctoral Science Foundation and the SUSTech Innovation and Entrepreneurship Fund.
He has published over ten papers in international journals and conferences, and his contributions have
been recognized with honors such as the National Scholarship for Doctoral Students and the Guangdong
Overseas Young Talents Program.
Workshop 23
Summary:
With the rapid growth of big data and artificial intelligence, the cybersecurity landscape is facing
unprecedented challenges. Malicious code, adversarial traffic, and disinformation campaigns are evolving
at an accelerating pace, rendering traditional defense mechanisms increasingly inadequate. At the same time,
privacy-preserving computation and secure collaborative learning have become essential for ensuring
trustworthy AI applications.
This workshop aims to bring together researchers and practitioners from academia, industry, and government to share novel theories, methodologies, and applications that address pressing security and privacy issues in the era of big data and AI. Topics of interest include, but are not limited to:
This workshop aims to bring together researchers and practitioners from academia, industry, and government to share novel theories, methodologies, and applications that address pressing security and privacy issues in the era of big data and AI. Topics of interest include, but are not limited to:
- Malicious Code and Malware Detection: AI-powered static and dynamic analysis, behavior-based detection, and adversarial evasion.
- Malicious Traffic Detection: Intelligent intrusion detection, anomaly detection in network flows, and deep learning for encrypted traffic analysis.
- AI-based News and Public Opinion Detection: Detecting misinformation, fake news, and coordinated disinformation campaigns using natural language processing and graph learning.
- Secure Federated Learning: Privacy-preserving distributed learning, adversarial robustness in federated systems, and defenses against poisoning and backdoor attacks.
- Privacy-Preserving Computation: Secure multi-party computation, homomorphic encryption, differential privacy, blockchain-based approaches, AI-Enabled cryptographic techniques, and cryptography-defined AI security.
Keywords: Malware and Malicious Code Detection, Secure Federated Learning, Privacy-Preserving Computation, Mutual Influence between Cryptography and AI
Chuan Zhang received his Ph.D. degree in computer science
from Beijing Institute of Technology,Beijing, China, in 2021. From Sept. 2019
to Sept.
2020, he worked as a visiting Ph.D. student with theBBCR Lab, Department of
Electrical and Computer Engineering, University of Waterloo, Canada.
He is currently an assistant professor at School of Cyberspace
Science and Technology, Beijing Institute of Technology. His
research interests include secure data services in cloud computing,
applied cryptography, machine learning, and blockchain.
Yijing Lin is a postdoc researcher with the State Key Laboratory of Networking and
Switching Technology, Beijing University of Posts and Telecommunications (BUPT),
where she received the Ph.D degree in 2024. She has published more than 20 papers including WWW,
IJCAI, IEEE TSC, TCOM, TNSE, TVT etc. Her publications include ESI highly cited papers, IEEE ComSoc
Best Readings and received four Best Paper Awards including IEEE OJCS, IEEE IWCMC, IEEE-CCF Service
Computing Technical Committee. Her current research interests include blockchain and data unlearning.
Qing Fan is an Associate Professor at North China Electric Power University and
she received the PhD degree in applied mathematics from the School of Mathematics and Statistics,
Wuhan University, Wuhan, China, in 2022. From 2022 to 2024, she worked as a Postdoctoral Research
Fellow with the School of Cyberspace Science and Technology, Beijing Institute of Technology. Her
research interests lie in applied cryptography, information security, and data privacy protection.
She has published over twenty papers, including first- or corresponding-author papers in leading journals
such as IEEE Transactions on Services Computing, IEEE Transactions on Information Forensics and Security,
and IEEE Transactions on Industrial Informatics. She actively contributes to the academic community as a
guest editor, technical program committee (TPC) chair, such as KSEM, ICA3PP and program committee member
for international conferences. She also serves as a reviewer for high-impact journals or proceedings,
including IEEE Transactions on Dependable and Secure Computing, the IEEE Communications Surveys and
Tutorials, and the Web Conference 2025. Her academic credentials and professional service make her a
strong candidate for workshop chair responsibilities.
Workshop 24
Summary:
This workshop focuses on the optimization techniques for deploying deep learning
models on embedded systems with limited computational and energy resources. Key topics
include model compression, quantization, pruning, hardware-aware neural architecture search,
and AI acceleration frameworks. The workshop aims to bring together researchers and
practitioners from academia and industry to discuss challenges and solutions for achieving
efficient, real-time, and low-power AI inference on edge devices.
Keywords: Deep Learning Model, AI acceleration, Embedded System
Rui Xu received the Ph.D. degree in Computer of Science Technology from East
China Normal University, Shanghai, China, in June 2023. She is a postdoctoral
researcher at the City University of Hong Kong from August 2023 to August 2024.
Now, she is an associate professor in the college of information science and technology
of Jinan University. Her research interests include embedded systems, non-volatile memory,
optimization algorithms, LLM optimization, and computer architecture.
Workshop 25
Summary:
Large Language Model (LLM) represents the latest developments in Artificial Intelligence (AI) technology.
It is forging a new security paradigm, including enhancing traditional cybersecurity and exposing its own inherent security risks.
For cybersecurity, LLM enables a shift from reactive defense to intelligent, proactive, and adaptive security mechanisms. Many other products,
like knowledge graphs and AI agents, are demonstrating great potential in enhancing threat detection, attack path reasoning, automated
penetration testing, and vulnerability discovery. Meanwhile, the widespread adoption and remarkable success of LLM have also positioned
it as a new target for attackers. There exist many vulnerabilities arising from the model structure, application algorithms, data, and
deployment environments. The most important problems include hallucination, biases, privacy leakage, and system failures. Ensuring LLM
robustness, reliability, and trustworthiness has emerged as a new hot research field.
This workshop aims to bring together researchers, practitioners, and industry experts to explore interesting security issues related to LLM. We invite contributions that present novel methods, practical experiences, or insightful ideas on the following topics (include but are not limited to).
This workshop aims to bring together researchers, practitioners, and industry experts to explore interesting security issues related to LLM. We invite contributions that present novel methods, practical experiences, or insightful ideas on the following topics (include but are not limited to).
- LLM-driven threat detection and anomaly recognition
- Intelligent attack path reasoning and predictive defense
- LLM-enhanced automated penetration testing and red/blue team exercises
- LLM-enhanced cyber vulnerability discovery, prioritization, automated verification, and intelligence analysis
- LLM-assisted cyber vulnerability patching and remediation strategies
- Robustness and adversarial defense in LLM
- Data integrity and privacy-preserving learning in LLM
- Verification, validation, and testing of LLM security
- Risk identification, assessment, and mitigation in LLM systems
- Case studies and real-world deployment experiences in LLM security and risk management
Keywords: LLM-enhanced cyber security, LLM-enhanced attacking, LLM-enhanced defense, LLM inherent security, trustworthy LLM, LLM adversarial and defense
Hui Lu is a national-level distinguished talent, and currently serves as Dean of the Institute of Cyberspace Advanced Technology at Guangzhou University, and Director of the Guangdong Key Laboratory of Cyber Security for Critical Infrastructure. He holds the positions of Secretary-General of the China Cyberspace Emerging Technology Security Innovation Forum and Head of the Competition and Exercise Office of the China Cyberspace Security Association. His main research focuses on intelligent network attack and defense, industrial internet security, and artificial intelligence security. As principal investigator, he has led numerous national key research and development projects, grants from the National Natural Science Foundation of China, projects under the Guangdong Provincial Key Areas R&D Program, and security-specific projects for China Southern Power Grid. His research outcomes have been published in over 60 papers in domestic and international journals and conferences, alongside more than 40 patents. His awards and honors include the Guangdong Provincial Science and Technology Progress Award (Second Prize), the Guangdong Provincial Philosophy and Social Sciences Outstanding Achievement Award (Second Prize), the Guangdong Provincial Outstanding Online Teaching Case Award during the pandemic phase, the Outstanding Case Award for Industry-Academia Collaboration in Cyberspace Security Education, the "Typical Practice Case in AI Security" from the China Cyberspace Security Association, and the China Industry-University-Research Cooperation Achievement Award (Second Prize).
He participated in the development of the "Shield Cube-Four Honeypots" active defense system. For major event cybersecurity assurance, the system ensured the platform security for the 24th Beijing Winter Olympics, the Hangzhou Asian Games, the Chengdu Universiade, and the Harbino Asian Winter Games. It has also supported cybersecurity attack-defense exercises for the Ministry of Education and the Guangdong Provincial "Yuedun" exercises, receiving multiple letters of appreciation from key national departments.
He participated in the development of the "Shield Cube-Four Honeypots" active defense system. For major event cybersecurity assurance, the system ensured the platform security for the 24th Beijing Winter Olympics, the Hangzhou Asian Games, the Chengdu Universiade, and the Harbino Asian Winter Games. It has also supported cybersecurity attack-defense exercises for the Ministry of Education and the Guangdong Provincial "Yuedun" exercises, receiving multiple letters of appreciation from key national departments.
His main research interests include Data Security, Cyberspace Security, High-Performance Computing, and Deep Learning. He has published over 30 papers in top-tier international conferences and journals. He has led 6 research projects, including those funded by the National Natural Science Foundation of China, the China Postdoctoral Science Foundation (Special Funding), and the Shandong Outstanding Postdoctoral Innovation Program. He has developed two open-source big data processing systems, with research outcomes applied in practical scenarios such as China Mobile’s “Big Cloud” product, the exascale domestic supercomputing internet, and marine big data analytics. He has won Shandong Provincial Science and Technology Progress Award (First Prize), China Computer Federation (CCF) Outstanding Doctoral Dissertation Award, and CCF Natural Science Award (Second Prize).
Daxin Zhu is Vice Dean and Professor at the School of Mathematics and Computer Science, Quanzhou Normal University. He also serves as a Senior Member of the China Computer Federation (CCF), Director of the Fujian Provincial Key Laboratory of New Technologies for Big Data Management and Knowledge Engineering, Vice President of the Fujian Computer Society, Executive Director of the Fujian Artificial Intelligence Society, and Chief Supervisor of the Quanzhou Artificial Intelligence Society. His research interests include Big Data Technology Applications, Data-Intensive Computing Methods and Applications, and Artificial Intelligence Applications.
Workshop 26
Summary:
The convergence of generative AI and edge computing is heralding a new paradigm for intelligent,
responsive, and privacy-preserving applications. This session, "Generative AI at the Edge: Systems, Optimizations,
and Real-World Applications," delves into the core challenges and transformative opportunities of deploying powerful
generative models beyond the cloud, directly onto resource-constrained edge devices.
We will move beyond theoretical potential to explore the tangible systems and architectural innovations required to make this feasible. Discussions will cover specialized hardware, efficient software stacks, and distributed frameworks that enable generative AI to operate in low-latency, often disconnected, environments. A central focus will be on cutting-edge optimization techniques, including model quantization, knowledge distillation, neural architecture search, and dynamic inference, which are crucial for shrinking large models to fit the computational, memory, and power budgets of the edge.
Finally, the session will showcase compelling real-world applications that are already being redefined by this synergy. Attendees will learn about on-device AI for personalized healthcare, real-time video synthesis in autonomous systems, private generative assistants, and adaptive industrial IoT solutions. This session is essential for researchers and practitioners aiming to understand and build the next generation of intelligent applications where data is generated and consumed at the edge.
We will move beyond theoretical potential to explore the tangible systems and architectural innovations required to make this feasible. Discussions will cover specialized hardware, efficient software stacks, and distributed frameworks that enable generative AI to operate in low-latency, often disconnected, environments. A central focus will be on cutting-edge optimization techniques, including model quantization, knowledge distillation, neural architecture search, and dynamic inference, which are crucial for shrinking large models to fit the computational, memory, and power budgets of the edge.
Finally, the session will showcase compelling real-world applications that are already being redefined by this synergy. Attendees will learn about on-device AI for personalized healthcare, real-time video synthesis in autonomous systems, private generative assistants, and adaptive industrial IoT solutions. This session is essential for researchers and practitioners aiming to understand and build the next generation of intelligent applications where data is generated and consumed at the edge.
Keywords: Generative AI, Edge Computing, Model Optimization
Miaojiang Chen received the Ph.D. degree in computer science from Central South University.
He is currently an Assistant Professor at the School of Computer and Electronic Information, Guangxi University,
China, and served as a Research Fellow at the University of Maryland, Baltimore County (UMBC). He has authored/co-authored
over 40 publications, with over 3000 citations. His research interests include deep reinforcement learning, the Internet of
Things, edge computing, transfer learning, and intelligent optimization.
Wenjing Xiao received the bachelor-straight-to-doctorate degree with Huazhong
University of Science and Technology, Wuhan, China. She is currently an Assistant
Professor of the School of Computer and Electronic Information, Guangxi University,
China. She has published more than 30 papers in top journals or conferences, with
over 700 citations. Her research interests include cloud computing, Internet of
Things, and cognitive computing.