IRTFOPEN has two meetings at IETF-125:
Chairs: Dirk Kutscher, Antoine Fressancourt
The goal of this session is to identify and discuss research challenges
for the IRTF at the intersection of AI systems and internetworking. As
AI workloads become increasingly distributed across devices, clusters,
datacenters, and administrative domains, they raise new questions for
networking research, including architecture, transport, reliability,
resource disaggregation, communication abstractions, and the
implications of AI agents as communicating entities. The session is
intended as a forum to help crystallize the most important open problems
and possible research directions for the IRTF. This framing builds on
the earlier 1st Workshop on Inter-networking Challenges for AI (INET4AI
2025), co-located with CoNEXT
2025 that discussed networking
challenges arising from large-scale distributed generative AI workloads.
| No. | Title | Speaker | Time |
|---|---|---|---|
| 1 | Welcome | Chairs | 05 min |
| 2 | Disaggregated Architectures for Large Model Inference | Mingxing Zhang, Tsinghua University | 25 min |
| 3 | Reliability Engineering Challenges in Networking for AI | Hong Xu, CUHK | 25 min |
| 4 | On AI Agent Networking | Lixia Zhang, UCLA | 25 min |
| 5 | Discussion on Internetworking Research Challenges for AI | All | 40 min |
Please remember that all sessions are being recorded.
Mingxing Zhang is a
Tenure-track Assistant Professor at Tsinghua University, focusing
primarily on memory system research. Initiator of the open-source
KVCache.AI projects Mooncake and KTransformers. Authored over 30 papers
in prestigious international conferences and journals such as OSDI,
SOSP, ASPLOS, HPCA, and EuroSys, including awards such as Best Paper at
FAST, Distinguished Paper at SIGSOFT, and the first OSDI paper from a
domestic Chinese university. Recipient of the ChinaSys Rising Star and
Outstanding Doctoral Dissertation Awards, IEEE TCSC Outstanding
Dissertation Award, selected into the China Association for Science and
Technology’s Young Talent Support Project. Previously served as Chief
Algorithm Technology Expert and Dean of the Innovation Research
Institute at Sangfor Technologies, where incubated products have been
deployed to tens of thousands of customers.
Hong Xu is an Associate
Professor in Department of Computer Science and Engineering, The Chinese
University of Hong Kong. His research area is computer networking and
systems, particularly machine learning systems and data center networks.
His work has received best paper awards from ACM SIGCOMM 2022, IEEE ICNP
2023 and 2015, among others. He has also received multiple collaborative
research awards from industry and distinguished reviewer/editor awards
from the community. He is a senior member of ACM and IEEE, and an
associate editor of ACM TOCS and IEEE TNSE.
Lixia Zhang received her PhD in
computer science from MIT and worked at the Xerox Palo Alto Research
Center as a member of the research staff. She is now a professor in the
Computer Science Department at UCLA, where she holds the UCLA Postel
Chair in Computer Systems. She is a fellow of the ACM and IEEE, a
recipient of the ACM SIGCOMM Lifetime Achievement Award and the IEEE
Internet Award, an inductee into the Internet Hall of Fame, and a member
of the National Academy of Engineering. Since 2010, she has led the
design and development of Named Data Networking (NDN), a new Internet
protocol architecture (http://named-data.net/).
Chair: Dirk Kutscher
The Applied Networking Research Prize
(ANRP) is awarded to recognise the best
recent results in applied networking, interesting new research ideas of
potential relevance to the Internet standards community, and upcoming
people that are likely to have an impact on Internet standards and
technologies, with a particular focus on cases where these people or
ideas would not otherwise get much exposure or be able to participate in
the discussion.
| No. | Title | Speaker | Time |
|---|---|---|---|
| 1 | Welcome | Chair | 15 min |
| 2 | Designing Transport-Level Encryption for Datacenter Networks | Tianyi Gao, University of Edinburgh | 40 min |
| 3 | ACE: Sending Burstiness Control for High-Quality Real-Time Communication | Xiangjie Huang, HKUST | 40 min |
| 4 | Discussion on Internetworking Challenges for AI | Chair, Antoine Fressancourt | 25 min |
Tianyi Gao is a PhD student in the School of
Informatics at the University of Edinburgh, supervised by Prof. Michio
Honda. He received MSc in Computer Science at the University of
Edinburgh in 2022 with Class Prize. He has also interned under
Prof. Guangyu Sun at the Advanced Institute of Information Technology
(AIIT), Peking University in 2020.
His research interests lie in designing high-performance and secure
datacenter networking systems. He is currently working on SMT, a
datacenter transport protocol with transport-level encryption. SMT is
designed as a generic, secure transport that can provide strong
confidentiality while maintaining low latency and high throughput for a
wide range of datacenter applications. He has also contributed to XO, a
framework for remote TCP connection offload that improves scalability
and reduces host overhead.
Xiangjie
Huang
is a first-year PhD student at the Hong Kong University of Science and
Technology, advised by Professor Zili Meng. Prior to starting his
doctoral studies, he obtained his master’s degree with a focus on video
coding. He is deeply passionate about advancing next-generation
real-time communication systems and improving them in every possible
aspect.