NetFabAI

    Scope of the workshop

    1st International Workshop on Networking and Fabric Architectures for AI Systems (NetFabAI)

    Recent advances in Artificial Intelligence have been driven not only by new models and algorithms, but also by innovations in systems, infrastructure, and software stacks. This workshop focuses on the design, implementation, and evaluation of systems that enable, accelerate, and scale AI workloads. We aim to bring together researchers and practitioners from systems, machine learning, and interdisciplinary communities to discuss challenges and opportunities at the intersection of AI and systems.

    • Explore system and network design approaches for supporting AI workloads at scale, with emphasis on fabrics, interconnects, and data movement.
    • Discuss challenges posed by communication-intensive and latency-sensitive AI applications, including synchronization, collectives, and tail latency.
    • Share lessons from academic and industrial efforts in building AI-oriented networking and fabric solutions.
    • Foster collaboration across networking, systems, and AI communities toward scalable and efficient connectivity for AI systems.
    • Examine emerging architectures and protocols such as scale-up/scale-out fabrics, UET, UAL, and CXL.
    • Promote evaluation and simulation methodologies that enable reproducible research on AI-scale infrastructure.

    This is the first edition of NetFabAI workshop in conjunction with the IFIP NETWORKING conference.

    This workshop will be held exclusively in-person.

    Topics of interest:

    Topics of interest include, but are not limited to, the following:

    • System architectures for training and inference of AI models
    • Fabrics for AI cluster
    • Distributed, parallel, and cloud systems for AI
    • Efficient scheduling, resource management, and orchestration for AI workloads
    • Hardware–software co-design for AI (e.g., accelerators, GPUs, TPUs)
    • Systems for large-scale and foundation models
    • Memory, storage, and I/O optimizations for AI systems
    • Model serving, deployment, and lifecycle management
    • Systems support for federated, edge, and on-device AI
    • Energy-efficient and sustainable AI systems
    • Debugging, monitoring, and observability for AI systems
    • Reliability, security, and privacy in AI systems
    • Benchmarks, datasets, and evaluation methodologies for AI systems
    • Case studies and real-world deployments of AI systems

    Important Dates

    • Paper submission deadline: March 22, 2026 April 7, 2026  April 14, 2026 (AoE) - Firm
    • Notification of acceptance: April 21st, 2026  April 28, 2026
    • Camera-ready deadline: April 30th, 2026 May 4, 2026
    • Workshop date: May 24th

    Paper submission

    Submitted papers should be written in English by following the IEEE conference format (double-column, 10pt font), with a maximum length limit of 6 (six) printed pages, including all figures, references, and appendices.

    Papers should be submitted through EDAS in PDF through the following link: EDAS

    Only original papers that have not been published or submitted for review elsewhere will be considered for publication in the proceedings.

    Papers will appear in the conference proceedings and will be submitted for inclusion into IEEE Xplore subject to meeting IEEE Xplore’s scope and quality requirements.

    At least one author of each accepted paper is required to register and present the work in the workshop.

    A single-blind review process will be followed.

    Workshop Organizing Team

    • Rinku Shah, IIIT-Delhi, India
    • Abed Mohammad Kamaluddin, Marvell, India
    • Priyanka Naik, IBM Research, India
    • ​​Chander Govindarajan, IBM Research, India

    TPC Members

    • Abed Mohammad Kamaluddin, Marvell, India
    • Arnab Kumar Paul, BITS Goa, India
    • Arpit Gupta, UC Santa Barbara, US
    • Chander Govindarajan, IBM Research, India
    • Divyanshu Saxena, UT Austin, US
    • Ertza Warraich, Univerity of Michigan, US
    • Michal Kalderon, Marvell, Israel
    • Mythili Vutukuru, IIT Bombay, India
    • Praveen Jayachandran, IBM Research, India
    • Praveen Tammana, IIT Hyderabad, India
    • Pravein Govindan Kannan, IBM Research, India
    • Priyanka Naik, IBM Research, India
    • Purushottam Kulkarni, IIT Bombay
    • Rinku Shah, IIIT-Delhi
    • Satananda Burla, Marvell, USA
    • Senad Durakovic, Marvell, USA