MobiSys 2026

Accepted Workshops

All workshops will be held on June 25th, 2026.

Workshop on EMPOWER 2026

Energy-efficient Machine learning for Performance-Optimized Wireless and Edge NetwoRks

Mobile and wireless networks are evolving toward highly heterogeneous ecosystems, encompassing smartphones, wearables, and dense edge infrastructures. Simultaneously, the integration of AI into these systems has triggered an “AI Compute-Energy Crisis,” where the demands of modern models often exceed the thermal and energy limits of constrained hardware.

EMPOWER 2026 bridges the gap between the machine learning community and the mobile systems community. We explore the full lifecycle of mobile intelligence: from AI for Networks, which focuses on scalable, trustworthy intelligence to optimize non-stationary network conditions and next-generation connectivity; to Systems for AI that emphasize lightweight architectures, brain-inspired computing, and intelligent AI workload scheduling to make intelligence viable on the edge. We solicit contributions that span the spectrum from algorithmic innovations to real-world system deployments. Topics include AI-native 6G architectures, trustworthy network operations, on-device GenAI, brain-inspired systems, and model compression.

Workshop Chairs:

Workshop on EMDL 2026

The 7th Int. Workshop on Embedded and Mobile Deep Learning – System Foundations for Generative AIs

Website: https://emdl-workshop.github.io/emdl26/

Since its inception in 2017, the EMDL workshop has tracked how breakthroughs in deep learning transformed the interpretation of sensor data for mobile systems like smartphones and wearable devices. In the early years, the community focused on making standard inference feasible, overcoming the severe demands that deep models exerted on local resources. By 2022, these methods had matured, successfully adapting CNN and RNN architectures to meet the stringent needs of mixed-reality and cyber-physical systems.

The Shift: From Discriminative to Generative: However, the landscape has shifted once again. We are witnessing a transition from Discriminative AI (classifying sensor data) to Generative AI (reasoning, explaining, and acting on context). While Generative AI (GenAI) brings unprecedented capabilities, it also presents a resource wall. Modern edge devices operate under constraints in memory bandwidth and energy availability that standard GenAI architectures—which are memory-bound and autoregressive—fundamentally exceed. Currently, the most advanced models reside almost exclusively on the cloud, challenging the autonomy of mobile platforms. In this context, the mobile computing community is in a unique position to begin the careful study of two core technical questions re-framed for the GenAI era. First, how should systems be architected to partition these massive workloads? We must move beyond simple offloading to explore dynamic collaboration where mobile devices handle context and lightweight generation while the cloud supports heavy lifting. Second, what is required to integrate GenAI into resource-constrained systems? This necessitates a re-examination of efficiency, spanning from the compression of Transformer architectures and diffusion models to the software/hardware optimization of mobile processors (CPUs, GPUs, NPUs) for memory-intensive generation rather than traditional convolution.

Scope and Goals: EMDL 2026 explores the intersection of Systems and Generative AI. Unlike traditional AIoT approaches that focus on lightweight classification, this workshop addresses the unique systems challenges of GenAI deployment. We focus on the full stack of efficient deployment: from algorithmic compression to hardware-software co-design for resource-efficient reasoning on wearables, robots, and mobile devices. We invite researchers to submit work that answers core technical questions for the GenAI era:

  1. Architecture: How should systems be architected to partition massive workloads between the cloud and the edge?.
  2. Efficiency: What is required to integrate memory-bound GenAI into resource-constrained systems?.
  3. Edge-Native Design: How do we define edge-native generative models designed explicitly for physical constraints?

Workshop Chairs:

Workshop on EIFCOM 2026

International Workshop on Mobile Systems with Efficient and Interactive Foundation Models

Foundation models have recently emerged as a powerful tool for various applications. However, their impact on mobile applications has been less investigated. Recent research showcases their ability to achieve unprecedented capabilities in areas such as task automation, hand sign detection, and visual question answering. However, their increasing complexity poses significant challenges in terms of sensor modality, diverse sensor environments, model efficiency, interactivity, and user experience. The EIFCom workshop aims to provide a forum for researchers, developers, and industry partners to share their experiences, present innovative solutions, and discuss the latest advancements in efficient foundation models for mobile applications.

Workshop Chairs:

Workshop on HeadSys 2026

1st Workshop on Head-Based Intelligent Systems

Website: https://www.eventcreate.com/e/headsys26

The 1st HeadSys workshop comes at a critical juncture where headcentric computing research, encompassing sensing, communication, and computing-based systems, has become increasingly prominent in the mobile and ubiquitous computing space. Head-worn devices occupy a uniquely privileged position on the human body, offering unparalleled access to physiological signals, environmental context, and natural modalities for human-computer interaction. With rapid advancements in smart glasses, smart earbuds, and AR/VR headsets, head-based systems are poised to reshape how we augment human perception, cognition, and communication.

Workshop Chairs:

Workshop on Agentic Systems

Agentic Systems Track: From Systems Foundations to the Extreme Edge

This track brings together two complementary workshops that examine agentic systems from different system perspectives. Authors should choose the workshop that best aligns with the core contribution of their paper. To assist authors in selecting the most appropriate venue, we clarify the distinct focuses of the AutoSys and AutoEdge workshops:

Website: https://autosys26.github.io/

AutoSys focuses on the systems foundations and architecture for agent capabilities across various platforms. We welcome papers on the architecture, reliability, and security of the entire system that enables agents, with topics including systems for GUI/coding agents, memory mechanisms, multi-agent collaboration, OS-level support, and system-level security.

Organizers:

Website: https://autoedge2026.github.io/

AutoEdge focuses on IoT and edge systems that enable autonomic self-management and agentic decision-making on resource-constrained devices. We invite work that shifts intelligence from the cloud to the extreme edge, using approaches such as TinyML, small language models, on-device reasoning, and multi-agent coordination to build systems that can self-configure, self-optimise, self-heal, and adapt. The workshop emphasises practical systems, frameworks, and deployments that demonstrate resilient, energy-efficient, and privacy-aware operation in dynamic domains such as smart cities, healthcare, industrial IoT, connected vehicles, and others.

Organizers:

Workshop on Real-World AI-Powered Systems

Real-World AI-Powered Systems Track: Co-located EnvSys and NetAISys

For the fourth year in a row, NetAISys and EnvSys are merging at ACM MobiSys 2026 to form a one-day joint workshop. The event brings together complementary perspectives on AI: NetAISys focuses on AI-powered networking systems, while EnvSys highlights AI-driven environmental sensing. Together, they offer a comprehensive forum for discussing research at the intersection of networking, AI, and environmental applications, with real-world EnvSys use cases grounding Networked AI Systems research.

NetAISys

Website: https://netaisys.github.io/

Organizers:

EnvSys

Website: https://envsensys.github.io/2026/

Organizers:

Workshop on Edge Intelligence

Edge Intelligence Track: From Systems to Applications

Authors are invited to submit their work to the workshop that best aligns with the primary contribution and emphasis of their paper. While both workshops address research at the edge of modern computing systems, they differ in focus and perspective. The following descriptions are intended to clarify the scope of each workshop and help authors decide whether their work is more systems- and infrastructure-oriented, or primarily centered on AI methods and applications at the edge.

EdgeSys : aims to bring together system researchers, data scientists, engineers, and practitioners to identify open directions and discuss the latest research ideas and results on edge systems, analytics, and networking, especially those related to novel and emerging technologies and use cases. With 8-year successful series, the workshop focuses on systems, analytics, and networking aspects, covering system architecture, distributed ML/AI algorithms, decentralized networking, distributed consensus and ledger techniques, edge services, and data analysis.

Organizers:

The Excellence in Edge AI workshop is dedicated to exploring the frontiers of AI and edge computing synergy, with a focus on developing scalable, robust AI systems. The workshop is organized and supported by the dAIEdge European Network of Excellence on “AI at the Edge”. In order to make the workshop more interactive and lively, it will include a demo session where the participants will be able to present live demos, either on-site or via video, of their research

Organizers:

If you are uncertain which workshop best matches your submission, please feel free to contact the chairs of both workshops for guidance before submitting.