EMPOWER 2026

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

Co-located with ACM MobiSys 2026 📍 Location: Cambridge, UK
📅 Date: June 25 or 26, 2026 (TBC)

---

📢 Call for Papers

EMPOWER 2026 bridges the gap between the machine learning community and the mobile systems community.

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.

We explore the full lifecycle of mobile intelligence. We solicit contributions that span the spectrum from algorithmic innovations to real-world system deployments, organized into two distinct tracks.

🎯 Workshop Tracks

To address the diverse challenges of the AI-Mobile ecosystem, EMPOWER 2026 welcomes submissions under two main tracks:

Track 1: AI for Networks

Focusing on scalable, trustworthy intelligence to optimize non-stationary network conditions and next-generation connectivity.

• Topics:
  • AI-native 6G and edge architectures
  • Trustworthy network operations and automation
  • Intelligent spectrum management
  • AI for network security and resilience

Track 2: Systems for AI

Focusing on lightweight architectures, brain-inspired computing, and intelligent AI workload scheduling to make intelligence viable on the edge.

• Topics:
  • On-device Generative AI (GenAI)
  • Model compression and quantization
  • Brain-inspired computing and neuromorphic systems
  • Energy-efficient AI workload scheduling
  • Thermal-aware mobile computing

---

📅 Important Dates

Event	Date
Submission Deadline	April 02, 2026 (AoE)
Notification of Acceptance	April 20, 2026 (AoE)
Camera-Ready Deadline	April 27, 2026 (AoE)
Workshop Date	June 25/26, 2026 (TBC)

(AoE = Anywhere on Earth)

---

📝 Submission Guidelines

We invite original research papers that have not been previously published and are not currently under review for publication.

Page Limits

• Full Papers: Up to 6 pages (including references).
• Position Papers: Up to 4 pages (including references).

Formatting Requirements

All submissions must be provided in PDF format and follow the specific formatting guidelines of MobiSys 2026:

• Font: 10pt font (or larger).
• Paper Size: Letter-sized (8.5” by 11”).
• Layout: Double-column.
  • Column width: 9.25” by 3.33”
  • Space between columns: 0.33”
• Spacing: Single-spaced.
• Abstract: Must contain fewer than 250 words.

LaTeX Template

Submissions can use the ACM Proceedings LaTeX Template. Authors remain responsible for checking that their resulting PDF meets the formatting specifications above.

Review Process

EMPOWER 2026 follows a double-blind review process.

• Anonymization: Authors must not reveal their identity in the submission. Please remove names, affiliations, and contact information from the PDF.
• Citations: Cite your own work in the third person (e.g., “Smith et al. showed…” rather than “We showed…”).

Submission Site

The submission link will be available soon.

---

👥 Organizing Committee

Workshop Chairs

• Matteo Mendula – Centre Tecnològic de Telecomunicacions de Catalunya (CTTC)
• Lintao Ye – Huazhong University of Science and Technology (HUST)
• Paolo Dini – Centre Tecnològic de Telecomunicacions de Catalunya (CTTC)
• Gustavo de Veciana – The University of Texas at Austin
• Carla Fabiana Chiasserini – Politecnico di Torino
• Sujata Pal – Indian Institute of Technology Ropar
• Vidushi Agarwal – University of Guelph, Canada
• Omer Rana – Cardiff University
• Sushmita Ruj – UNSW, Sydney
• Balaji Palanisamy – University of Pittsburgh
• Nitin Auluck – Indian Institute of Technology Ropar

---

Registration

Registration for the workshop will be handled through the main MobiSys 2026 website.

---

📮 Contact

If you have any questions regarding the workshop or submission process, please reach out to the workshop chairs at:
📧 [mmendula@cttc.es]