Important dates

• Paper Submission Deadline
  August 31, 2026
• Author Notification Deadline
  September 30, 2026
• Camera-ready Submission Deadline
  October 2, 2026
• Workshop Date
  November 17, 2026

All deadlines are 23:59 AoE (Anywhere on Earth).

Topics of interest

RISE-DL welcomes original research, prior work, preliminary results, work-in-progress, and exploratory research directions on scalable and efficient deep learning across heterogeneous computing environments—from IoT and edge devices to cloud infrastructures—spanning model design, training, inference, and deployment. Topics of interest include, but are not limited to:

• Training for long-term sustainability

  Quantization-aware training, pruning-aware training, knowledge distillation, and green-aware neural architecture search.

• Scalable training of generative AI

  KV-cache optimization for LLMs, memory-efficient attention algorithms, and parameter-efficient fine-tuning.

• Fast inference and serving techniques

  Speculative decoding for LLMs, early-exit strategies, and caching mechanisms.

• On-device, continual, and incremental learning

  Test-time adaptation, online and lifelong learning, and personalization at the edge under resource constraints.

• Data-centric efficient deep learning

  Data pruning, compression, selection, and dataset distillation.

• Benchmarking, metrics, and evaluation

  Methodologies for efficiency and sustainability, including energy consumption, latency, memory footprint, and carbon emissions.

• Distributed learning across the edge–cloud continuum

  Federated learning, split learning, and gossip learning.

Submission guidelines

We invite submissions in two categories:

• Short papers: from 3 to 4 pages, including figures, tables, and references.
• Regular papers: from 6 to 8 pages, including figures, tables, and references.

All submissions must be written in English, anonymized for double-blind review, and prepared using the ACM article template, as recommended in the IoT 2026 submission guidelines. At least one author of each accepted paper is required to register for the conference.

Papers must be submitted through the EasyChair submission system: https://easychair.org/conferences/?conf=iot2026 . Authors should create a new submission and then select “RISE-DL: Research and Innovation in Scalable and Efficient Deep Learning” as the submission track.