venue: SEC
year: 2025
papers:
- title: 'lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models'
  authors:
  - Haoxin Wang 0003
  reason: "Provides the first detailed runtime profiling framework for on-device LLM inference, revealing key latency bottlenecks across diverse edge hardware configurations."
- title: 'SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving'
  authors:
  - Xiangchen Li
  reason: "Adapts speculative decoding to edge serving constraints, reducing LLM token generation latency while respecting the tight memory and compute budgets of edge nodes."
- title: 'SledgeScale: Load-Aware Dispatch and Deadline-Driven Scheduling for Scalable,
    Dense Serverless Computing in Edge Data Centers'
  authors:
  - Xiaosu Lyu
  reason: "Introduces a load-aware dispatch and deadline-driven scheduler for dense serverless edge data centers, demonstrating substantial SLA compliance improvements over baseline policies."
- title: 'Warping the Edge: Enabling Instant Mobility for Stateful Applications over
    5G and Beyond'
  authors:
  - Mukhtiar Ahmad
  reason: "Achieves near-instantaneous stateful application migration across 5G edge nodes by combining memory snapshotting with network-layer forwarding continuity."
- title: Uncertainty-Aware RL-Based Scheduling of Multi-DNN Workloads on Edge MPSoCs
  authors:
  - Soroush Heidari
  reason: "Uses uncertainty-aware reinforcement learning to schedule concurrent DNN workloads on heterogeneous edge MPSoCs, reducing deadline misses under dynamic arrival patterns."
- title: 'SEEB-GPU: Early-Exit Aware Scheduling and Batching for Edge GPU Inference'
  authors:
  - Srinivasan Subramaniyan
  reason: "Exploits early-exit branching in DNN inference to build an adaptive batching and scheduling policy for edge GPUs that cuts average latency without sacrificing throughput."
- title: 'Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation'
  authors:
  - Sudaksh Kalra
  reason: "Proposes elastic transformer transformations that resize model capacity at runtime to match available edge resources, enabling continuous inference under fluctuating conditions."
- title: 'PlatformX: An End-to-End Transferable Platform for Energy-Efficient Neural
    Architecture Search'
  authors:
  - Xiaolong Tu
  reason: "Presents a transferable NAS platform that searches for energy-efficient DNN architectures deployable across heterogeneous edge targets with minimal re-search overhead."
- title: 'Bayes-Split-Edge: Bayesian Optimization for Constrained Collaborative Inference
    in Wireless Edge Systems'
  authors:
  - Fatemeh Zahra Safaeipour
  reason: "Applies Bayesian optimization to find optimal split points for collaborative inference in wireless edge systems, accounting for dynamic channel and computation constraints."
- title: Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic
    Mobile Edge Networks
  authors:
  - Eldiyar Zhantileuov
  reason: "Develops a DNN partitioning strategy for mobile edge networks that minimizes end-to-end latency while satisfying energy budgets under time-varying link conditions."
- title: LLM-Driven Auto Configuration for Transient IoT Device Collaboration
  authors:
  - Hetvi Shastri
  reason: "Leverages LLMs to automate the configuration of transient IoT device coalitions, reducing manual setup overhead and adapting collaboration policies to changing device membership."
- title: 'fReeLoaders: An IoT Ecosystem for Real-Time Deadline-Driven Task Scheduling
    using Reinforcement Learning'
  authors:
  - Marshall Clyburn
  reason: "Builds a reinforcement-learning scheduler for IoT ecosystems that meets real-time task deadlines by exploiting opportunistic idle capacity across heterogeneous edge devices."