---
title: SEC 2025 Digest
venue: SEC
year: 2025
date: '2025-01-01'
tags: []
paper_count: 12
draft: false
---

12 papers selected.

---

### lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models

*Haoxin Wang 0003*

**TL;DR** — Provides the first detailed runtime profiling framework for on-device LLM inference, revealing key latency bottlenecks across diverse edge hardware configurations.

---

### SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving

*Xiangchen Li*

**TL;DR** — Adapts speculative decoding to edge serving constraints, reducing LLM token generation latency while respecting the tight memory and compute budgets of edge nodes.

---

### SledgeScale: Load-Aware Dispatch and Deadline-Driven Scheduling for Scalable, Dense Serverless Computing in Edge Data Centers

*Xiaosu Lyu*

**TL;DR** — Introduces a load-aware dispatch and deadline-driven scheduler for dense serverless edge data centers, demonstrating substantial SLA compliance improvements over baseline policies.

---

### Warping the Edge: Enabling Instant Mobility for Stateful Applications over 5G and Beyond

*Mukhtiar Ahmad*

**TL;DR** — Achieves near-instantaneous stateful application migration across 5G edge nodes by combining memory snapshotting with network-layer forwarding continuity.

---

### Uncertainty-Aware RL-Based Scheduling of Multi-DNN Workloads on Edge MPSoCs

*Soroush Heidari*

**TL;DR** — Uses uncertainty-aware reinforcement learning to schedule concurrent DNN workloads on heterogeneous edge MPSoCs, reducing deadline misses under dynamic arrival patterns.

---

### SEEB-GPU: Early-Exit Aware Scheduling and Batching for Edge GPU Inference

*Srinivasan Subramaniyan*

**TL;DR** — 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.

---

### Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation

*Sudaksh Kalra*

**TL;DR** — Proposes elastic transformer transformations that resize model capacity at runtime to match available edge resources, enabling continuous inference under fluctuating conditions.

---

### PlatformX: An End-to-End Transferable Platform for Energy-Efficient Neural Architecture Search

*Xiaolong Tu*

**TL;DR** — Presents a transferable NAS platform that searches for energy-efficient DNN architectures deployable across heterogeneous edge targets with minimal re-search overhead.

---

### Bayes-Split-Edge: Bayesian Optimization for Constrained Collaborative Inference in Wireless Edge Systems

*Fatemeh Zahra Safaeipour*

**TL;DR** — Applies Bayesian optimization to find optimal split points for collaborative inference in wireless edge systems, accounting for dynamic channel and computation constraints.

---

### Energy-efficient DNN Dividing Technique for Latency Optimization in Dynamic Mobile Edge Networks

*Eldiyar Zhantileuov*

**TL;DR** — Develops a DNN partitioning strategy for mobile edge networks that minimizes end-to-end latency while satisfying energy budgets under time-varying link conditions.

---

### LLM-Driven Auto Configuration for Transient IoT Device Collaboration

*Hetvi Shastri*

**TL;DR** — Leverages LLMs to automate the configuration of transient IoT device coalitions, reducing manual setup overhead and adapting collaboration policies to changing device membership.

---

### fReeLoaders: An IoT Ecosystem for Real-Time Deadline-Driven Task Scheduling using Reinforcement Learning

*Marshall Clyburn*

**TL;DR** — Builds a reinforcement-learning scheduler for IoT ecosystems that meets real-time task deadlines by exploiting opportunistic idle capacity across heterogeneous edge devices.