6 papers
Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating
Evan Chen, Shiqiang Wang, Kevin S Chan +2
Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained routers or collaboration-aware f…
CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
Seohyeon Cha, Huancheng Chen, Dongjun Kim +4
Post-training quantization (PTQ) enables efficient deployment of large language models by mapping pretrained weights to low-bit formats without retraining, typically using a small…
SPRINT: Semi-supervised Prototypical Representation for Few-Shot Class-Incremental Tabular Learning
Umid Suleymanov, Murat Kantarcioglu, Kevin S Chan +6
Real-world systems must continuously adapt to novel concepts from limited data without forgetting previously acquired knowledge. While Few-Shot Class-Incremental Learning (FSCIL) i…
Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback
Haoran Zhang, Seohyeon Cha, Hasan Burhan Beytur +3
Hierarchical inference systems route tasks across multiple computational layers, where each node may either finalize a prediction locally or offload the task to a node in the next…
Optimal Resource Allocation for ML Model Training and Deployment under Concept Drift
Hasan Burhan Beytur, Gustavo de Veciana, Haris Vikalo +1
We study how to allocate resources for training and deployment of machine learning (ML) models under concept drift and limited budgets. We consider a setting in which a model provi…
Batching-Aware Joint Model Onloading and Offloading for Hierarchical Multi-Task Inference
Seohyeon Cha, Kevin Chan, Gustavo de Veciana +1
The growing demand for intelligent services on resource-constrained edge devices has spurred the development of collaborative inference systems that distribute workloads across end…