434 citations · 525 across the 14 of their papers we have counts for
6 papers · 1 filter
Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding
Jihoon Park, Seungeun Oh, Seong-Lyun Kim
To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with p…
Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models
Seungeun Oh, Jinhyuk Kim, Jihong Park +3
This paper studies a hybrid language model (HLM) architecture that integrates a small language model (SLM) operating on a mobile device with a large language model (LLM) hosted at…
Federated Knowledge Distillation
Hyowoon Seo, Jihong Park, Seungeun Oh +2
Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges…
Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup
Seungeun Oh, Jihong Park, Eunjeong Jeong +3
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, l…
Multi-hop Federated Private Data Augmentation with Sample Compression
Eunjeong Jeong, Seungeun Oh, Jihong Park +3
On-device machine learning (ML) has brought about the accessibility to a tremendous amount of data from the users while keeping their local data private instead of storing it in a…
Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data
Eunjeong Jeong, Seungeun Oh, Hyesung Kim +3
On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication o…