7 papers
Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission
Seungeun Oh, Jinhyuk Kim, Jihong Park +4
To support emerging language-based applications using dispersed and heterogeneous computing resources, the hybrid language model (HLM) offers a promising architecture, where an on-…
Breaking the Capacity Bottleneck in Model-Heterogeneous Federated Learning via Gradual Model Restoration
Chengjie Ma, Seungeun Oh, Jihong Park +1
Federated learning (FL) enables distributed model training, yet in heterogeneous deployments, Bandwidth-Constrained Clients (BCCs) often contribute inefficiently due to limited upl…
Semantics-Aware Hierarchical Token Communication: Clustering, Bit Mapping, and Power Allocation
Jihoon Lee, Seungeun Oh, Jihong Park +2
Despite the rise of token communication (TokCom) as a new paradigm beyond traditional bit communication, existing approaches have primarily adopted artificial intelligence (AI)-cen…
Action Deviation-Aware Inference for Low-Latency Wireless Robots
Jeyoung Park, Yeonsub Lim, Seungeun Oh +3
To support latency-sensitive AI applications ranging from autonomous driving to industrial robot manipulation, 6G envisions distributed ML with computational resources in mobile, e…
Deadline-Aware Bandwidth Allocation for Semantic Generative Communication with Diffusion Models
Jinhyuk Choi, Jihong Park, Seungeun Oh +1
The importance of Radio Access Network (RAN) in support Artificial Intelligence (AI) application services has grown significantly, underscoring the need for an integrated approach…
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…