5 papers
Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families
Abdulrahman Alabdulkareem, Irene Tenison, Yang Zhang +3
LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent receives the text. This constrains communication to…
Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries
Hina Dixit, Punit Kumar, Irene Tenison +1
Cross-organization language-model adaptation increasingly faces hard governance constraints: in many deployments, device-level model state-parameters, activations, optimizer state,…
Activation-Efficient Fine-Tuning via Sequence-Compressed Low-Rank Subspaces
Irene Tenison, Stella Ahn, Miriam Kim +2
Parameter-Efficient Fine-Tuning (PEFT) has become the standard approach for adapting large language models (LLMs). However, despite reducing trainable parameter counts, many PEFT m…
Forget to Generalize: Iterative Adaptation for Generalization in Federated Learning
Abdulrahman Alotaibi, Irene Tenison, Miriam Kim +2
The Web is naturally heterogeneous with user devices, geographic regions, browsing patterns, and contexts all leading to highly diverse, unique datasets. Federated Learning (FL) is…
FTTE: Enabling Federated and Resource-Constrained Deep Edge Intelligence
Irene Tenison, Anna Murphy, Charles Beauville +1
Federated learning (FL) enables collaborative model training across distributed devices while preserving data privacy, but deployment on resource-constrained edge nodes remains cha…