Title |
|---|
 AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation
Loop on Mobile DevicesIEEE Internet of Things Journal (IEEE IoT J.), 2024 |
 DARDA: Domain-Aware Real-Time Dynamic Neural Network AdaptationIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2024 |
 CARIn: Constraint-Aware and Responsive Inference on Heterogeneous
Devices for Single- and Multi-DNN WorkloadsACM Transactions on Embedded Computing Systems (TECS), 2024 |
 SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with
Tunable Memory BudgetAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Multimodal Federated Learning via Contrastive Representation EnsembleInternational Conference on Learning Representations (ICLR), 2023 |
