Effective Long-Context Scaling of Foundation Models.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024
Towards Next-Generation Intelligent Assistants Leveraging LLM Techniques.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023
Joint Federated Learning and Personalization for on-Device ASR.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023
Where to Begin? Exploring the Impact of Pre-Training and Initialization in Federated Learning.
CoRR, 2022
FedSynth: Gradient Compression via Synthetic Data in Federated Learning.
CoRR, 2022
PAPAYA: Practical, Private, and Scalable Federated Learning.
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Fifth Conference on Machine Learning and Systems, 2022
Federated Learning with Partial Model Personalization.
Proceedings of the International Conference on Machine Learning, 2022
Federated Learning with Buffered Asynchronous Aggregation.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022
Active Federated Learning.
CoRR, 2019
Federated User Representation Learning.
CoRR, 2019
Critical Branches and Lucky Loads in Control-Independence Architectures
PhD thesis, 2009
Fetch-Criticality Reduction through Control Independence.
Proceedings of the 35th International Symposium on Computer Architecture (ISCA 2008), 2008
Branch-mispredict level parallelism (BLP) for control independence.
Proceedings of the 14th International Conference on High-Performance Computer Architecture (HPCA-14 2008), 2008
PaCo: Probability-based path confidence prediction.
Proceedings of the 14th International Conference on High-Performance Computer Architecture (HPCA-14 2008), 2008
Exploiting Postdominance for Speculative Parallelization.
Proceedings of the 13st International Conference on High-Performance Computer Architecture (HPCA-13 2007), 2007