Segueix
Francisco Romero
Francisco Romero
Stanford University
Correu electrònic verificat a stanford.edu - Pàgina d'inici
Títol
Citada per
Citada per
Any
{INFaaS}: Automated model-less inference serving
F Romero, Q Li, NJ Yadwadkar, C Kozyrakis
2021 USENIX Annual Technical Conference (USENIX ATC 21), 397-411, 2021
310*2021
From laptop to lambda: Outsourcing everyday jobs to thousands of transient functional containers
S Fouladi, F Romero, D Iter, Q Li, S Chatterjee, C Kozyrakis, M Zaharia, ...
2019 USENIX annual technical conference (USENIX ATC 19), 475-488, 2019
2712019
Faa $ t: A transparent auto-scaling cache for serverless applications
F Romero, GI Chaudhry, Í Goiri, P Gopa, P Batum, NJ Yadwadkar, ...
Proceedings of the ACM symposium on cloud computing, 122-137, 2021
1302021
Llama: A heterogeneous & serverless framework for auto-tuning video analytics pipelines
F Romero, M Zhao, NJ Yadwadkar, C Kozyrakis
Proceedings of the ACM symposium on cloud computing, 1-17, 2021
1022021
Predicting therapist empathy in motivational interviews using language features inspired by psycholinguistic norms.
J Gibson, N Malandrakis, F Romero, DC Atkins, SS Narayanan
Interspeech, 1947-1951, 2015
702015
Mage: Online and interference-aware scheduling for multi-scale heterogeneous systems
F Romero, C Delimitrou
Proceedings of the 27th international conference on parallel architectures …, 2018
682018
A case for managed and model-less inference serving
NJ Yadwadkar, F Romero, Q Li, C Kozyrakis
Proceedings of the Workshop on Hot Topics in Operating Systems, 184-191, 2019
342019
Interference-aware scheduling for inference serving
D Mendoza, F Romero, Q Li, NJ Yadwadkar, C Kozyrakis
Proceedings of the 1st Workshop on Machine Learning and Systems, 80-88, 2021
332021
Optimizing video analytics with declarative model relationships
F Romero, J Hauswald, A Partap, D Kang, M Zaharia, C Kozyrakis
Proceedings of the VLDB Endowment 16 (3), 447-460, 2022
282022
VIVA: An End-to-End System for Interactive Video Analytics.
D Kang, F Romero, PD Bailis, C Kozyrakis, M Zaharia
CIDR, 2022
252022
Multiple instance learning for behavioral coding
J Gibson, A Katsamanis, F Romero, B Xiao, P Georgiou, S Narayanan
IEEE Transactions on Affective Computing 8 (1), 81-94, 2015
112015
Zelda: Video analytics using vision-language models
F Romero, C Winston, J Hauswald, M Zaharia, C Kozyrakis
arXiv preprint arXiv:2305.03785, 2023
82023
Model selection for latency-critical inference serving
D Mendoza, F Romero, C Trippel
Proceedings of the Nineteenth European Conference on Computer Systems, 1016-1038, 2024
52024
Assessing and implementing automated news classification
F Romero, Z Koochak
Standford, CA: Standford University, 2015
52015
Processing system with encoding for processing multiple analog signals
D Thompson, H Marr, F Romero
US Patent 9,391,631, 2016
32016
The TRaCaR Ratio: Selecting the Right Storage Technology for Active Dataset-Serving Databases
F Romero, B Braun, D Cheriton
arXiv preprint arXiv:2006.14793, 2020
12020
En aquests moments el sistema no pot dur a terme l'operació. Torneu-ho a provar més tard.
Articles 1–16