Peer-reviewed Publications

[IPDPS'26] HarMoEny: Efficient multi-GPU inference of MoE models. IEEE International Parallel & Distributed Processing Symposium, 2026. Z. Doucet*, R. Sharma, M. de Vos, R. Pires, AM. Kermarrec, O. Balmau.

[EuroSys '26] MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing. The European Conference on Computer Systems EuroSys 2026. R. Nouaji*, S. Bitchebe*, R. Macedo, O. Balmau. Best Poster Award!

[OSR ‘26] PostLearn: Towards A Learned Index For PostgreSQL. Peer-reviewed Journal ACM SIGOPS Operating Systems Review (OSR). A. Fuad*, S. Vashisth*, O. Balmau, B Kemme. Invited paper.

[EdgeSys’26] Wagg: Cost-aware Aggregation of Windowing Operators in Stream Processing. ACM Workshop on Edge Systems, Analytics, and Networking (collocated with MobiSys). P.Mishra*, R. Deng*, A.da Silva Veith, O. Balmau, E. de Lara.

[EuroMLSys’26] The Cost of Expertise: Understanding MoE Decode Performance. ACM Workshop on Machine Learning and Systems (collocated with EuroSys). S. Abuzakuk, O. Balmau, J. Chen*, A-M. Kermarrec, R. Pires, R. Prabhu, M. de Vos.

[CHEOPS ‘26] PostLearn: Towards A Learned Index For PostgreSQL. ACM Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems (collocated with EuroSys). A. Fuad*, S. Vashisth*, O. Balmau, B Kemme. Top paper, invited to publish in OSR ‘26 special issue.

[PVLDB '25] Keigo: Co-designing Log-Structured Merge Key-Value Stores with a Non-Volatile, Concurrency-aware Storage Hierarchy. Proceedings of the VLDB Endowment 2025. R. Adao*, Z. Wu*, C. Zhou*, O. Balmau, J. Paulo, R. Macedo.

[EuroMLSys’25] Accelerating MoE Model Inference with Expert Sharding. ACM Workshop on Machine Learning and Systems (collocated with EuroSys). O. Balmau, A-M. Kermarrec, R. Pires, A Espirito Santo, M. de Vos, M. Vujasinovic.

[Middleware '24] vPIM: Processing-in-Memory Virtualization. ACM/IFIP International Middleware Conference. D. Teguia, J. Chen, S. Bitchebe, O. Balmau, A. Tchana. [pdf] [slides]

[SEC '24] Falcon: Live Reconfiguration for Stateful Stream Processing on the Edge. ACM/IEEE Symposium on Edge Computing.  P. Mishra, N. Bore, B. Ramprasad, M. Thiessen, M. Gabel, A. da Silva Veith, O. Balmau, E. de Lara. Best Paper Award! [pdf][talk][code]

[OSR ‘24] Is Bare-metal I/O Performance with User-defined Storage Drives Inside VMs Possible? ACM SIGOPS Operating Systems Review (OSR). S. Rolon, O. Balmau. Invited paper. [pdf][slides]

[EuroMLSys '24] SpeedyLoader: Efficient Pipelining of Data Preprocessing and Machine Learning Training ACM Workshop on Machine Learning and Systems (collocated with EuroSys). R. Nouaji, S. Bitchebe, O. Balmau. [pdf][slides]

[EdgeSys '24] Stream Processing with Adaptive Edge-Enhanced Confidential Computing ACM International Workshop on Edge Systems, Analytics, and Networking (collocated with EuroSys). Y. Yan, P. Mishra, W. Huang, A. Mehta, O. Balmau, D. Lie. [pdf][slides]

[EdgeSys '24] PathFS: A File System for the Hierarchical Edge ACM International Workshop on Edge Systems, Analytics, and Networking (collocated with EuroSys). V. Dantas de Lima Melo, M. Thiessen, A. Panas, A. da Silva Veith, K. Yano, O. Balmau, E. de Lara [pdf][slides]

[EuroSys '24 - Poster] PAM: Fast Reactive Reconfiguration for Stateful Stream Processing ACM International Workshop on Edge Systems, Analytics, and Networking. P. Mishra, O. Balmau, E. de Lara [pdf]

[CHEOPS '23] Is Bare-metal I/O Performance with User-defined Storage Drives Inside VMs Possible? ACM Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems. S. Rolon, O. Balmau. Distinguished paper, invited to publish in ACM Operating Systems Review [pdf][slides]

[SIGMOD Record '22] Characterizing I/O in Machine Learning with MLPerf Storage. SIGMOD Record DBrainstorming. O. Balmau. [pdf]

[SEC '22] Shepherd: Seamless Stream Processing on the Edge. AACM/IEEE Symposium on Edge Computing. B. Ramprasad, P. Mishra, M. Thiessen, H. Chen, A. da Silva Veith, M. Gabel, O. Balmau, A. Chow, E. de Lara. [pdf] [code] [talk] 

[CHEOPS '22] TONE: Cutting Tail-Latency in Learned Indexes. ACM Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems. Y. Zhang, X. Xiong, O. Balmau. [pdf] [code] [talk]

[OSDI '20] Snapshot Isolation Without Snapshots. USENIX Symposium on Operating Systems Design and Implementation 2020 (17% acceptance ratio). B. Lepers, O. Balmau, K. Gupta , W. Zwaenepoel. [pdf] [code] [slides]