default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCID5th EuroMLSys@EuroSys 2025: Rotterdam, The Netherlands
- Eiko Yoneki, Amir H. Payberah:
Proceedings of the 5th Workshop on Machine Learning and Systems, EuroMLSys 2025, World Trade Center, Rotterdam, The Netherlands, 30 March 2025- 3 April 2025. ACM 2025, ISBN 979-8-4007-1538-9 - Akash Balasaheb Dhasade
, Anne-Marie Kermarrec, Erick Lavoie, Johan Pouwelse, Rishi Sharma, Martijn de Vos:
Practical Federated Learning without a Server. 1-11 - Marcel Gregoriadis, Quinten Stokkink, Johan Pouwelse:
Decentralized Adaptive Ranking using Transformers. 12-18 - Kunal Jain, Anjaly Parayil, Ankur Mallick, Esha Choukse, Xiaoting Qin, Jue Zhang, Íñigo Goiri, Rujia Wang, Chetan Bansal, Victor Rühle, Anoop Kulkarni, Steve Kofsky, Saravan Rajmohan:
Performance Aware LLM Load Balancer for Mixed Workloads. 19-30 - Aidan Ferguson, Perry Gibson, Lara D'Agata, Parker McLeod, Ferhat Yaman, Amitabh Das, Ian Colbert, José Cano:
Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs. 31-38 - José Duato, José I. Mestre, Manuel F. Dolz, Enrique S. Quintana-Ortí, José Cano:
Decoupling Structural and Quantitative Knowledge in ReLU-based Deep Neural Networks. 39-45 - Mao Lin, Hyeran Jeon:
Understanding Oversubscribed Memory Management for Deep Learning Training. 46-55 - Hongchao Du, Shangyu Wu, Arina Kharlamova, Nan Guan, Chun Jason Xue:
FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference. 56-65 - Shai Aviram Bergman, Zhang Ji, Anne-Marie Kermarrec, Diana Petrescu, Rafael Pires, Mathis Randl, Martijn de Vos:
Leveraging Approximate Caching for Faster Retrieval-Augmented Generation. 66-73 - Rachid Guerraoui, Anne-Marie Kermarrec, Diana Petrescu, Rafael Pires, Mathis Randl, Martijn de Vos:
Efficient Federated Search for Retrieval-Augmented Generation. 74-81 - Kahfi S. Zulkifli, Wenbo Qian, Shaowei Zhu, Yuan Zhou, Zhen Zhang, Chang Lou:
Verifying Semantic Equivalence of Large Models with Equality Saturation. 82-89 - Pedro F. Silvestre, Peter R. Pietzuch:
Systems Opportunities for LLM Fine-Tuning using Reinforcement Learning. 90-99 - Moonmoon Mohanty, Gautham Bolar, Preetam Patil, UmaMaheswari Devi, Felix George, Pratibha Moogi, Parimal Parag:
Deferred prefill for throughput maximization in LLM inference. 100-106 - Pedro Gimenes, Aaron Zhao, George A. Constantinides:
AMPLE: Event-Driven Accelerator for Mixed-Precision Inference of Graph Neural Networks. 107-113 - Dhruv Garg, Debopam Sanyal, Myungjin Lee, Alexey Tumanov, Ada Gavrilovska:
Client Availability in Federated Learning: It Matters! 114-121 - Amir Noohi, Mostafa Derispour, Antonio Barbalace:
RMAI: Rethinking Memory for AI (Inference): In-Kernel Remote Shared Memory as a Software Alternative to CXL. 122-131 - Mohammad Siavashi, Faezeh Keshmiri Dindarloo, Dejan Kostic, Marco Chiesa:
Priority-Aware Preemptive Scheduling for Mixed-Priority Workloads in MoE Inference. 132-138 - Yifan Wang, Kenneth P. Birman:
Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs. 139-147 - Maximilian Jakob Heer, Benjamin Ramhorst, Gustavo Alonso:
Machine Learning-based Deep Packet Inspection at Line Rate for RDMA on FPGAs. 148-155 - Akash Balasaheb Dhasade, Anne-Marie Kermarrec, Tuan-Anh Nguyen, Rafael Pires, Martijn de Vos:
Harnessing Increased Client Participation with Cohort-Parallel Federated Learning. 156-167 - Haci Ismail Aslan, Philipp Wiesner, Ping Xiong, Odej Kao:
β-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation. 168-175 - Achref Rebai, Marco Canini:
OptimusNIC: Offloading Optimizer State to SmartNICs for Efficient Large-Scale AI Training. 176-182 - Boris Radovic, Marco Canini, Samuel Horváth, Veljko Pejovic, Praneeth Vepakomma:
Towards a Unified Framework for Split Learning. 183-191 - Oana Balmau, Anne-Marie Kermarrec, Rafael Pires, André Loureiro Espírito Santo, Martijn de Vos, Milos Vujasinovic:
Accelerating MoE Model Inference with Expert Sharding. 192-199 - Excel Chukwu, Laurent Bindschaedler:
May the Memory Be With You: Efficient and Infinitely Updatable State for Large Language Models. 200-207 - Patrick Wilhelm, Thorsten Wittkopp, Odej Kao:
Beyond Test-Time Compute Strategies: Advocating Energy-per-Token in LLM Inference. 208-215 - Jihao Xin, Marco Canini, Peter Richtárik, Samuel Horváth:
Global-QSGD: Allreduce-Compatible Quantization for Distributed Learning with Theoretical Guarantees. 216-229 - Sina Sheikholeslami, Hamid Ghasemirahni, Amir Hossein Payberah, Tianze Wang, Jim Dowling, Vladimir Vlassov:
Utilizing Large Language Models for Ablation Studies in Machine Learning and Deep Learning. 230-237 - Stefan Behfar, Richard Mortier, Jon Crowcroft:
Analysis of Information Propagation in Ethereum Network Using Combined Graph Attention Network and Reinforcement Learning to Optimize Network Efficiency and Scalability. 238-245 - Ruiqi Lai, Siyu Cao, Leqi Li, Luo Mai, Dmitrii Ustiugov:
Manage the Workloads not the Cluster: Designing a Control Plane for Large-Scale AI Clusters. 246-253 - Igor Polyakov, Alexey Dukhanov, Egor Spirin:
TAGC: Optimizing Gradient Communication in Distributed Transformer Training. 254-260 - Christos Sad, George Retsinas, Dimitrios Soudris, Kostas Siozios, Dimosthenis Masouros:
Towards Asynchronous Peer-to-Peer Federated Learning for Heterogeneous Systems. 261-268 - Diogen Babuc, Teodor-Florin Fortis:
Hybrid Task Scheduling for Optimized Neural Network Inference on Skin Lesions in Resource-Constrained Systems. 269-275 - Theodoros Aslanidis, Sokol Kosta, Spyros Lalis, Dimitris Chatzopoulos:
Cross-Domain DRL Agents for Efficient Job Placement in the Cloud-Edge Continuum. 276-285
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2025-11-28 23:53 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
