{"total":17,"rows":[{"id":"2505.06371","title":"The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization","created":"2025-05-09","cited_by_count":33,"area":null},{"id":"2501.08219","title":"Characterizing LLM Inference Energy-Performance Tradeoffs across Workloads and GPU Scaling","created":"2025-01-14","cited_by_count":19,"area":null},{"id":"2601.22076","title":"Where Do the Joules Go? Diagnosing Inference Energy Consumption","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2601.17654","title":"Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training","created":"2026-01-25","cited_by_count":3,"area":null},{"id":"2512.09946","title":"ELANA: A Simple Energy and Latency Analyzer for LLMs","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2409.18324","title":"Input-Dependent Power Usage in GPUs","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2501.10187","title":"Good things come in small packages: Should we build AI clusters with Lite-GPUs?","created":"2025-01-17","cited_by_count":1,"area":null},{"id":"2505.01468","title":"One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2506.21329","title":"Active Inference AI Systems for Scientific Discovery","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2512.08365","title":"Magneton: Optimizing Energy Efficiency of ML Systems via Differential Energy Debugging","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.08991","title":"Optimising for Energy Efficiency and Performance in Machine Learning","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2605.16255","title":"Designing Datacenter Power Delivery Hierarchies for the AI Era","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.07632","title":"Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2608.17849","title":"Efficient Resource Optimization for Split Federated Learning","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.11542","title":"Characterizing Job Power Elasticity for Power-Flexible AI Training","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13922","title":"Minibatch persistency, eight years later: what batch reuse costs in steps and joules, and what it saves in data","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.24205","title":"A principled approach for energy-efficient training via phase-aware GPU frequency tuning","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}