{"total":79,"rows":[{"id":"2408.00741","title":"DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency","created":"2024-08-01","cited_by_count":112,"area":null},{"id":"2403.07648","title":"Characterization of Large Language Model Development in the Datacenter","created":"2024-03-12","cited_by_count":46,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2403.12844","title":"MELTing point: Mobile Evaluation of Language Transformers","created":"2024-03-19","cited_by_count":36,"area":null},{"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":"2508.15734","title":"Measuring the environmental impact of delivering AI at Google Scale","created":"2025-08-21","cited_by_count":32,"area":null},{"id":"2407.16893","title":"The Price of Prompting: Profiling Energy Use in Large Language Models Inference","created":"2024-07-04","cited_by_count":23,"area":null},{"id":"2312.06902","title":"Reducing Energy Bloat in Large Model Training","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2309.01172","title":"FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs","created":"2023-09-03","cited_by_count":20,"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":"2312.04836","title":"Thermodynamic Computing System for AI Applications","created":"2023-12-08","cited_by_count":16,"area":null},{"id":"2410.12032","title":"MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI","created":"2024-10-15","cited_by_count":16,"area":null},{"id":"2306.01811","title":"DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2511.05597","title":"From Prompts to Power: Measuring the Energy Footprint of LLM Inference","created":"2025-11-05","cited_by_count":12,"area":null},{"id":"2505.11415","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2025-05-16","cited_by_count":11,"area":"moe"},{"id":"2308.06053","title":"Cost-effective On-device Continual Learning over Memory Hierarchy with Miro","created":"2023-08-11","cited_by_count":10,"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":"2308.12908","title":"POLCA: Power Oversubscription in LLM Cloud Providers","created":"2023-08-24","cited_by_count":9,"area":null},{"id":"2510.23972","title":"An efficient probabilistic hardware architecture for diffusion-like models","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2310.19991","title":"PolyThrottle: Energy-efficient Neural Network Inference on Edge Devices","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2509.10371","title":"Characterizing the Efficiency of Distributed Training: A Power, Performance, and Thermal Perspective","created":"2025-09-12","cited_by_count":5,"area":null},{"id":"2602.18755","title":"DualScale: Energy-Efficient Disaggregated LLM Serving via Phase-Aware Placement and DVFS","created":"2026-02-21","cited_by_count":5,"area":"inference"},{"id":"2604.09048","title":"Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures","created":"2026-04-10","cited_by_count":5,"area":"inference"},{"id":"2309.06047","title":"Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2312.00103","title":"DeepEn2023: Energy Datasets for Edge Artificial Intelligence","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2407.20124","title":"AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2411.17712","title":"Generative AI on the Edge: Architecture and Performance Evaluation","created":"2024-11-18","cited_by_count":4,"area":null},{"id":"2510.08055","title":"From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill","created":"2025-10-09","cited_by_count":4,"area":"moe"},{"id":"2503.10666","title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2510.01889","title":"Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection","created":"2025-10-02","cited_by_count":3,"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":"2303.02508","title":"Chasing Low-Carbon Electricity for Practical and Sustainable DNN Training","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2503.04865","title":"E4: Energy-Efficient DNN Inference for Edge Video Analytics Via Early-Exit and DVFS","created":"2025-03-06","cited_by_count":2,"area":"inference"},{"id":"2506.18289","title":"Tu(r)ning AI Green: Exploring Energy Efficiency Cascading with Orthogonal Optimizations","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2511.19476","title":"FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection","created":"2025-11-22","cited_by_count":2,"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":"2604.09611","title":"Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows","created":"2026-03-12","cited_by_count":2,"area":"inference"},{"id":"2608.21719","title":"PowerSlider: Exploiting Phase Asymmetry for LLM Serving under Demand Response","created":"2026-08-22","cited_by_count":2,"area":"inference"},{"id":"2311.11424","title":"Tensor-Aware Energy Accounting","created":"2023-11-19","cited_by_count":1,"area":null},{"id":"2312.08298","title":"Venn: Resource Management for Collaborative Learning Jobs","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2409.18324","title":"Input-Dependent Power Usage in GPUs","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2411.18873","title":"Automating Energy-Efficient GPU Kernel Generation: A Fast Search-Based Compilation Approach","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2501.02181","title":"SMDP-Based Dynamic Batching for Improving Responsiveness and Energy Efficiency of Batch Services","created":"2025-01-04","cited_by_count":1,"area":null},{"id":"2502.18323","title":"Accelerated Training on Low-Power Edge Devices","created":"2025-02-25","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":"2508.07706","title":"Energy Consumption in Parallel Neural Network Training","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2604.16682","title":"KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving","created":"2026-04-17","cited_by_count":1,"area":"agents"},{"id":"2605.11999","title":"The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures","created":"2026-05-12","cited_by_count":1,"area":"inference"},{"id":"2605.21427","title":"PALS: Power-Aware LLM Serving for Mixture-of-Experts Models","created":"2026-05-20","cited_by_count":1,"area":"moe"},{"id":"2605.23348","title":"XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.25098","title":"Power-Flexible AI Data Centers: A New Paradigm for Grid-Responsive Compute","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.05933","title":"Energy-Efficient GPU DVFS for Fine-Tuning of SLMs on Resource-constrained Embedded Devices","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2309.08615","title":"Energy Concerns with HPC Systems and Applications","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2501.16397","title":"THOR: A Generic Energy Estimation Approach for On-Device Training","created":"2025-01-27","cited_by_count":0,"area":null},{"id":"2504.01506","title":"MLKV: Efficiently Scaling up Large Embedding Model Training with Disk-based Key-Value Storage","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2507.10409","title":"Energy Efficiency in AI for 5G and Beyond: A DeepRx Case Study","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2511.02373","title":"A new class of Markov random fields enabling lightweight sampling","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2512.03864","title":"Hyperdimensional Computing for Sustainable Manufacturing: An Initial Assessment","created":"2025-12-03","cited_by_count":0,"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":"2603.26483","title":"EcoFair: Energy-Efficient Inference Routing for Edge AI under Data Degradation","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.23255","title":"Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.17653","title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.23918","title":"The Model Parking Tax: Quantifying the Hidden Energy Cost of Always-On GPU Model Deployment","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.27599","title":"The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution","created":"2026-05-26","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":"2606.21869","title":"The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.30391","title":"Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs","created":"2026-06-29","cited_by_count":0,"area":"inference"},{"id":"2607.22621","title":"Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.07427","title":"A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy","created":"2026-08-07","cited_by_count":0,"area":"mllm"},{"id":"2608.17849","title":"Efficient Resource Optimization for Split Federated Learning","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.11133","title":"Phase-Decoupled, Model-Calibrated Power Control for Disaggregated LLM Serving","created":"2026-09-10","cited_by_count":0,"area":"inference"},{"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":"2609.23085","title":"Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving","created":"2026-09-19","cited_by_count":0,"area":"lr"},{"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},{"id":"2610.01282","title":"Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.12599","title":"STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules","created":"2026-10-08","cited_by_count":0,"area":"moe"}],"next_cursor":null}