{"total":19,"rows":[{"id":"2310.03003","title":"From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference","created":"2023-10-04","cited_by_count":170,"area":null},{"id":"2302.14838","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","created":"2023-02-28","cited_by_count":131,"area":null},{"id":"2406.08413","title":"Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference","created":"2024-06-12","cited_by_count":15,"area":null},{"id":"2502.05610","title":"Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2409.11416","title":"The Unseen AI Disruptions for Power Grids: LLM-Induced Transients","created":"2024-09-09","cited_by_count":10,"area":null},{"id":"2402.16714","title":"Quantum Transformer: Accelerating model inference via quantum linear algebra","created":"2024-02-26","cited_by_count":9,"area":null},{"id":"2402.18593","title":"Sustainable Supercomputing for AI: GPU Power Capping at HPC Scale","created":"2024-02-25","cited_by_count":9,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2401.01851","title":"The Power of Training: How Different Neural Network Setups Influence the Energy Demand","created":"2024-01-03","cited_by_count":7,"area":null},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2411.10599","title":"Generating Energy-efficient code with LLMs","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2405.00738","title":"HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2408.01446","title":"Estimating Environmental Cost Throughout Model's Adaptive Life Cycle","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2502.11723","title":"Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2311.14114","title":"SONIQ: System-Optimized Noise-Injected Ultra-Low-Precision Quantization with Full-Precision Parity","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2402.04359","title":"Adaptive Inference: Theoretical Limits and Unexplored Opportunities","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2406.16962","title":"MetaGreen: Meta-Learning Inspired Transformer Selection for Green Semantic Communication","created":"2024-06-22","cited_by_count":0,"area":null},{"id":"2412.15511","title":"RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability","created":"2024-12-20","cited_by_count":0,"area":null}],"next_cursor":null}