{"total":55,"rows":[{"id":"2509.18101","title":"A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services","created":"2025-08-30","cited_by_count":17,"area":null},{"id":"2505.14733","title":"The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute","created":"2025-05-20","cited_by_count":15,"area":"lr"},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2505.21627","title":"Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2511.05722","title":"OckBench: Measuring the Efficiency of LLM Reasoning","created":"2025-11-07","cited_by_count":11,"area":"lr"},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2506.12353","title":"Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models","created":"2025-06-14","cited_by_count":10,"area":"lr"},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.05695","title":"SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference","created":"2026-02-05","cited_by_count":6,"area":null},{"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":"2510.27256","title":"ECVL-ROUTER: Scenario-Aware Routing for Vision-Language Models","created":"2025-10-31","cited_by_count":4,"area":"mllm"},{"id":"2601.22362","title":"Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2603.15699","title":"This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2607.26571","title":"From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs","created":"2026-07-29","cited_by_count":3,"area":null},{"id":"2508.16700","title":"GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model","created":"2025-08-22","cited_by_count":2,"area":"moe"},{"id":"2509.04827","title":"VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing","created":"2025-09-05","cited_by_count":2,"area":"inference"},{"id":"2602.05712","title":"Towards Green AI: Decoding the Energy of LLM Inference in Software Development","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.16068","title":"Resource Consumption Threats in Large Language Models","created":"2026-03-17","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":"2608.28044","title":"Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms","created":"2026-08-28","cited_by_count":2,"area":"moe"},{"id":"2510.02810","title":"Dissecting Transformers: A CLEAR Perspective towards Green AI","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.21970","title":"Performance Trade-offs of Optimizing Small Language Models for E-Commerce","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2512.24863","title":"Big AI is accelerating the metacrisis: What can we do?","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2601.05267","title":"Transforming User Defined Criteria into Explainable Indicators with an Integrated LLM AHP System","created":"2025-11-12","cited_by_count":1,"area":null},{"id":"2601.22357","title":"Small Talk, Big Impact: The Energy Cost of Thanking AI","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.06064","title":"iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2602.17697","title":"Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.26378","title":"Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2607.00274","title":"SEFORA: Student Essays with Feedback Corpus and LLM Feedback Evaluation Framework","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.09172","title":"Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2506.06446","title":"Tokenization Multiplicity Leads to Arbitrary Price Variation in LLM-as-a-service","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2512.23767","title":"Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2602.09691","title":"Is Knowledge Distillation Actually Greener? A Case Study in Machine Translation","created":"2026-02-10","cited_by_count":0,"area":"distill"},{"id":"2603.02633","title":"Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization Guarantees","created":"2026-03-03","cited_by_count":0,"area":"moe"},{"id":"2603.02949","title":"SEALing the Gap: A Reference Framework for LLM Inference Carbon Estimation via Multi-Benchmark Driven Embodiment","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.23668","title":"Energy Efficient Software Hardware CoDesign for Machine Learning: From TinyML to Large Language Models","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.16368","title":"Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM","created":"2026-03-22","cited_by_count":0,"area":"inference"},{"id":"2605.27787","title":"Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems","created":"2026-05-27","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":"2606.10861","title":"From Perception to Action: Can UI Interventions Foster Sustainable LLM Chatbot","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.22606","title":"Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.04553","title":"Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.18068","title":"Human Grounded Evaluation of Large Language Models for Optical Network Automation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.21985","title":"Unified Static-Dynamic Pruning for Efficient LLM Inference","created":"2026-07-24","cited_by_count":0,"area":"inference"},{"id":"2608.01530","title":"ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentation","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.12350","title":"From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.18149","title":"TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2609.03716","title":"Artificial Intelligence for Energy Optimization in Data Centers","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.05565","title":"Toward Sustainable Distributed LLM Inference: A Systems Synthesis and Research Agenda for an Energy-, Carbon-, and Cache-Aware llm-d Control Plane","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.19499","title":"Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.23130","title":"From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving","created":"2026-09-19","cited_by_count":0,"area":"inference"},{"id":"2609.31341","title":"The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33965","title":"Greenpixie's AI Token Methodology: Assessing the Energy, Water and CO2-eq Impact of AI Tokens for Open and Closed Weight Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35569","title":"Beyond Energy: When Sustainability Dimensions Reshape LLM Serving Decisions","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04295","title":"Language-Conditioned Token and Reasoning Efficiency in Large Language Models: A Paired Cross-Lingual Study Protocol","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}