{"total":61,"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":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2501.02600","title":"TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms","created":"2025-01-05","cited_by_count":29,"area":null},{"id":"2407.04014","title":"Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems","created":"2024-07-04","cited_by_count":28,"area":"inference"},{"id":"2410.01518","title":"InfiniPot: Infinite Context Processing on Memory-Constrained LLMs","created":"2024-10-02","cited_by_count":27,"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":"2501.04437","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","created":"2025-01-08","cited_by_count":23,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2408.05235","title":"SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving","created":"2024-08-05","cited_by_count":19,"area":"inference"},{"id":"2409.04267","title":"An overview of domain-specific foundation model: key technologies, applications and challenges","created":"2024-09-06","cited_by_count":19,"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":"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":"2412.15246","title":"Accelerating Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":14,"area":"rag"},{"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":"2410.08391","title":"KV Prediction for Improved Time to First Token","created":"2024-10-10","cited_by_count":11,"area":"inference"},{"id":"2411.17741","title":"Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments","created":"2024-11-24","cited_by_count":9,"area":"inference"},{"id":"2504.11750","title":"Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures","created":"2025-04-16","cited_by_count":8,"area":null},{"id":"2501.18784","title":"Successor-Generator Planning with LLM-generated Heuristics","created":"2025-01-30","cited_by_count":7,"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":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","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":"2412.14426","title":"All-in-One Tuning and Structural Pruning for Domain-Specific LLMs","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2411.14458","title":"Improving training time and GPU utilization in geo-distributed language model training","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2501.10421","title":"CodEv: An Automated Grading Framework Leveraging Large Language Models for Consistent and Constructive Feedback","created":"2025-01-10","cited_by_count":3,"area":null},{"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":"2408.11939","title":"Matmul or No Matmul in the Era of 1-bit LLMs","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2410.10849","title":"Continuous Approximations for Improving Quantization Aware Training of LLMs","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2501.14105","title":"MedSlice: Fine-Tuned Large Language Models for Secure Clinical Note Sectioning","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2505.19349","title":"DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model","created":"2025-05-25","cited_by_count":2,"area":null},{"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":"2509.26534","title":"Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2601.08833","title":"Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications","created":"2025-11-14","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":"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":"2606.23001","title":"EnerInfer: Energy-Aware On-Device LLM Inference","created":"2026-06-22","cited_by_count":2,"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":"2502.10896","title":"Developing Conversational Speech Systems for Robots to Detect Speech Biomarkers of Cognition in People Living with Dementia","created":"2025-02-15","cited_by_count":1,"area":null},{"id":"2504.01994","title":"PIM-LLM: A High-Throughput Hybrid PIM Architecture for 1-bit LLMs","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2504.17070","title":"MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2505.06330","title":"Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2510.16439","title":"FrugalPrompt: Reducing Contextual Overhead in Large Language Models via Token Attribution","created":"2025-10-18","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":"2602.17697","title":"Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters","created":"2026-02-06","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":"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":"2411.09580","title":"Software Performance Engineering for Foundation Model-Powered Software","created":"2024-11-14","cited_by_count":0,"area":null},{"id":"2502.01806","title":"Toward Neurosymbolic Program Comprehension","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2505.19529","title":"Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.18674","title":"Is There a Case for Conversation Optimized Tokenizers in Large Language Models?","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2508.09231","title":"Beyond Technocratic XAI: The Who, What & How in Explanation Design","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2604.27032","title":"LLM-Guided Runtime Parameter Optimization for Energy-Efficient Model Inference","created":"2026-04-29","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":"2608.01891","title":"Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency Scaling","created":"2026-08-03","cited_by_count":0,"area":"inference"},{"id":"2608.25096","title":"Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.28667","title":"GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon","created":"2026-08-24","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":"2609.33965","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":"2610.08444","title":"ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference","created":"2026-10-06","cited_by_count":0,"area":"vla"}],"next_cursor":null}