{"total":16,"rows":[{"id":"2505.09598","title":"How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference","created":"2025-05-14","cited_by_count":76,"area":null},{"id":"2605.19537","title":"The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility","created":"2026-05-19","cited_by_count":8,"area":null},{"id":"2505.22107","title":"Curse of High Dimensionality Issue in Transformer for Long-context Modeling","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2510.13724","title":"FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2511.16682","title":"Bench360: Benchmarking Local LLM Inference from 360 Degrees","created":"2025-11-12","cited_by_count":4,"area":null},{"id":"2507.23093","title":"On the Sustainability of AI Inferences in the Edge","created":"2025-07-30","cited_by_count":1,"area":null},{"id":"2605.31432","title":"DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.17104","title":"Prefill/Decode-Aware Evaluation of LLM Inference on Emerging AI Accelerators","created":"2026-06-14","cited_by_count":1,"area":null},{"id":"2608.25053","title":"Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2503.05852","title":"Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2511.07776","title":"Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2602.09336","title":"FM SO.P: A Progressive Task Mixture Framework with Automatic Evaluation for Cross-Domain SOP Understanding","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2604.20420","title":"Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2608.26676","title":"FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.04053","title":"The Cost of a Hop: Benchmarking NLIP and A2A","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09778","title":"Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression Testing","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}