{"list":"other","total":51,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2312.12456","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","created":"2023-12-16","cited_by_count":217},{"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},{"id":"2007.03051","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","created":"2020-07-06","cited_by_count":169},{"id":"2510.04374","title":"GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks","created":"2025-10-05","cited_by_count":158},{"id":"2503.04761","title":"Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations","created":"2025-02-11","cited_by_count":96},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"2401.17644","title":"BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems","created":"2024-01-31","cited_by_count":87},{"id":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84},{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79},{"id":"2011.14203","title":"EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference","created":"2020-11-28","cited_by_count":70},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61},{"id":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55},{"id":"2502.03261","title":"CARROT: A Cost Aware Rate Optimal Router","created":"2025-02-05","cited_by_count":39},{"id":"2505.19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","created":"2025-05-26","cited_by_count":38},{"id":"2508.12631","title":"Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing","created":"2025-08-18","cited_by_count":34},{"id":"2006.07512","title":"FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply","created":"2020-06-12","cited_by_count":33},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25},{"id":"2504.08850","title":"SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting","created":"2025-04-11","cited_by_count":23},{"id":"2409.03753","title":"WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild","created":"2024-09-05","cited_by_count":20},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20},{"id":"2407.00010","title":"Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads","created":"2024-04-25","cited_by_count":17},{"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},{"id":"2505.07460","title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","created":"2025-05-12","cited_by_count":14},{"id":"2506.09397","title":"SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving","created":"2025-06-11","cited_by_count":13},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13},{"id":"2408.06646","title":"Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models","created":"2024-08-13","cited_by_count":11},{"id":"2312.10078","title":"Early ChatGPT User Portrait through the Lens of Data","created":"2023-12-10","cited_by_count":6},{"id":"2503.18989","title":"A Novel Hat-Shaped Device-Cloud Collaborative Inference Framework for Large Language Models","created":"2025-03-23","cited_by_count":5}],"next_cursor":null}