{"list":"other","total":56,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"2311.18677","title":"Splitwise: Efficient generative LLM inference using phase splitting","created":"2023-11-30","cited_by_count":558},{"id":"2403.02310","title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve","created":"2024-03-04","cited_by_count":526},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295},{"id":"2408.00724","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","created":"2024-08-01","cited_by_count":290},{"id":"2311.04939","title":"LooGLE: Can Long-Context Language Models Understand Long Contexts?","created":"2023-11-08","cited_by_count":202},{"id":"1802.05399","title":"Competitive caching with machine learned advice","created":"2018-02-15","cited_by_count":195},{"id":"2006.09123","title":"Algorithms with Predictions","created":"2020-06-16","cited_by_count":153},{"id":"2405.08813","title":"CinePile: A Long Video Question Answering Dataset and Benchmark","created":"2024-05-14","cited_by_count":114},{"id":"2405.19888","title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","created":"2024-05-30","cited_by_count":99},{"id":"2305.13144","title":"Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline","created":"2023-05-22","cited_by_count":86},{"id":"2408.15792","title":"Efficient LLM Scheduling by Learning to Rank","created":"2024-08-28","cited_by_count":85},{"id":"2306.06000","title":"S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput","created":"2023-06-09","cited_by_count":81},{"id":"2402.05099","title":"Hydragen: High-Throughput LLM Inference with Shared Prefixes","created":"2024-02-07","cited_by_count":73},{"id":"2404.08509","title":"Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction","created":"2024-04-12","cited_by_count":66},{"id":"2412.20993","title":"Efficiently Scaling LLM Reasoning with Certaindex","created":"2024-12-30","cited_by_count":58},{"id":"1902.00732","title":"Scheduling with Predictions and the Price of Misprediction","created":"2019-02-02","cited_by_count":47},{"id":"2410.01035","title":"Don't Stop Me Now: Embedding Based Scheduling for LLMs","created":"2024-10-01","cited_by_count":35},{"id":"2402.01869","title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","created":"2024-02-02","cited_by_count":33},{"id":"2103.05604","title":"Flow Time Scheduling with Uncertain Processing Time","created":"2021-03-09","cited_by_count":29},{"id":"2406.04785","title":"Enabling Efficient Batch Serving for LMaaS via Generation Length Prediction","created":"2024-06-07","cited_by_count":20},{"id":"2109.08424","title":"Distortion-Oblivious Algorithms for Minimizing Flow Time","created":"2021-09-17","cited_by_count":15},{"id":"2110.00633","title":"Uniform Bounds for Scheduling with Job Size Estimates","created":"2021-10-01","cited_by_count":12},{"id":"2309.02233","title":"Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering","created":"2023-09-05","cited_by_count":11},{"id":"2006.15463","title":"Queues with Small Advice","created":"2020-06-27","cited_by_count":9},{"id":"2402.03564","title":"SkipPredict: When to Invest in Predictions for Scheduling","created":"2024-02-05","cited_by_count":3},{"id":"1410.6122","title":"PSBS: Practical Size-Based Scheduling","created":"2014-10-22","cited_by_count":2},{"id":"1905.12155","title":"The Supermarket Model with Known and Predicted Service Times","created":"2019-05-23","cited_by_count":2},{"id":"1907.04824","title":"Scheduling With Inexact Job Sizes: The Merits of Shortest Processing Time First","created":"2019-07-10","cited_by_count":2},{"id":"1403.5996","title":"Revisiting Size-Based Scheduling with Estimated Job Sizes","created":"2014-03-24","cited_by_count":1}],"next_cursor":null}