{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"2311.18677","title":"Splitwise: Efficient generative LLM inference using phase splitting","created":"2023-11-30","cited_by_count":558},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"2305.09781","title":"SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification","created":"2023-05-16","cited_by_count":365},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"id":"2411.10109","title":"LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals","created":"2024-11-15","cited_by_count":249},{"id":"2403.03952","title":"Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders","created":"2024-03-06","cited_by_count":224},{"id":"2405.16444","title":"CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion","created":"2024-05-26","cited_by_count":223},{"id":"2310.07240","title":"CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving","created":"2023-10-11","cited_by_count":203},{"id":"2412.20138","title":"TradingAgents: Multi-Agents LLM Financial Trading Framework","created":"2024-12-28","cited_by_count":188},{"id":"2508.07976","title":"Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL","created":"2025-08-11","cited_by_count":150},{"id":"2402.14034","title":"AgentScope: A Flexible yet Robust Multi-Agent Platform","created":"2024-02-21","cited_by_count":121},{"id":"2405.19888","title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","created":"2024-05-30","cited_by_count":99},{"id":"1904.03711","title":"Neo: A Learned Query Optimizer","created":"2019-04-07","cited_by_count":80},{"id":"2002.11054","title":"MLIR: A Compiler Infrastructure for the End of Moore's Law","created":"2020-02-25","cited_by_count":65},{"id":"2502.14902","title":"PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths","created":"2025-02-18","cited_by_count":61},{"id":"2008.09213","title":"Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads","created":"2020-08-20","cited_by_count":56},{"id":"2410.12189","title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","created":"2024-10-16","cited_by_count":52},{"id":"2502.05957","title":"AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents","created":"2025-02-09","cited_by_count":52},{"id":"2411.00114","title":"Project Sid: Many-agent simulations toward AI civilization","created":"2024-10-31","cited_by_count":49},{"id":"2005.14038","title":"HetPipe: Enabling Large DNN Training on (Whimpy) Heterogeneous GPU Clusters through Integration of Pipelined Model Parallelism and Data Parallelism","created":"2020-05-28","cited_by_count":46},{"id":"1805.01046","title":"BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics","created":"2018-05-02","cited_by_count":41},{"id":"2405.14696","title":"A Declarative System for Optimizing AI Workloads","created":"2024-05-23","cited_by_count":37},{"id":"2407.11418","title":"Semantic Operators: A Declarative Model for Rich, AI-based Data Processing","created":"2024-07-16","cited_by_count":34},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32},{"id":"2403.05821","title":"Optimizing LLM Queries in Relational Data Analytics Workloads","created":"2024-03-09","cited_by_count":22},{"id":"2508.16279","title":"AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications","created":"2025-08-22","cited_by_count":17},{"id":"2412.09237","title":"LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation","created":"2024-12-12","cited_by_count":15},{"id":"2506.01979","title":"SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism","created":"2025-05-16","cited_by_count":15},{"id":"2411.03519","title":"AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution","created":"2024-11-05","cited_by_count":14},{"id":"2201.00309","title":"Optimizing Machine Learning Inference Queries with Correlative Proxy Models","created":"2022-01-02","cited_by_count":13},{"id":"2205.04713","title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","created":"2022-05-10","cited_by_count":12},{"id":"2503.15520","title":"Agent-S: LLM Agentic workflow to automate Standard Operating Procedures","created":"2025-02-03","cited_by_count":10},{"id":"2503.10918","title":"Resource Heterogeneity-Aware and Utilization-Enhanced Scheduling for Deep Learning Clusters","created":"2025-03-13","cited_by_count":1}],"next_cursor":null}