{"list":"other","total":54,"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":"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2505.22618","title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding","created":"2025-05-28","cited_by_count":420},{"id":"2310.12823","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","created":"2023-10-19","cited_by_count":338},{"id":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268},{"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":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2006.04710","title":"The Lipschitz Constant of Self-Attention","created":"2020-06-08","cited_by_count":174},{"id":"2410.02506","title":"Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems","created":"2024-10-03","cited_by_count":141},{"id":"2402.12185","title":"ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning","created":"2024-02-19","cited_by_count":128},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126},{"id":"2404.09526","title":"LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism","created":"2024-04-15","cited_by_count":112},{"id":"2010.11418","title":"Rethinking pooling in graph neural networks","created":"2020-10-22","cited_by_count":73},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66},{"id":"2503.04629","title":"SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing","created":"2025-03-06","cited_by_count":49},{"id":"2312.15224","title":"LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination","created":"2023-12-23","cited_by_count":48},{"id":"2502.02723","title":"Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives","created":"2025-02-04","cited_by_count":48},{"id":"2509.25541","title":"Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play","created":"2025-09-29","cited_by_count":37},{"id":"2509.04439","title":"ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory","created":"2025-09-04","cited_by_count":24},{"id":"2408.11061","title":"StructuredRAG: JSON Response Formatting with Large Language Models","created":"2024-08-07","cited_by_count":22},{"id":"2412.12009","title":"SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval","created":"2024-12-16","cited_by_count":21},{"id":"2309.11268","title":"StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding","created":"2023-09-20","cited_by_count":19},{"id":"2504.10739","title":"HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding","created":"2025-04-14","cited_by_count":19},{"id":"2406.00059","title":"Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution","created":"2024-05-29","cited_by_count":17},{"id":"2412.05311","title":"DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent","created":"2024-11-28","cited_by_count":15},{"id":"2410.09873","title":"Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy","created":"2024-10-13","cited_by_count":14},{"id":"2410.18311","title":"CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation","created":"2024-10-23","cited_by_count":14},{"id":"2502.15816","title":"GenAI at the Edge: Comprehensive Survey on Empowering Edge Devices","created":"2025-02-19","cited_by_count":14},{"id":"2506.02281","title":"Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals","created":"2025-06-02","cited_by_count":13},{"id":"2507.17135","title":"SADA: Stability-guided Adaptive Diffusion Acceleration","created":"2025-07-23","cited_by_count":11},{"id":"2404.09529","title":"Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models","created":"2024-04-15","cited_by_count":10},{"id":"2311.05596","title":"LLM Augmented Hierarchical Agents","created":"2023-11-09","cited_by_count":9},{"id":"2403.15835","title":"Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression","created":"2024-03-23","cited_by_count":8},{"id":"2412.17029","title":"GraphAgent: Agentic Graph Language Assistant","created":"2024-12-22","cited_by_count":8},{"id":"2505.19235","title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","created":"2025-05-25","cited_by_count":8}],"next_cursor":null}