{"list":"other","total":55,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2402.02750","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","created":"2024-02-05","cited_by_count":637},{"id":"2406.10774","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","created":"2024-06-16","cited_by_count":501},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"id":"2310.19102","title":"Atom: Low-bit Quantization for Efficient and Accurate LLM Serving","created":"2023-10-29","cited_by_count":272},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","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":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177},{"id":"2307.02628","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","created":"2023-07-05","cited_by_count":89},{"id":"2406.02542","title":"Loki: Low-rank Keys for Efficient Sparse Attention","created":"2024-06-04","cited_by_count":89},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47},{"id":"1602.03602","title":"Wireless Communications with Unmanned Aerial Vehicles: Opportunities and Challenges","created":"2016-02-11","cited_by_count":43},{"id":"2412.03248","title":"AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning","created":"2024-12-04","cited_by_count":43},{"id":"1907.02745","title":"Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data","created":"2019-07-05","cited_by_count":39},{"id":"2310.11731","title":"Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning","created":"2023-10-18","cited_by_count":36},{"id":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34},{"id":"1705.02723","title":"Joint Trajectory and Communication Design for Multi-UAV Enabled Wireless Networks","created":"2017-05-08","cited_by_count":32},{"id":"2501.02600","title":"TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms","created":"2025-01-05","cited_by_count":29},{"id":"2308.15030","title":"SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget","created":"2023-08-29","cited_by_count":27},{"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":"2408.05235","title":"SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving","created":"2024-08-05","cited_by_count":19},{"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":"2407.05347","title":"A Queueing Theoretic Perspective on Low-Latency LLM Inference with Variable Token Length","created":"2024-07-07","cited_by_count":16},{"id":"2507.12000","title":"DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding","created":"2025-07-16","cited_by_count":15},{"id":"2403.02694","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","created":"2024-03-05","cited_by_count":14},{"id":"2312.11882","title":"ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference","created":"2023-12-19","cited_by_count":13},{"id":"2411.17089","title":"KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation","created":"2024-11-26","cited_by_count":13},{"id":"2205.11854","title":"Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Learning","created":"2022-05-24","cited_by_count":12},{"id":"2507.01728","title":"Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach","created":"2025-07-02","cited_by_count":11},{"id":"2509.12211","title":"TinyServe: Query-Aware Cache Selection for Efficient LLM Serving","created":"2025-08-28","cited_by_count":9},{"id":"2405.07140","title":"Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization","created":"2024-05-12","cited_by_count":7},{"id":"2508.00234","title":"Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts","created":"2025-08-01","cited_by_count":7},{"id":"2311.05931","title":"Early-Exit Neural Networks with Nested Prediction Sets","created":"2023-11-10","cited_by_count":6},{"id":"2412.19494","title":"Retrieval-augmented Generation for GenAI-enabled Semantic Communications","created":"2024-12-27","cited_by_count":5},{"id":"1912.13203","title":"Modeling and Analysis of Energy Harvesting and Smart Grid-Powered Wireless Communication Networks: A Contemporary Survey","created":"2019-12-31","cited_by_count":4},{"id":"2508.11291","title":"Dynamic Quality-Latency Aware Routing for LLM Inference in Wireless Edge-Device Networks","created":"2025-08-15","cited_by_count":4},{"id":"2310.20375","title":"GreenCourier: Carbon-Aware Scheduling for Serverless Functions","created":"2023-10-31","cited_by_count":3},{"id":"2505.07841","title":"Task-Oriented Multimodal Token Transmission in Resource-Constrained Multiuser Networks","created":"2025-05-06","cited_by_count":3},{"id":"2512.04088","title":"Toward Sustainability-Aware LLM Inference on Edge Clusters","created":"2025-11-01","cited_by_count":3},{"id":"2507.07954","title":"Input Conditioned Layer Dropping in Speech Foundation Models","created":"2025-07-10","cited_by_count":2},{"id":"2508.01744","title":"AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization","created":"2025-08-03","cited_by_count":2},{"id":"2508.12597","title":"UAV Individual Identification via Distilled RF Fingerprints-Based LLM in ISAC Networks","created":"2025-08-18","cited_by_count":2},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2},{"id":"2406.15732","title":"AI-Driven Approaches for Optimizing Power Consumption: A Comprehensive Survey","created":"2024-06-22","cited_by_count":1},{"id":"2411.08672","title":"Joint Model Caching and Resource Allocation in Generative AI-Enabled Wireless Edge Networks","created":"2024-11-13","cited_by_count":1},{"id":"2512.01167","title":"A TinyML Reinforcement Learning Approach for Energy-Efficient Light Control in Low-Cost Greenhouse Systems","created":"2025-12-01","cited_by_count":1}],"next_cursor":null}