{"total":69,"rows":[{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2312.06786","title":"Mixture-of-Linear-Experts for Long-term Time Series Forecasting","created":"2023-12-11","cited_by_count":29,"area":null},{"id":"2401.08383","title":"Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference","created":"2024-01-16","cited_by_count":28,"area":"moe"},{"id":"2408.11304","title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","created":"2024-08-21","cited_by_count":27,"area":"moe"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2505.01821","title":"Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey","created":"2025-05-03","cited_by_count":14,"area":null},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2505.07634","title":"Neural Brain: A Neuroscience-inspired Framework for Embodied Agents","created":"2025-05-12","cited_by_count":10,"area":"agents"},{"id":"2512.24618","title":"Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models","created":"2025-12-31","cited_by_count":10,"area":"agents"},{"id":"2606.25115","title":"Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory","created":"2026-06-23","cited_by_count":9,"area":"agents"},{"id":"2401.01923","title":"The Internet of Things in the Era of Generative AI: Vision and Challenges","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2505.16056","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","created":"2025-05-21","cited_by_count":8,"area":"moe"},{"id":"2402.09360","title":"HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference","created":"2024-02-14","cited_by_count":7,"area":"inference"},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2505.09214","title":"The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2507.06567","title":"SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference","created":"2025-07-09","cited_by_count":7,"area":"moe"},{"id":"2508.12851","title":"Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement","created":"2025-08-18","cited_by_count":7,"area":"moe"},{"id":"2501.09410","title":"MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models","created":"2025-01-16","cited_by_count":6,"area":"moe"},{"id":"2510.15312","title":"Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution","created":"2025-10-17","cited_by_count":5,"area":"rag"},{"id":"2511.10054","title":"BuddyMoE: Exploiting Expert Redundancy to Accelerate Memory-Constrained Mixture-of-Experts Inference","created":"2025-11-13","cited_by_count":5,"area":"moe"},{"id":"2605.10380","title":"Agent-X: Full Pipeline Acceleration of On-device AI Agents","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2601.21198","title":"ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling","created":"2026-01-29","cited_by_count":4,"area":"moe"},{"id":"2603.21276","title":"Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity","created":"2026-03-22","cited_by_count":4,"area":"moe"},{"id":"2408.10230","title":"A General-Purpose Device for Interaction with LLMs","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2410.10181","title":"Scalable Multi-Domain Adaptation of Language Models using Modular Experts","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2503.00245","title":"CoSMoEs: Compact Sparse Mixture of Experts","created":"2025-02-28","cited_by_count":3,"area":"moe"},{"id":"2506.19884","title":"MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection","created":"2025-06-24","cited_by_count":3,"area":null},{"id":"2502.04747","title":"Every Software as an Agent: Blueprint and Case Study","created":"2025-02-07","cited_by_count":2,"area":"agents"},{"id":"2508.09208","title":"CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge","created":"2025-08-10","cited_by_count":2,"area":"moe"},{"id":"2603.19172","title":"DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge","created":"2026-03-19","cited_by_count":2,"area":"moe"},{"id":"2604.06515","title":"Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees","created":"2026-04-07","cited_by_count":2,"area":"moe"},{"id":"2607.02501","title":"Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots","created":"2026-07-02","cited_by_count":2,"area":"wm"},{"id":"2607.05476","title":"Parameter-Free Encoders Remain Viable for RDB Foundation Models","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2402.12061","title":"All Language Models Large and Small","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2402.16848","title":"InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2508.19078","title":"Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices","created":"2025-08-26","cited_by_count":1,"area":"moe"},{"id":"2602.13052","title":"Quantization-Aware Collaborative Inference for Large Embodied AI Models","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2608.18261","title":"Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall: A Pre-Registered Negative Result with a Systems Measurement Study","created":"2026-08-18","cited_by_count":1,"area":"moe"},{"id":"2509.23248","title":"Resource-Aware LLM Reasoning for Mobile Edge General Intelligence","created":"2025-09-27","cited_by_count":0,"area":"lr"},{"id":"2602.23312","title":"Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.07857","title":"Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2604.26334","title":"Efficient, VRAM-Constrained xLM Inference on Clients","created":"2026-04-29","cited_by_count":0,"area":"mllm"},{"id":"2605.11537","title":"Fast MoE Inference via Predictive Prefetching and Expert Replication","created":"2026-05-12","cited_by_count":0,"area":"moe"},{"id":"2607.20981","title":"Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligence","created":"2026-07-23","cited_by_count":0,"area":"moe"},{"id":"2607.23099","title":"Decoding the Skew: Distribution-Aware MoE Inference with Adaptive Kernel Dispatch","created":"2026-07-25","cited_by_count":0,"area":"moe"},{"id":"2608.00577","title":"HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference","created":"2026-08-01","cited_by_count":0,"area":"moe"},{"id":"2608.05303","title":"EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.10362","title":"MemSpec: Memory-Aware Runtime for Adaptive Draft Scheduling in Speculative Decoding on Edge Devices","created":"2026-08-11","cited_by_count":0,"area":"inference"},{"id":"2609.01338","title":"mzCache: On-Device LLM Memory Management under Multitasking","created":"2026-09-01","cited_by_count":0,"area":"inference"},{"id":"2609.04238","title":"Budgeting Bytes: A Windowed Storage Roofline and Dual-Budget Architecture Ablations for Storage-Bound LLM Decoding","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.06551","title":"EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs","created":"2026-09-06","cited_by_count":0,"area":"moe"},{"id":"2609.14643","title":"BigMoMo: Efficient Inference of Large-Scale MoE with Speculative Decoding on Mobile Devices","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2609.18110","title":"SSD-LLaMA: SSD-Native Inference for Trillion-Parameter MoE at 1+ Token/s on a Consumer PC","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.23582","title":"ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.26061","title":"TopoCompress: Topology Aware Token Compression Algorithm for Distributed Edge MoE Inference","created":"2026-08-01","cited_by_count":0,"area":"moe"},{"id":"2609.35882","title":"GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2610.06387","title":"Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07219","title":"Cascadia: Resident 975B MoE Inference on Eleven AI PCs","created":"2026-10-05","cited_by_count":0,"area":"moe"},{"id":"2610.13328","title":"DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving","created":"2026-10-09","cited_by_count":0,"area":"moe"}],"next_cursor":null}