{"total":103,"rows":[{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270,"area":"agents"},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62,"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":"2502.14866","title":"LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention","created":"2025-02-20","cited_by_count":41,"area":"inference"},{"id":"2412.04315","title":"Densing Law of LLMs","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2411.10640","title":"BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices","created":"2024-11-16","cited_by_count":25,"area":"mllm"},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2411.02335","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","created":"2024-11-04","cited_by_count":22,"area":null},{"id":"2501.14794","title":"Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference","created":"2025-01-11","cited_by_count":22,"area":null},{"id":"2502.11880","title":"Bitnet.cpp: Efficient Edge Inference for Ternary LLMs","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2410.18311","title":"CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2501.12689","title":"IC-Cache: Efficient Large Language Model Serving via In-context Caching","created":"2025-01-22","cited_by_count":13,"area":null},{"id":"2505.02922","title":"RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference","created":"2025-05-05","cited_by_count":13,"area":"inference"},{"id":"2506.07533","title":"MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts","created":"2025-06-09","cited_by_count":12,"area":"moe"},{"id":"2412.01380","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","created":"2024-12-02","cited_by_count":11,"area":"inference"},{"id":"2506.24045","title":"Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC","created":"2025-06-30","cited_by_count":11,"area":"agents"},{"id":"2509.23324","title":"Scaling LLM Test-Time Compute with Mobile NPU on Smartphones","created":"2025-09-27","cited_by_count":11,"area":"lr"},{"id":"2410.03613","title":"Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices","created":"2024-10-04","cited_by_count":10,"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":"2505.17052","title":"SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs","created":"2025-05-16","cited_by_count":10,"area":"inference"},{"id":"2505.05950","title":"FloE: On-the-Fly MoE Inference on Memory-constrained GPU","created":"2025-05-09","cited_by_count":9,"area":"moe"},{"id":"2506.16500","title":"SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity","created":"2025-06-19","cited_by_count":9,"area":null},{"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,"area":"mllm"},{"id":"2506.10443","title":"MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices","created":"2025-06-12","cited_by_count":8,"area":"inference"},{"id":"2506.09351","title":"DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts","created":"2025-06-11","cited_by_count":7,"area":"moe"},{"id":"2507.08771","title":"BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity","created":"2025-07-11","cited_by_count":6,"area":"moe"},{"id":"2410.19274","title":"Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2507.02135","title":"Dissecting the Impact of Mobile DVFS Governors on LLM Inference Performance and Energy Efficiency","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2507.20984","title":"SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"id":"2510.12178","title":"Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey","created":"2025-10-14","cited_by_count":5,"area":null},{"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":"2511.11907","title":"KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference","created":"2025-11-14","cited_by_count":5,"area":"inference"},{"id":"2503.03777","title":"FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2504.07878","title":"Token Level Routing Inference System for Edge Devices","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2504.08378","title":"Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2506.08276","title":"LEANN: A Low-Storage Vector Index","created":"2025-06-09","cited_by_count":4,"area":"rag"},{"id":"2508.16703","title":"ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2511.07427","title":"DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones","created":"2025-10-20","cited_by_count":4,"area":"inference"},{"id":"2604.26837","title":"Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving","created":"2026-04-29","cited_by_count":4,"area":"inference"},{"id":"2406.18069","title":"Large Language Models for Cuffless Blood Pressure Measurement From Wearable Biosignals","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2409.09071","title":"Elastic On-Device LLM Service","created":"2024-09-08","cited_by_count":3,"area":null},{"id":"2410.14740","title":"Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2502.02818","title":"TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware","created":"2025-02-05","cited_by_count":3,"area":null},{"id":"2503.06019","title":"GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices","created":"2025-03-08","cited_by_count":3,"area":"mllm"},{"id":"2505.00232","title":"Scaling On-Device GPU Inference for Large Generative Models","created":"2025-05-01","cited_by_count":3,"area":null},{"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":"2508.18983","title":"SMoE: An Algorithm-System Co-Design for Pushing MoE to the Edge via Expert Substitution","created":"2025-08-26","cited_by_count":3,"area":"moe"},{"id":"2605.27081","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2502.11417","title":"DiSCo: Device-Server Collaborative LLM-Based Text Streaming Services","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2503.06029","title":"SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2507.08505","title":"Efficient Deployment of Vision-Language Models on Mobile Devices: A Case Study on OnePlus 13R","created":"2025-07-11","cited_by_count":2,"area":"mllm"},{"id":"2508.09035","title":"P/D-Device: Disaggregated Large Language Model between Cloud and Devices","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2605.16786","title":"Lever: Speculative LLM Inference on Smartphones","created":"2026-05-16","cited_by_count":2,"area":"inference"},{"id":"2606.23001","title":"EnerInfer: Energy-Aware On-Device LLM Inference","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2607.05476","title":"Parameter-Free Encoders Remain Viable for RDB Foundation Models","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2412.10856","title":"RWKV-edge: Deeply Compressed RWKV for Resource-Constrained Devices","created":"2024-12-14","cited_by_count":1,"area":null},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2505.17701","title":"COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2508.14302","title":"GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMs","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2510.05109","title":"Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices","created":"2025-09-25","cited_by_count":1,"area":"mllm"},{"id":"2510.11400","title":"FedHybrid: Breaking the Memory Wall of Federated Learning via Hybrid Tensor Management","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.15620","title":"On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding","created":"2025-10-17","cited_by_count":1,"area":"rag"},{"id":"2511.18692","title":"VLM in a flash: I/O-Efficient Sparsification of Vision-Language Model via Neuron Chunking","created":"2025-11-24","cited_by_count":1,"area":"mllm"},{"id":"2512.03927","title":"OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference","created":"2025-12-03","cited_by_count":1,"area":"moe"},{"id":"2512.09723","title":"Mixture of Lookup Key-Value Experts","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2601.11553","title":"PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices","created":"2025-12-10","cited_by_count":1,"area":"rag"},{"id":"2601.11652","title":"WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching","created":"2026-01-15","cited_by_count":1,"area":"inference"},{"id":"2602.15379","title":"FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2605.27435","title":"When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.21428","title":"Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study","created":"2026-06-19","cited_by_count":1,"area":"moe"},{"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":"2505.00745","title":"Responsive DNN Adaptation for Video Analytics against Environment Shift via Hierarchical Mobile-Cloud Collaborations","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2506.03296","title":"APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs","created":"2025-06-03","cited_by_count":0,"area":"inference"},{"id":"2506.12403","title":"Bridging the Digital Divide: Small Language Models as a Pathway for Physics and Photonics Education in Underdeveloped Regions","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2508.01540","title":"MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning","created":"2025-08-03","cited_by_count":0,"area":"mllm"},{"id":"2603.09642","title":"Multi-DNN Inference of Sparse Models on Edge SoCs","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.21026","title":"MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.26334","title":"Efficient, VRAM-Constrained xLM Inference on Clients","created":"2026-04-29","cited_by_count":0,"area":"mllm"},{"id":"2604.27476","title":"EdgeFM: Efficient Edge Inference for Vision-Language Models","created":"2026-04-30","cited_by_count":0,"area":"mllm"},{"id":"2606.11357","title":"TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.22496","title":"Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.18081","title":"SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.02995","title":"SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2608.25062","title":"FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration","created":"2026-08-25","cited_by_count":0,"area":"inference"},{"id":"2608.25777","title":"LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.01338","title":"mzCache: On-Device LLM Memory Management under Multitasking","created":"2026-09-01","cited_by_count":0,"area":"inference"},{"id":"2609.01798","title":"How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03079","title":"LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference","created":"2026-09-02","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":"2609.07966","title":"MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.12412","title":"HoliBench: A Cross-Platform Benchmarking and Deployment Toolkit for Foundation Models in CPS-IoT Applications","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.14507","title":"Physically Partitioned KVCache Format for CPU--GPU Load Balancing in MoE Inference","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2609.21172","title":"TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching","created":"2026-09-18","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}