{"total":62,"rows":[{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2512.02924","title":"AutoNeural: Co-Designing Vision-Language Models for NPU Inference","created":"2025-12-02","cited_by_count":17,"area":"mllm"},{"id":"2504.19720","title":"Taming the Titans: A Survey of Efficient LLM Inference Serving","created":"2025-04-28","cited_by_count":16,"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":"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":"2409.16997","title":"INT-FlashAttention: Enabling Flash Attention for INT8 Quantization","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2411.05046","title":"PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training","created":"2024-11-07","cited_by_count":7,"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":"2510.16040","title":"Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing","created":"2025-10-16","cited_by_count":5,"area":"inference"},{"id":"2504.00002","title":"Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices","created":"2025-03-10","cited_by_count":4,"area":null},{"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":"2409.15342","title":"Recall: Empowering Multimodal Embedding for Edge Devices","created":"2024-09-09","cited_by_count":3,"area":null},{"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":"2601.19908","title":"CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference","created":"2025-12-12","cited_by_count":3,"area":"mllm"},{"id":"2602.08722","title":"QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.23791","title":"The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense","created":"2026-03-24","cited_by_count":3,"area":"agents"},{"id":"2504.15303","title":"High-Throughput LLM inference on Heterogeneous Clusters","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2505.11417","title":"EdgeWisePersona: A Dataset for On-Device User Profiling from Natural Language Interactions","created":"2025-05-16","cited_by_count":2,"area":null},{"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":"2509.26534","title":"Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.01439","title":"Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2602.06063","title":"Mapping Gemma3 onto an Edge Dataflow Architecture","created":"2026-01-27","cited_by_count":2,"area":null},{"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":"2501.10187","title":"Good things come in small packages: Should we build AI clusters with Lite-GPUs?","created":"2025-01-17","cited_by_count":1,"area":null},{"id":"2505.08793","title":"Onboard Optimization and Learning: A Survey","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2506.13772","title":"MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs","created":"2025-06-05","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":"2601.11553","title":"PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices","created":"2025-12-10","cited_by_count":1,"area":"rag"},{"id":"2602.00397","title":"Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity","created":"2026-01-30","cited_by_count":1,"area":null},{"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":"2604.12931","title":"Token Encoding for Semantic Recovery","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.21231","title":"SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference","created":"2026-04-23","cited_by_count":1,"area":"inference"},{"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":"2606.11257","title":"Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite","created":"2026-06-09","cited_by_count":1,"area":"rag"},{"id":"2606.13740","title":"Efficient On-Device Diffusion LLM Inference with Mobile NPU","created":"2026-06-11","cited_by_count":1,"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":"2509.25155","title":"Context-Driven Performance Modeling for Causal Inference Operators on Neural Processing Units","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2512.11532","title":"Parallax: Runtime Parallelization for Operator Fallbacks in Heterogeneous Edge Systems","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2512.17108","title":"Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.12962","title":"TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.26835","title":"ANVIL: Accelerator-Native Video Interpolation via Codec Motion Vector Priors","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.00789","title":"Make Your LVLM KV Cache More Lightweight","created":"2026-05-01","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":"2606.20571","title":"Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices","created":"2026-04-27","cited_by_count":0,"area":"rag"},{"id":"2606.27634","title":"Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.14618","title":"PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.25498","title":"Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling","created":"2026-07-28","cited_by_count":0,"area":"inference"},{"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":"2609.01338","title":"mzCache: On-Device LLM Memory Management under Multitasking","created":"2026-09-01","cited_by_count":0,"area":"inference"},{"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":"2609.06674","title":"Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces","created":"2026-09-06","cited_by_count":0,"area":null},{"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":"2609.21172","title":"TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching","created":"2026-09-18","cited_by_count":0,"area":"inference"},{"id":"2609.23314","title":"ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.32114","title":"Empowering Hybrid Attention Models on NPUs","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34727","title":"Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2610.00465","title":"AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.17321","title":"GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17436","title":"SchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}