{"total":126,"rows":[{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723,"area":null},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"area":null},{"id":"2403.12844","title":"MELTing point: Mobile Evaluation of Language Transformers","created":"2024-03-19","cited_by_count":36,"area":null},{"id":"2410.20011","title":"A Survey of Small Language Models","created":"2024-10-25","cited_by_count":31,"area":null},{"id":"2504.06225","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","created":"2025-04-08","cited_by_count":28,"area":null},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2508.09136","title":"Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices","created":"2025-08-12","cited_by_count":16,"area":null},{"id":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2501.10885","title":"CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention","created":"2025-01-18","cited_by_count":14,"area":null},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2508.06097","title":"Recurrent Deep Differentiable Logic Gate Networks","created":"2025-08-08","cited_by_count":12,"area":null},{"id":"2601.10639","title":"STEM: Scaling Transformers with Embedding Modules","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2408.04413","title":"Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers","created":"2024-08-08","cited_by_count":11,"area":null},{"id":"2502.02883","title":"SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2502.06663","title":"EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2502.07503","title":"Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2407.00928","title":"FoldGPT: Simple and Effective Large Language Model Compression Scheme","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2407.09276","title":"H2O-Danube3 Technical Report","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2409.20247","title":"Resource Allocation for Stable LLM Training in Mobile Edge Computing","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2411.17800","title":"STAR: Synthesis of Tailored Architectures","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2502.04164","title":"Efficient Distributed Optimization under Heavy-Tailed Noise","created":"2025-02-06","cited_by_count":7,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2602.05495","title":"Transport and Merge: Cross-Architecture Merging for Large Language Models","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2502.03460","title":"Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2404.17871","title":"Deep Learning Library Testing: Definition, Methods and Challenges","created":"2024-04-27","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":"2508.04581","title":"Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning","created":"2025-08-06","cited_by_count":5,"area":null},{"id":"2509.14275","title":"FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health","created":"2025-09-16","cited_by_count":5,"area":null},{"id":"2510.06126","title":"lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2602.11506","title":"RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2406.04523","title":"Proofread: Fixes All Errors with One Tap","created":"2024-06-06","cited_by_count":4,"area":null},{"id":"2410.16703","title":"PLDR-LLM: Large Language Model from Power Law Decoder Representations","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2501.14713","title":"FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing","created":"2025-01-24","cited_by_count":4,"area":null},{"id":"2606.01495","title":"CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability","created":"2026-05-31","cited_by_count":4,"area":null},{"id":"2403.07921","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2408.10230","title":"A General-Purpose Device for Interaction with LLMs","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2411.05281","title":"Fox-1: Open Small Language Model for Cloud and Edge","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2502.06924","title":"XAMBA: Enabling Efficient State Space Models on Resource-Constrained Neural Processing Units","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2505.06461","title":"Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference","created":"2025-05-09","cited_by_count":3,"area":null},{"id":"2506.09316","title":"On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2509.07324","title":"Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagation","created":"2025-09-09","cited_by_count":3,"area":null},{"id":"2511.06838","title":"P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2605.17172","title":"OpenJarvis: Personal AI, On Personal Devices","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2407.00996","title":"Can Small Language Models Learn, Unlearn, and Retain Noise Patterns?","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2409.00286","title":"OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2410.19456","title":"Computational Bottlenecks of Training Small-scale Large Language Models","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2412.14708","title":"Creation of AI-driven Smart Spaces for Enhanced Indoor Environments -- A Survey","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2502.11417","title":"DiSCo: Device-Server Collaborative LLM-Based Text Streaming Services","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2505.24009","title":"Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2505.24149","title":"RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2506.09061","title":"EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2508.04337","title":"Modelling and Classifying the Components of a Literature Review","created":"2025-08-06","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":"2509.20321","title":"Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2509.25850","title":"RL-Guided Data Selection for Language Model Finetuning","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.18383","title":"MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2601.10580","title":"Form and Meaning in Intrinsic Multilingual Evaluations","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2602.00166","title":"Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.03420","title":"Zero-Shot Quantization via Weight-Space Arithmetic","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2605.04062","title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2605.25966","title":"Mapping the Schedule x Bit-Width Boundary in Sub-100M Quantisation-Aware Training","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2405.19284","title":"Optimizing Foundation Model Inference on a Many-tiny-core Open-source RISC-V Platform","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2408.11845","title":"LLaMA based Punctuation Restoration With Forward Pass Only Decoding","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2411.09837","title":"Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models","created":"2024-11-14","cited_by_count":1,"area":null},{"id":"2501.06126","title":"Merging Feed-Forward Sublayers for Compressed Transformers","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2502.15761","title":"AIvaluateXR: An Evaluation Framework for on-Device AI in XR with Benchmarking Results","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2503.21782","title":"Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2504.09687","title":"Domain-Adaptive Continued Pre-Training of Small Language Models","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2507.01457","title":"Tensor Program Optimization for the RISC-V Vector Extension Using Probabilistic Programs","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2507.14802","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","created":"2025-07-20","cited_by_count":1,"area":null},{"id":"2509.06326","title":"AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2510.25784","title":"zFLoRA: Zero-Latency Fused Low-Rank Adapters","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2601.00543","title":"ECR: Manifold-Guided Semantic Cues for Compact Language Models","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2603.15954","title":"MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment","created":"2026-03-16","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":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.29128","title":"Apertus LLM Family Expansion via Distillation and Quantization","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.31796","title":"CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.25053","title":"Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.32534","title":"DepthBench: Measuring How Residual Connections Enable More Computational Depth","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2503.10707","title":"CALLM: Understanding Cancer Survivors' Emotions and Intervention Opportunities via Mobile Diaries and Context-Aware Language Models","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.00831","title":"SmallPlan: Leverage Small Language Models for Sequential Path Planning with Simulation-Powered, LLM-Guided Distillation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2506.00859","title":"FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2506.05402","title":"Lorica: A Synergistic Fine-Tuning Framework for Advancing Personalized Adversarial Robustness","created":"2025-06-04","cited_by_count":0,"area":null},{"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":"2506.13514","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2507.10580","title":"An Offline Mobile Conversational Agent for Mental Health Support: Learning from Emotional Dialogues and Psychological Texts with Student-Centered Evaluation","created":"2025-07-11","cited_by_count":0,"area":null}],"next_cursor":"100"}