{"total":223,"rows":[{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079,"area":"mllm"},{"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":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471,"area":"inference"},{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415,"area":"lr"},{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307,"area":"inference"},{"id":"2502.17416","title":"Reasoning with Latent Thoughts: On the Power of Looped Transformers","created":"2025-02-24","cited_by_count":240,"area":"lr"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"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":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117,"area":"lr"},{"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":"2504.15364","title":"KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments","created":"2025-04-21","cited_by_count":51,"area":"inference"},{"id":"2404.01744","title":"Octopus v2: On-device language model for super agent","created":"2024-04-02","cited_by_count":47,"area":"agents"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"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":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2501.06713","title":"MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation","created":"2025-01-12","cited_by_count":28,"area":"rag"},{"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":"2506.14852","title":"Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents","created":"2025-06-17","cited_by_count":27,"area":"agents"},{"id":"2408.13986","title":"AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction","created":"2024-08-26","cited_by_count":25,"area":"agents"},{"id":"2403.06199","title":"Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models","created":"2024-03-10","cited_by_count":24,"area":"mllm"},{"id":"2510.07358","title":"Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts","created":"2025-10-08","cited_by_count":24,"area":"lr"},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22,"area":"distill"},{"id":"2410.01524","title":"HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models","created":"2024-10-02","cited_by_count":19,"area":"distill"},{"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":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15,"area":null},{"id":"2406.10290","title":"MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases","created":"2024-06-12","cited_by_count":14,"area":"mllm"},{"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":"2411.06681","title":"WDMoE: Wireless Distributed Mixture of Experts for Large Language Models","created":"2024-11-11","cited_by_count":12,"area":"moe"},{"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":"2501.01144","title":"BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference","created":"2025-01-02","cited_by_count":11,"area":"inference"},{"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":"2507.01079","title":"MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAG","created":"2025-07-01","cited_by_count":11,"area":"rag"},{"id":"2412.01822","title":"VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models","created":"2024-12-02","cited_by_count":10,"area":"mllm"},{"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":"2412.11475","title":"OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference","created":"2024-12-16","cited_by_count":8,"area":"mllm"},{"id":"2404.11459","title":"Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent","created":"2024-04-17","cited_by_count":7,"area":"agents"},{"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":"2411.14717","title":"FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data","created":"2024-11-22","cited_by_count":7,"area":"mllm"},{"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":"2505.12099","title":"TinyRS-R1: Compact Multimodal Language Model for Remote Sensing","created":"2025-05-17","cited_by_count":7,"area":"mllm"},{"id":"2509.17396","title":"EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments","created":"2025-09-22","cited_by_count":7,"area":"inference"},{"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":"2510.14961","title":"Efficient Parallel Samplers for Recurrent-Depth Models and Their Connection to Diffusion Language Models","created":"2025-10-16","cited_by_count":7,"area":"diffusion"},{"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":"2505.07984","title":"SAMChat: Introducing Chain of Thought Reasoning and GRPO to a Multimodal Small Language Model for Small Scale Remote Sensing","created":"2025-05-12","cited_by_count":6,"area":"lr"},{"id":"2506.14913","title":"Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning","created":"2025-06-17","cited_by_count":6,"area":"safety"},{"id":"2509.26497","title":"Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation","created":"2025-09-30","cited_by_count":6,"area":"distill"},{"id":"2404.17871","title":"Deep Learning Library Testing: Definition, Methods and Challenges","created":"2024-04-27","cited_by_count":5,"area":null},{"id":"2409.17312","title":"BabyLlama-2: Ensemble-Distilled Models Consistently Outperform Teachers With Limited Data","created":"2024-09-25","cited_by_count":5,"area":"distill"},{"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":"2509.24050","title":"Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"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":"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":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2602.09080","title":"Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models","created":"2026-02-09","cited_by_count":5,"area":"mllm"},{"id":"2602.10377","title":"Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs","created":"2026-02-10","cited_by_count":5,"area":"vla"},{"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":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"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":"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":"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":"2503.00245","title":"CoSMoEs: Compact Sparse Mixture of Experts","created":"2025-02-28","cited_by_count":3,"area":"moe"},{"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":"2509.16476","title":"Eye Gaze Tells You Where to Compute: Gaze-Driven Efficient VLMs","created":"2025-09-20","cited_by_count":3,"area":"mllm"},{"id":"2511.06719","title":"MobileLLM-Pro Technical Report","created":"2025-11-10","cited_by_count":3,"area":"distill"},{"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":"2601.00644","title":"FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding","created":"2026-01-02","cited_by_count":3,"area":"inference"},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"}],"next_cursor":"100"}