{"total":87,"rows":[{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177,"area":"inference"},{"id":"2305.05920","title":"Fast Distributed Inference Serving for Large Language Models","created":"2023-05-10","cited_by_count":145,"area":"inference"},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"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":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2406.01566","title":"Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow","created":"2024-06-03","cited_by_count":55,"area":null},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"area":null},{"id":"2407.14561","title":"NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals","created":"2024-07-18","cited_by_count":45,"area":null},{"id":"2404.14527","title":"M\\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity","created":"2024-04-22","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2501.04437","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","created":"2025-01-08","cited_by_count":23,"area":null},{"id":"2502.00722","title":"Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs","created":"2025-02-02","cited_by_count":22,"area":"inference"},{"id":"2308.04945","title":"LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking","created":"2023-08-09","cited_by_count":20,"area":null},{"id":"2210.11948","title":"lo-fi: distributed fine-tuning without communication","created":"2022-10-19","cited_by_count":19,"area":null},{"id":"2507.16372","title":"Depth Gives a False Sense of Privacy: LLM Internal States Inversion","created":"2025-07-22","cited_by_count":17,"area":null},{"id":"2401.12576","title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","created":"2024-01-23","cited_by_count":16,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2503.06433","title":"Seesaw: High-throughput LLM Inference via Model Re-sharding","created":"2025-03-09","cited_by_count":15,"area":"inference"},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2509.26182","title":"Parallax: Efficient LLM Inference Service over Decentralized Environment","created":"2025-09-30","cited_by_count":12,"area":"inference"},{"id":"2502.12996","title":"Eager Updates For Overlapped Communication and Computation in DiLoCo","created":"2025-02-18","cited_by_count":11,"area":null},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2403.10616","title":"DiPaCo: Distributed Path Composition","created":"2024-03-15","cited_by_count":10,"area":null},{"id":"2503.16585","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","created":"2025-03-20","cited_by_count":10,"area":"mllm"},{"id":"2509.10439","title":"Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration","created":"2025-09-12","cited_by_count":9,"area":null},{"id":"2305.08286","title":"A Language Model of Java Methods with Train/Test Deduplication","created":"2023-05-15","cited_by_count":7,"area":null},{"id":"2312.14751","title":"Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2401.07788","title":"Activations and Gradients Compression for Model-Parallel Training","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2410.03529","title":"No Need to Talk: Asynchronous Mixture of Language Models","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2503.12896","title":"Privacy-Preserving LLM Embedding Transmission for End-Cloud Collaboration","created":"2025-03-17","cited_by_count":5,"area":"rag"},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2407.02328","title":"Efficient Sparse Attention needs Adaptive Token Release","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2409.04833","title":"Achieving Peak Performance for Large Language Models: A Systematic Review","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2501.14784","title":"DeServe: Towards Affordable Offline LLM Inference via Decentralization","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2502.09921","title":"A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMs","created":"2025-02-14","cited_by_count":4,"area":"inference"},{"id":"2304.11257","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","created":"2023-04-21","cited_by_count":3,"area":null},{"id":"2312.00388","title":"LinguaLinked: A Distributed Large Language Model Inference System for Mobile Devices","created":"2023-12-01","cited_by_count":3,"area":"inference"},{"id":"2411.16003","title":"eFedLLM: Efficient LLM Inference Based on Federated Learning","created":"2024-11-24","cited_by_count":3,"area":"inference"},{"id":"2507.05731","title":"A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation","created":"2025-07-08","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":"2608.19147","title":"Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets","created":"2026-08-19","cited_by_count":3,"area":"inference"},{"id":"2507.06931","title":"DICE: Data Influence Cascade in Decentralized Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2602.02192","title":"ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2602.08019","title":"The Rise of Sparse Mixture-of-Experts: A Survey from Algorithmic Foundations to Decentralized Architectures and Vertical Domain Applications","created":"2026-02-08","cited_by_count":2,"area":"moe"},{"id":"2603.04028","title":"A Multi-Dimensional Quality Scoring Framework for Decentralized LLM Inference with Proof of Quality","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2604.11943","title":"ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2411.16462","title":"Lion Cub: Minimizing Communication Overhead in Distributed Lion","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2505.23219","title":"Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism","created":"2025-05-29","cited_by_count":1,"area":"inference"},{"id":"2506.02965","title":"PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs","created":"2025-06-03","cited_by_count":1,"area":"moe"},{"id":"2510.24242","title":"Enabling Near-realtime Remote Sensing via Satellite-Ground Collaboration of Large Vision-Language Models","created":"2025-10-28","cited_by_count":1,"area":"mllm"},{"id":"2602.18181","title":"SeedFlood: A Step Toward Scalable Decentralized Fine-Tuning of LLMs","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2604.17701","title":"WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference","created":"2026-04-20","cited_by_count":1,"area":"inference"},{"id":"2606.11196","title":"PoQ-Judge: A Multi-Architecture Evaluation Framework for Cost-Aware Proof-of-Quality in Decentralized LLM Inference","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2411.02908","title":"Photon: Federated LLM Pre-Training","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2506.21240","title":"Zero-Shot Learning for Obsolescence Risk Forecasting","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2507.05043","title":"MoLink: Distributed and Efficient Serving Framework for Large Models","created":"2025-07-07","cited_by_count":0,"area":"inference"},{"id":"2509.16508","title":"Federated Learning with Ad-hoc Adapter Insertions: The Case of Soft-Embeddings for Training Classifier-as-Retriever","created":"2025-09-20","cited_by_count":0,"area":"rag"},{"id":"2510.19670","title":"CoSense-LLM: Semantics at the Edge with Cost- and Uncertainty-Aware Cloud-Edge Cooperation","created":"2025-10-22","cited_by_count":0,"area":"inference"},{"id":"2602.16760","title":"Privacy-Aware Split Inference with Speculative Decoding for Large Language Models over Wide-Area Networks","created":"2026-02-18","cited_by_count":0,"area":"inference"},{"id":"2603.28622","title":"Trust-Aware Routing for Distributed Generative AI Inference at the Edge","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.02372","title":"Backdoor Attacks on Decentralised Post-Training","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.23464","title":"Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.28764","title":"SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.24722","title":"Decentralised AI Training and Inference with BlockTrain","created":"2026-06-23","cited_by_count":0,"area":null},{"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":"2608.07974","title":"ZeroLock: Concurrent Memory-Efficient LLM Training via Modular Update Decoupling","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2609.15664","title":"CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.19169","title":"SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops","created":"2026-09-12","cited_by_count":0,"area":"inference"},{"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":"2609.34045","title":"Kafila: Serving Large Language Models on a Trusted Set of Heterogeneous Commodity Machines","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35882","title":"GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2609.35883","title":"CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2609.38697","title":"Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI Infrastructure","created":"2026-09-30","cited_by_count":0,"area":"inference"},{"id":"2609.40093","title":"Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUs","created":"2026-09-30","cited_by_count":0,"area":"moe"},{"id":"2610.04867","title":"Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design","created":"2026-10-04","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":"2610.08268","title":"DySCo: Dynamic Sharding for Collaborative Edge-Cloud LLM Inference with Depth-Synchronized Batching","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}