{"total":217,"rows":[{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057,"area":"alignment"},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617,"area":"inference"},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270,"area":"agents"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2403.19708","title":"Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention","created":"2024-03-23","cited_by_count":163,"area":"inference"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"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":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128,"area":null},{"id":"2409.15790","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":"2406.06282","title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone","created":"2024-06-10","cited_by_count":103,"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":"2411.11217","title":"MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs","created":"2024-11-18","cited_by_count":73,"area":"moe"},{"id":"2402.07033","title":"Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models","created":"2024-02-10","cited_by_count":71,"area":"moe"},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62,"area":null},{"id":"2408.02544","title":"Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions","created":"2024-08-05","cited_by_count":56,"area":"mllm"},{"id":"2408.14690","title":"Training-Free Activation Sparsity in Large Language Models","created":"2024-08-26","cited_by_count":55,"area":"inference"},{"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":"2403.11421","title":"FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines","created":"2024-03-18","cited_by_count":49,"area":"inference"},{"id":"2410.18038","title":"POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","created":"2024-10-23","cited_by_count":47,"area":null},{"id":"2402.13516","title":"ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models","created":"2024-02-21","cited_by_count":45,"area":"inference"},{"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":"2410.22134","title":"ProMoE: Fast MoE-based LLM Serving using Proactive Caching","created":"2024-10-29","cited_by_count":40,"area":"moe"},{"id":"2412.04315","title":"Densing Law of LLMs","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2406.05955","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","created":"2024-06-10","cited_by_count":38,"area":"moe"},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2411.01142","title":"NEO: Saving GPU Memory Crisis with CPU Offloading for Online LLM Inference","created":"2024-11-02","cited_by_count":37,"area":"inference"},{"id":"2502.17298","title":"Delta Decompression for MoE-based LLMs Compression","created":"2025-02-24","cited_by_count":33,"area":"moe"},{"id":"2506.23266","title":"Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging","created":"2025-06-29","cited_by_count":28,"area":"moe"},{"id":"2402.13720","title":"Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding","created":"2024-02-21","cited_by_count":25,"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":"2503.18292","title":"Jenga: Effective Memory Management for Serving LLM with Heterogeneity","created":"2025-03-24","cited_by_count":25,"area":"inference"},{"id":"2406.02500","title":"Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques","created":"2024-06-04","cited_by_count":24,"area":"moe"},{"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":"2504.08850","title":"SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting","created":"2025-04-11","cited_by_count":23,"area":"inference"},{"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":"2502.11880","title":"Bitnet.cpp: Efficient Edge Inference for Ternary LLMs","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"area":null},{"id":"2410.04691","title":"Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning","created":"2024-10-07","cited_by_count":21,"area":null},{"id":"2504.19449","title":"R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference","created":"2025-04-28","cited_by_count":21,"area":"inference"},{"id":"2504.15299","title":"D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving","created":"2025-04-17","cited_by_count":20,"area":"moe"},{"id":"2408.05235","title":"SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving","created":"2024-08-05","cited_by_count":19,"area":"inference"},{"id":"2410.17954","title":"ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling","created":"2024-10-23","cited_by_count":19,"area":"moe"},{"id":"2411.16102","title":"BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2504.08784","title":"SLOs-Serve: Optimized Serving of Multi-SLO LLMs","created":"2025-04-05","cited_by_count":19,"area":null},{"id":"2412.10543","title":"METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation","created":"2024-12-13","cited_by_count":17,"area":"rag"},{"id":"2504.05897","title":"HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference","created":"2025-04-08","cited_by_count":16,"area":"moe"},{"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":"2401.10910","title":"Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior","created":"2024-01-09","cited_by_count":15,"area":"agents"},{"id":"2503.05066","title":"Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts","created":"2025-03-07","cited_by_count":15,"area":"moe"},{"id":"2503.06433","title":"Seesaw: High-throughput LLM Inference via Model Re-sharding","created":"2025-03-09","cited_by_count":15,"area":"inference"},{"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":"2502.15618","title":"Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing","created":"2025-02-21","cited_by_count":14,"area":null},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2412.18934","title":"Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference","created":"2024-12-25","cited_by_count":13,"area":"inference"},{"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":"2510.10302","title":"SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference","created":"2025-10-11","cited_by_count":13,"area":"moe"},{"id":"2501.01990","title":"Towards Sustainable Large Language Model Serving","created":"2024-12-31","cited_by_count":12,"area":null},{"id":"2503.10905","title":"Learning to Inference Adaptively for Multimodal Large Language Models","created":"2025-03-13","cited_by_count":12,"area":"lr"},{"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":"2507.01438","title":"EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices","created":"2025-07-02","cited_by_count":11,"area":"inference"},{"id":"2505.17052","title":"SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs","created":"2025-05-16","cited_by_count":10,"area":"inference"},{"id":"2510.02758","title":"TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling","created":"2025-10-03","cited_by_count":10,"area":"inference"},{"id":"2506.16500","title":"SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2403.11621","title":"Let's Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model","created":"2024-03-18","cited_by_count":8,"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":"2509.23638","title":"LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers","created":"2025-09-28","cited_by_count":8,"area":"moe"},{"id":"2603.17435","title":"ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression","created":"2026-03-18","cited_by_count":8,"area":"inference"},{"id":"2402.09360","title":"HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference","created":"2024-02-14","cited_by_count":7,"area":"inference"},{"id":"2409.01366","title":"CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification","created":"2024-09-02","cited_by_count":7,"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":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2503.00392","title":"Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving","created":"2025-03-01","cited_by_count":7,"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":"2602.09316","title":"Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density","created":"2026-02-10","cited_by_count":7,"area":"moe"},{"id":"2606.06256","title":"RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention","created":"2026-06-04","cited_by_count":7,"area":"inference"},{"id":"2408.15518","title":"Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models","created":"2024-08-28","cited_by_count":6,"area":null},{"id":"2503.09716","title":"MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching","created":"2025-03-12","cited_by_count":6,"area":"moe"},{"id":"2504.07494","title":"Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving","created":"2025-04-10","cited_by_count":6,"area":"inference"},{"id":"2505.14884","title":"Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2507.01299","title":"La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation","created":"2025-07-02","cited_by_count":6,"area":null},{"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":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2509.24626","title":"SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2607.03333","title":"SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference","created":"2026-07-03","cited_by_count":6,"area":"agents"},{"id":"2406.01392","title":"Sparsity-Accelerated Training for Large Language Models","created":"2024-06-03","cited_by_count":5,"area":null},{"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":"2412.07174","title":"Post-Training Statistical Calibration for Higher Activation Sparsity","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2503.18869","title":"Reimagining Memory Access for LLM Inference: Compression-Aware Memory Controller Design","created":"2025-03-24","cited_by_count":5,"area":"inference"},{"id":"2504.16397","title":"Compass: SLO-aware Query Planner for Compound AI Serving at Scale","created":"2025-04-23","cited_by_count":5,"area":null},{"id":"2506.06644","title":"Spark Transformer: Reactivating Sparsity in FFN and Attention","created":"2025-06-07","cited_by_count":5,"area":null},{"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":"2602.18755","title":"DualScale: Energy-Efficient Disaggregated LLM Serving via Phase-Aware Placement and DVFS","created":"2026-02-21","cited_by_count":5,"area":"inference"},{"id":"2603.09983","title":"MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios","created":"2026-02-12","cited_by_count":5,"area":"moe"},{"id":"2406.06562","title":"Achieving Sparse Activation in Small Language Models","created":"2024-06-03","cited_by_count":4,"area":null}],"next_cursor":"100"}