{"total":82,"rows":[{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141,"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":"2312.03003","title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","created":"2023-12-04","cited_by_count":58,"area":null},{"id":"2410.15332","title":"EPIC: Efficient Position-Independent Caching for Serving Large Language Models","created":"2024-10-20","cited_by_count":47,"area":null},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46,"area":null},{"id":"2503.08311","title":"Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference","created":"2025-03-11","cited_by_count":33,"area":null},{"id":"2407.00326","title":"Teola: Towards End-to-End Optimization of LLM-based Applications","created":"2024-06-29","cited_by_count":32,"area":null},{"id":"2412.03594","title":"BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching","created":"2024-11-29","cited_by_count":32,"area":null},{"id":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31,"area":null},{"id":"2412.04036","title":"SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions","created":"2024-12-05","cited_by_count":25,"area":null},{"id":"2312.14950","title":"TypeFly: Flying Drones with Large Language Model","created":"2023-12-08","cited_by_count":23,"area":null},{"id":"2403.05821","title":"Optimizing LLM Queries in Relational Data Analytics Workloads","created":"2024-03-09","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2502.07776","title":"Auditing Prompt Caching in Language Model APIs","created":"2025-02-11","cited_by_count":20,"area":null},{"id":"2510.03346","title":"KVComm: Enabling Efficient LLM Communication through Selective KV Sharing","created":"2025-10-02","cited_by_count":18,"area":null},{"id":"2402.14808","title":"RelayAttention for Efficient Large Language Model Serving with Long System Prompts","created":"2024-02-22","cited_by_count":13,"area":null},{"id":"2403.12900","title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2506.08607","title":"Sample Efficient Demonstration Selection for In-Context Learning","created":"2025-06-10","cited_by_count":13,"area":null},{"id":"2410.05265","title":"PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2505.01658","title":"A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency","created":"2025-05-03","cited_by_count":12,"area":null},{"id":"2604.13226","title":"KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs","created":"2026-04-14","cited_by_count":10,"area":null},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2402.15943","title":"Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware","created":"2024-02-25","cited_by_count":6,"area":null},{"id":"2404.10552","title":"Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning","created":"2024-04-16","cited_by_count":6,"area":null},{"id":"2602.01519","title":"You Need an Encoder for Native Position-Independent Caching","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2606.17107","title":"Models Take Notes at Prefill: KV Cache Can Be Editable and Composable","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2404.03353","title":"Towards Pareto Optimal Throughput in Small Language Model Serving","created":"2024-04-04","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2510.10138","title":"Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2510.18546","title":"EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2606.07684","title":"Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching","created":"2026-06-05","cited_by_count":5,"area":null},{"id":"2601.23088","title":"From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2508.05012","title":"Making Prompts First-Class Citizens for Adaptive LLM Pipelines","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2511.17565","title":"Generative Caching for Structurally Similar Prompts and Responses","created":"2025-11-14","cited_by_count":3,"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":"2506.15138","title":"Less Is More: Reducing Token Counts Without Compromising Performance","created":"2025-06-18","cited_by_count":2,"area":null},{"id":"2510.25979","title":"AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2512.21925","title":"Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2601.01712","title":"RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2606.28565","title":"KernelSight-LM: A Kernel-Level LLM Inference Simulator","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.23806","title":"A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2607.26694","title":"Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2409.19134","title":"Confidential Prompting: Privacy-preserving LLM Inference on Cloud","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2411.08932","title":"PyGen: A Collaborative Human-AI Approach to Python Package Creation","created":"2024-11-13","cited_by_count":1,"area":null},{"id":"2510.07105","title":"Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.20653","title":"Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.01188","title":"ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2511.02647","title":"Federated Attention: A Distributed Paradigm for Collaborative LLM Inference over Edge Networks","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.06010","title":"MoSKA: Mixture of Shared KV Attention for Efficient Long-Sequence LLM Inference","created":"2025-11-08","cited_by_count":1,"area":null},{"id":"2601.00847","title":"You Only Need Your Transformer 25% of the Time: Meaning-First Execution for Eliminating Unnecessary Inference","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2603.12344","title":"Can Decision Trees Teach Large Language Models? Distilling Verbalized Knowledge for Molecular Property Prediction","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.05438","title":"Residual-Mass Accounting for Partial-KV Decoding","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.30613","title":"CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.28263","title":"CoMem: Reusing Transformer Depth across Queries with Persistent Intermediate Residuals","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.19047","title":"Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2609.37725","title":"Context Language Models","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2609.39358","title":"Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2505.10640","title":"The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2505.14992","title":"Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2509.12592","title":"Match Chat: Real Time Generative AI and Generative Computing for Tennis","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2510.08774","title":"Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2511.00101","title":"Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2512.07090","title":"Leveraging KV Similarity for Online Structured Pruning in LLMs","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.23049","title":"Accelerating Language Model Workflows with Prompt Choreography","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2602.22812","title":"Accelerating Local LLMs on Resource-Constrained Edge Devices via Distributed Prompt Caching","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.14159","title":"HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2605.07325","title":"CSR: Infinite-Horizon Real-Time Policies with Massive Cached State Representations","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.00946","title":"Lodestar: An Online-Learning LLM Inference Router","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.29565","title":"Speculative Pre-Positioning: Decoding Stateful Sessions to the Next Decision Point Off the Critical Path","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.28268","title":"LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.22237","title":"Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.26140","title":"Affix Cache for Diffusion Large Language Models","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2609.04288","title":"Scalable Context Orchestration for Serving LLMs Over Voice","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.18935","title":"Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.33477","title":"Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35263","title":"WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39394","title":"Can Computation from Earlier Problems Help LLMs Solve New Ones?","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39938","title":"LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02233","title":"Budgeted Cache Repair for Cross-Context KV-Cache Reuse","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.02839","title":"To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.10845","title":"Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12133","title":"Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}