{"total":196,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168,"area":null},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2510.09665","title":"LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference","created":"2025-10-08","cited_by_count":126,"area":"inference"},{"id":"2407.18003","title":"Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption","created":"2024-07-25","cited_by_count":97,"area":"inference"},{"id":"2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","created":"2025-10-03","cited_by_count":61,"area":"inference"},{"id":"2502.14051","title":"RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression","created":"2025-02-19","cited_by_count":41,"area":"inference"},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2409.15355","title":"Block-Attention for Efficient Prefilling","created":"2024-09-14","cited_by_count":37,"area":"rag"},{"id":"2601.16725","title":"LongCat-Flash-Thinking-2601 Technical Report","created":"2026-01-23","cited_by_count":34,"area":"lr"},{"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":"2408.08147","title":"P/D-Serve: Serving Disaggregated Large Language Model at Scale","created":"2024-08-15","cited_by_count":27,"area":"inference"},{"id":"2411.01783","title":"Context Parallelism for Scalable Million-Token Inference","created":"2024-11-04","cited_by_count":26,"area":null},{"id":"2508.01989","title":"Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving","created":"2025-08-04","cited_by_count":23,"area":"inference"},{"id":"2503.16525","title":"KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse","created":"2025-03-17","cited_by_count":22,"area":"inference"},{"id":"2505.07203","title":"PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications","created":"2025-05-12","cited_by_count":21,"area":"inference"},{"id":"2502.07776","title":"Auditing Prompt Caching in Language Model APIs","created":"2025-02-11","cited_by_count":20,"area":null},{"id":"2507.10150","title":"Past-Future Scheduler for LLM Serving under SLA Guarantees","created":"2025-07-14","cited_by_count":20,"area":"inference"},{"id":"2504.08784","title":"SLOs-Serve: Optimized Serving of Multi-SLO LLMs","created":"2025-04-05","cited_by_count":19,"area":null},{"id":"2506.17188","title":"Towards AI Search Paradigm","created":"2025-06-20","cited_by_count":19,"area":null},{"id":"2502.00937","title":"ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving","created":"2025-02-02","cited_by_count":18,"area":"mllm"},{"id":"2412.08890","title":"Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries","created":"2024-12-12","cited_by_count":17,"area":"inference"},{"id":"2507.08143","title":"Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores","created":"2025-07-10","cited_by_count":17,"area":"inference"},{"id":"2410.00428","title":"LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management","created":"2024-10-01","cited_by_count":16,"area":"inference"},{"id":"2501.05460","title":"Efficiently Serving Large Multimodal Models Using EPD Disaggregation","created":"2024-12-25","cited_by_count":16,"area":"mllm"},{"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":"2504.19867","title":"semi-PD: Towards Efficient LLM Serving via Phase-Wise Disaggregated Computation and Unified Storage","created":"2025-04-28","cited_by_count":16,"area":"inference"},{"id":"2510.17238","title":"StreamingThinker: Large Language Models Can Think While Reading","created":"2025-10-20","cited_by_count":15,"area":"lr"},{"id":"2503.08195","title":"Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation","created":"2025-03-11","cited_by_count":14,"area":"safety"},{"id":"2503.20552","title":"Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation","created":"2025-03-26","cited_by_count":14,"area":"inference"},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2604.26256","title":"DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training","created":"2026-04-29","cited_by_count":14,"area":null},{"id":"2409.17264","title":"No Request Left Behind: Tackling Heterogeneity in Long-Context LLM Inference with Medha","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2509.17863","title":"Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving","created":"2025-09-22","cited_by_count":13,"area":"moe"},{"id":"2512.03416","title":"TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity","created":"2025-12-03","cited_by_count":12,"area":"inference"},{"id":"2412.18169","title":"KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving","created":"2024-12-24","cited_by_count":11,"area":"inference"},{"id":"2604.15039","title":"Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter","created":"2026-04-16","cited_by_count":11,"area":"inference"},{"id":"2502.03589","title":"HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference","created":"2025-02-05","cited_by_count":10,"area":"inference"},{"id":"2504.03775","title":"FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling","created":"2025-04-03","cited_by_count":10,"area":"inference"},{"id":"2507.09019","title":"On Evaluating Performance of LLM Inference Serving Systems","created":"2025-07-11","cited_by_count":10,"area":"inference"},{"id":"2507.11953","title":"IAM: Efficient Inference through Attention Mapping between Different-scale LLMs","created":"2025-07-16","cited_by_count":10,"area":"inference"},{"id":"2601.06288","title":"AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving","created":"2026-01-09","cited_by_count":9,"area":"inference"},{"id":"2501.14743","title":"KVDirect: Distributed Disaggregated LLM Inference","created":"2024-12-13","cited_by_count":8,"area":"inference"},{"id":"2512.19206","title":"MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning","created":"2025-12-22","cited_by_count":8,"area":"lr"},{"id":"2603.28101","title":"Heddle: A Distributed Orchestration System for Agentic RL Rollout","created":"2026-03-30","cited_by_count":8,"area":"agents"},{"id":"2604.03143","title":"TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing","created":"2026-04-03","cited_by_count":8,"area":"inference"},{"id":"2409.12490","title":"CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs","created":"2024-09-19","cited_by_count":7,"area":null},{"id":"2502.12665","title":"A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization","created":"2025-02-18","cited_by_count":7,"area":"inference"},{"id":"2507.10069","title":"ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism","created":"2025-07-14","cited_by_count":7,"area":"mllm"},{"id":"2508.08192","title":"Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions","created":"2025-08-11","cited_by_count":7,"area":"inference"},{"id":"2410.12247","title":"EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference","created":"2024-10-16","cited_by_count":6,"area":"moe"},{"id":"2503.02154","title":"AugFL: Augmenting Federated Learning with Pretrained Models","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2504.09285","title":"DynaServe: Unified and Elastic Execution for Dynamic Disaggregated LLM Serving","created":"2025-04-12","cited_by_count":6,"area":"inference"},{"id":"2505.23022","title":"Scorpio: Serving Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference","created":"2025-05-29","cited_by_count":6,"area":"inference"},{"id":"2509.24832","title":"SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching","created":"2025-09-29","cited_by_count":6,"area":"inference"},{"id":"2505.11916","title":"Arrow: Adaptive Scheduling Mechanisms for Disaggregated LLM Inference Architecture","created":"2025-05-17","cited_by_count":5,"area":"inference"},{"id":"2508.19559","title":"Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference","created":"2025-08-27","cited_by_count":5,"area":null},{"id":"2509.16495","title":"Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloads","created":"2025-09-20","cited_by_count":5,"area":"inference"},{"id":"2511.00413","title":"Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse","created":"2025-11-01","cited_by_count":5,"area":"agents"},{"id":"2601.00397","title":"Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving","created":"2026-01-01","cited_by_count":5,"area":null},{"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":"2603.20218","title":"An experimental study of KV cache reuse strategies in chunk-level caching systems","created":"2026-03-03","cited_by_count":5,"area":"rag"},{"id":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"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":"2504.16786","title":"MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores","created":"2025-04-23","cited_by_count":4,"area":null},{"id":"2505.17694","title":"CoDec: Prefix-Shared Decoding Kernel for LLMs","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2602.12029","title":"PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving","created":"2026-02-12","cited_by_count":4,"area":"inference"},{"id":"2607.08032","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","created":"2026-07-09","cited_by_count":4,"area":"agents"},{"id":"2607.08057","title":"Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization","created":"2026-07-09","cited_by_count":4,"area":"inference"},{"id":"2607.25852","title":"AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding","created":"2026-07-28","cited_by_count":4,"area":"inference"},{"id":"2412.11814","title":"EventSum: A Large-Scale Event-Centric Summarization Dataset for Chinese Multi-News Documents","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2503.08461","title":"FastCache: Optimizing Multimodal LLM Serving through Lightweight KV-Cache Compression Framework","created":"2025-03-11","cited_by_count":3,"area":"inference"},{"id":"2504.09345","title":"MoE-Lens: Towards the Hardware Limit of High-Throughput MoE LLM Serving Under Resource Constraints","created":"2025-04-12","cited_by_count":3,"area":"moe"},{"id":"2504.10326","title":"AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference","created":"2025-04-14","cited_by_count":3,"area":"inference"},{"id":"2508.15919","title":"HFX: Joint Design of Algorithms and Systems for Multi-SLO Serving and Fast Scaling","created":"2025-08-21","cited_by_count":3,"area":"inference"},{"id":"2509.17542","title":"Disaggregated Prefill and Decoding Inference System for Large Language Model Serving on Multi-Vendor GPUs","created":"2025-09-22","cited_by_count":3,"area":"inference"},{"id":"2510.13223","title":"BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure","created":"2025-10-15","cited_by_count":3,"area":"inference"},{"id":"2602.06932","title":"When RL Meets Adaptive Speculative Training: A Unified Training-Serving System","created":"2026-02-06","cited_by_count":3,"area":"inference"},{"id":"2602.16603","title":"FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving","created":"2026-02-18","cited_by_count":3,"area":"inference"},{"id":"2604.24351","title":"Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion","created":"2026-04-27","cited_by_count":3,"area":"diffusion"},{"id":"2605.01708","title":"SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving","created":"2026-05-03","cited_by_count":3,"area":"inference"},{"id":"2605.09329","title":"Test-Time Speculation","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2605.24022","title":"Adaptive KV Cache Reuse for Fast Long-Context LLM Serving","created":"2026-05-20","cited_by_count":3,"area":"inference"},{"id":"2606.12688","title":"M*: A Modular, Extensible, Serving System for Multimodal Models","created":"2026-06-10","cited_by_count":3,"area":"wm"},{"id":"2607.00466","title":"ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving","created":"2026-07-01","cited_by_count":3,"area":"moe"},{"id":"2411.00915","title":"Empower Vision Applications with LoRA LMM","created":"2024-11-01","cited_by_count":2,"area":"mllm"},{"id":"2502.06846","title":"Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2502.15763","title":"Hybrid Offline-online Scheduling Method for Large Language Model Inference Optimization","created":"2025-02-14","cited_by_count":2,"area":null},{"id":"2503.17707","title":"PipeBoost: Resilient Pipelined Architecture for Fast Serverless LLM Scaling","created":"2025-03-22","cited_by_count":2,"area":"inference"},{"id":"2505.11820","title":"Chain-of-Model Learning for Language Model","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2510.17015","title":"Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering","created":"2025-10-19","cited_by_count":2,"area":"agents"},{"id":"2604.09613","title":"Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference","created":"2026-03-13","cited_by_count":2,"area":"inference"},{"id":"2605.02960","title":"MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving","created":"2026-05-03","cited_by_count":2,"area":"moe"},{"id":"2605.04357","title":"Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs","created":"2026-05-05","cited_by_count":2,"area":"inference"},{"id":"2606.00288","title":"Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2606.09061","title":"Fairness-Aware and Latency-Controllable Scheduling for Chunked-Prefill LLM Serving","created":"2026-06-08","cited_by_count":2,"area":"inference"},{"id":"2606.13126","title":"MiniPIC: Flexible Position-Independent Caching in <100LOC","created":"2026-06-11","cited_by_count":2,"area":"rag"},{"id":"2606.28565","title":"KernelSight-LM: A Kernel-Level LLM Inference Simulator","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2607.02043","title":"Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving","created":"2026-07-02","cited_by_count":2,"area":"inference"},{"id":"2608.19758","title":"FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving","created":"2026-08-20","cited_by_count":2,"area":"inference"}],"next_cursor":"100"}