{"total":33,"rows":[{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2604.12989","title":"Accelerating Speculative Decoding with Block Diffusion Draft Trees","created":"2026-04-14","cited_by_count":29,"area":"inference"},{"id":"2510.18586","title":"TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications","created":"2025-10-21","cited_by_count":16,"area":"inference"},{"id":"2601.11580","title":"Speculative Decoding: Performance or Illusion?","created":"2025-12-31","cited_by_count":15,"area":"inference"},{"id":"2604.19572","title":"A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression","created":"2026-04-21","cited_by_count":15,"area":"inference"},{"id":"2605.29343","title":"Draft-OPD: On-Policy Distillation for Speculative Draft Models","created":"2026-05-28","cited_by_count":11,"area":"inference"},{"id":"2606.16824","title":"CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents","created":"2026-06-15","cited_by_count":10,"area":"inference"},{"id":"2602.08005","title":"ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference","created":"2026-02-08","cited_by_count":9,"area":"inference"},{"id":"2607.07847","title":"When Does Continual Learning Require Learning","created":"2026-07-08","cited_by_count":7,"area":"inference"},{"id":"2504.14992","title":"Efficient Pretraining Length Scaling","created":"2025-04-21","cited_by_count":6,"area":"inference"},{"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":"2511.16193","title":"Fast LLM Post-training via Decoupled and Fastest-of-N Speculation","created":"2025-11-20","cited_by_count":4,"area":"inference"},{"id":"2603.22910","title":"EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction","created":"2026-03-24","cited_by_count":4,"area":"inference"},{"id":"2603.16514","title":"FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation Mechanism","created":"2026-03-17","cited_by_count":3,"area":"inference"},{"id":"2604.22312","title":"Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation","created":"2026-04-24","cited_by_count":3,"area":"inference"},{"id":"2602.01274","title":"PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length","created":"2026-02-01","cited_by_count":2,"area":"inference"},{"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":"2606.31315","title":"BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding","created":"2026-06-30","cited_by_count":2,"area":"inference"},{"id":"2603.10353","title":"S-HPLB: Efficient LLM Attention Serving via Sparsity-Aware Head Parallelism Load Balance","created":"2026-03-11","cited_by_count":1,"area":"inference"},{"id":"2604.18170","title":"Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing","created":"2026-04-20","cited_by_count":1,"area":"inference"},{"id":"2608.30295","title":"CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration","created":"2026-08-31","cited_by_count":1,"area":"inference"},{"id":"2609.18675","title":"HBFlex: A Flexible Memory System for Bridging Fine-Grained LLM States and Coarse-Grained HBF Parallel Execution","created":"2026-09-16","cited_by_count":1,"area":"inference"},{"id":"2609.26300","title":"CompKV: Compensation-Aware KV Selection for Long-Context LLM Inference","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2606.03739","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","created":"2026-06-02","cited_by_count":0,"area":"inference"},{"id":"2607.26633","title":"NELSSA: A GPU-PNM Heterogeneous System for Mixed-Length LLM Serving via Length-based Request Placement","created":"2026-07-29","cited_by_count":0,"area":"inference"},{"id":"2608.03839","title":"Oilbird: Training-Free Speculative Decoding with Keys the Verifier Already Computes","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2609.16491","title":"PipeSwift: Revisiting Pipeline Parallelism for Large-Scale Completion-Oriented Agentic LLM Serving","created":"2026-09-15","cited_by_count":0,"area":"inference"},{"id":"2609.17475","title":"JustFit: Just-in-Time State Management for Local LLM Serving","created":"2026-09-15","cited_by_count":0,"area":"inference"},{"id":"2609.23900","title":"LumoTree: Path-Parallel Speculative Verification for Hybrid Language Models","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.27746","title":"The KV Cache Working Set: Online Capacity Planning for LLM Inference Systems","created":"2026-09-23","cited_by_count":0,"area":"inference"},{"id":"2609.34380","title":"DPS: Dual-Mode Precision LLM Serving with Semi-Unified Memory","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.39972","title":"UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding","created":"2026-09-30","cited_by_count":0,"area":"inference"},{"id":"2610.20392","title":"FOLD: Position-Free Far Memory with Local Order for Long-Context Speculative Decoding","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}