{"total":30,"rows":[{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"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":"2408.12320","title":"TensorOpera Router: A Multi-Model Router for Efficient LLM Inference","created":"2024-08-22","cited_by_count":60,"area":"inference"},{"id":"2603.04445","title":"Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey","created":"2026-02-23","cited_by_count":19,"area":"inference"},{"id":"2509.02718","title":"Efficient Training-Free Online Routing for High-Volume Multi-LLM Serving","created":"2025-09-02","cited_by_count":13,"area":"inference"},{"id":"2501.14808","title":"HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location","created":"2025-01-15","cited_by_count":10,"area":"inference"},{"id":"2605.13734","title":"KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving","created":"2026-05-13","cited_by_count":7,"area":"inference"},{"id":"2501.09367","title":"PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge Networks","created":"2025-01-16","cited_by_count":6,"area":"inference"},{"id":"2602.10729","title":"BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization","created":"2026-02-11","cited_by_count":6,"area":"inference"},{"id":"2609.00891","title":"CacheBridge: Efficient Cross-Model KV Cache Transfer","created":"2026-09-01","cited_by_count":6,"area":"inference"},{"id":"2408.08470","title":"Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models","created":"2024-08-16","cited_by_count":5,"area":"inference"},{"id":"2410.14257","title":"Revisiting Service Level Objectives and System Level Metrics in Large Language Model Serving","created":"2024-10-18","cited_by_count":5,"area":"inference"},{"id":"2604.05417","title":"Multi-Drafter Speculative Decoding with Alignment Feedback","created":"2026-04-07","cited_by_count":4,"area":"inference"},{"id":"2607.28979","title":"KV Cache Translation across Heterogeneous Large Language Models","created":"2026-07-31","cited_by_count":4,"area":"inference"},{"id":"2505.07680","title":"SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models","created":"2025-05-12","cited_by_count":2,"area":"inference"},{"id":"2508.03611","title":"Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling","created":"2025-08-05","cited_by_count":2,"area":"inference"},{"id":"2603.12646","title":"98$\\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router","created":"2026-03-13","cited_by_count":2,"area":"inference"},{"id":"2605.24793","title":"Beyond the Target: From Imitation to Collaboration in Speculative Decoding","created":"2026-05-24","cited_by_count":2,"area":"inference"},{"id":"2607.23815","title":"Kalypso: Relational LLM Serving","created":"2026-07-26","cited_by_count":2,"area":"inference"},{"id":"2603.23525","title":"Prompt Compression in Production Task Orchestration: A Pre-Registered Randomized Trial","created":"2026-03-06","cited_by_count":1,"area":"inference"},{"id":"2606.17949","title":"RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM Serving","created":"2026-06-16","cited_by_count":1,"area":"inference"},{"id":"2607.15516","title":"Cache-Aware Prompt Compression:A Two-Tier Cost Model for LLM API Caching","created":"2026-07-17","cited_by_count":1,"area":"inference"},{"id":"2609.07786","title":"Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference","created":"2026-09-07","cited_by_count":1,"area":"inference"},{"id":"2606.27457","title":"Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving","created":"2026-06-25","cited_by_count":0,"area":"inference"},{"id":"2609.06940","title":"Unified AI Gateway: A Framework for Joint Model Routing and KV Cache Management","created":"2026-09-07","cited_by_count":0,"area":"inference"},{"id":"2609.08306","title":"HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2610.11358","title":"RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation","created":"2026-10-08","cited_by_count":0,"area":"inference"},{"id":"2610.12242","title":"TokenRouter: Efficient Serving System for Token-Level LLM Routing","created":"2026-10-08","cited_by_count":0,"area":"inference"},{"id":"2610.14688","title":"Accelerating Cross-Model LLM Inference via Attention Map Reuse","created":"2026-10-10","cited_by_count":0,"area":"inference"},{"id":"2610.15509","title":"CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff","created":"2026-10-11","cited_by_count":0,"area":"inference"}],"next_cursor":null}