{"total":34,"rows":[{"id":"2602.21548","title":"DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference","created":"2026-02-25","cited_by_count":15,"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":"2607.07847","title":"When Does Continual Learning Require Learning","created":"2026-07-08","cited_by_count":7,"area":"inference"},{"id":"2602.22593","title":"FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving","created":"2026-02-26","cited_by_count":6,"area":"inference"},{"id":"2605.19660","title":"OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond","created":"2026-05-19","cited_by_count":5,"area":"inference"},{"id":"2602.02108","title":"Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts","created":"2026-02-02","cited_by_count":4,"area":"inference"},{"id":"2606.09659","title":"End-to-End Context Compression at Scale","created":"2026-06-08","cited_by_count":4,"area":"inference"},{"id":"2602.12151","title":"OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration","created":"2026-02-12","cited_by_count":3,"area":"inference"},{"id":"2511.03092","title":"SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators","created":"2025-11-05","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":"2605.29727","title":"Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting","created":"2026-05-28","cited_by_count":2,"area":"inference"},{"id":"2608.04074","title":"Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms","created":"2026-08-04","cited_by_count":2,"area":"inference"},{"id":"2608.28444","title":"Sliding-window beats linear attention","created":"2026-08-28","cited_by_count":2,"area":"inference"},{"id":"2609.35621","title":"Cartridges++: KV Cache Compression without Off-Context Derailment","created":"2026-09-28","cited_by_count":2,"area":"inference"},{"id":"2603.23701","title":"The Diminishing Returns of Early-Exit Decoding in Modern LLMs","created":"2026-03-24","cited_by_count":1,"area":"inference"},{"id":"2609.26368","title":"HySparse2: Hybrid Sparse Attention with Two-Level KV Sharing","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2509.03377","title":"TRACE: Unlocking Effective CXL Bandwidth via Lossless Compression and Precision Scaling","created":"2025-09-03","cited_by_count":0,"area":"inference"},{"id":"2511.15950","title":"A Scalable NorthPole System with End-to-End Vertical Integration for Low-Latency and Energy-Efficient LLM Inference","created":"2025-11-20","cited_by_count":0,"area":"inference"},{"id":"2511.22481","title":"OmniInfer: System-Wide Acceleration Techniques for Optimizing LLM Serving Throughput and Latency","created":"2025-11-27","cited_by_count":0,"area":"inference"},{"id":"2604.05012","title":"Comparative Characterization of KV Cache Management Strategies for LLM Inference","created":"2026-04-06","cited_by_count":0,"area":"inference"},{"id":"2604.05942","title":"BOSCH: Black-Box Binary Optimization for Short-Context Attention-Head Selection in LLMs","created":"2026-04-07","cited_by_count":0,"area":"inference"},{"id":"2605.10453","title":"SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding","created":"2026-05-11","cited_by_count":0,"area":"inference"},{"id":"2605.15051","title":"An Interpretable Latency Model for Speculative Decoding in LLM Serving","created":"2026-05-14","cited_by_count":0,"area":"inference"},{"id":"2606.01336","title":"LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning","created":"2026-05-31","cited_by_count":0,"area":"inference"},{"id":"2606.03770","title":"E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments","created":"2026-06-02","cited_by_count":0,"area":"inference"},{"id":"2606.14779","title":"Unified KV Pooling to Accelerate Long-Context LLM Serving","created":"2026-06-10","cited_by_count":0,"area":"inference"},{"id":"2607.21985","title":"Unified Static-Dynamic Pruning for Efficient LLM Inference","created":"2026-07-24","cited_by_count":0,"area":"inference"},{"id":"2608.07855","title":"CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents","created":"2026-08-08","cited_by_count":0,"area":"inference"},{"id":"2608.21541","title":"Beyond Sparse Weights: When Is Attention Compressible?","created":"2026-08-21","cited_by_count":0,"area":"inference"},{"id":"2609.10812","title":"ExaServe: Large-Scale LLM Serving on Exascale HPC Systems","created":"2026-09-09","cited_by_count":0,"area":"inference"},{"id":"2609.23314","title":"ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.26763","title":"SARA: SLO-Aware Resource Allocation for Disaggregated Agentic LLM Services","created":"2026-09-22","cited_by_count":0,"area":"inference"},{"id":"2609.33410","title":"FoldAttention: Declared-Reference Softmax for Fast Decode and Deterministic Backward","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2610.13060","title":"KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse","created":"2026-10-09","cited_by_count":0,"area":"inference"}],"next_cursor":null}