NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
94 results for “keyword:"llm serving"” in ICLR 2027. 13 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VestigeKV: Query-Independent Sparse Attention with Certified Recall for NoPE-MLA Caches▼1611.50
[PDF]Same Conversation, Different Tokens: Characterizing and Mitigating Token Drift for Efficient Multi-Turn LLM Serving▼4.5k2.67
[PDF]DStreamer: Acceptance-Aligned Diffusion Streaming for High-Throughput Serving and Online RLVR▲3972.67
[PDF]HEPH: 3-Bit Grid-Aligned Trellis Quantization of MXFP4 Mixture-of-Experts for Accurate, Hadamard-Free Serving▲20k2.67
[PDF]Know Before You Route: Dual-Signal Expert Prefetching with Conformal Coverage Guarantees for Sparse MoE LLMs▲3972.67
[PDF]Progressive Conformal Prediction for Remaining-Length Estimation in Large Language Models▼1361.33
[PDF]KVReclaim: Recompute-Aware Placement and Migration-Free Reclamation for KV Caches on ZNS SSDs▼5.8k2.33
[PDF]RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation▼11k2.33
[PDF]Where to Speculate: Cross-Request Survival-Value Allocation for Batched Speculative Decoding▼1.2k1.67
[PDF]Resource Isolation Is Not Performance Isolation: Virtual Freeness for Disaggregated LLM Serving▼12k1.67
[PDF]AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines▼4.5k2.67
[PDF]Imbalance-aware NUMA Memory Placement: A Simple Approach To Mixture-of-Experts Serving on Tightly Coupled Architectures▼5.8k2.33
[PDF]LMSysDojo: Building Scalable Analytical Agents for Optimizing Complex LLM Serving Systems▲1.7k3.33
[PDF]Every Second Counts: Quality-Cost-Aware LLM Routing for Low-Latency Concurrent Multi-LLM Serving▼1.2k1.67