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
180 results for “keyword:"llm inference"” in ICLR 2027. 24 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration▼5.1k2.60
[PDF]PiCoKV: Dequantization-Free KV Cache Quantization via Binary Principal-Component Coding▼1.2k3.00
[PDF]Quantize, Evict, or Both? When Mixed KV-Cache Allocation Pays, and Why its Distortion Proxy Misleads▼5.8k2.33
[PDF]Speculating on the Past: Lossless Reuse of Stale KV Caches via Self-Speculative Verification▼4.3k2.00
[PDF]Think Global, Act Local: Efficient KV Cache Quantization via Global Prefill Calibration of Early Decoding▲3952.67
[PDF]ICM-bench: A Benchmark for Evaluating the In-context Modification Ability of Large Language Models▼4.3k2.00
Withdrawn or desk rejected (24)
[PDF]DyS-MoE: Virtualizing Dynamic Expert Execution with Static Windows for Resource-Constrained MoE InferenceWithdrawn2.00
[PDF]SpecRelay: Amortize or Avoid the Round Trip in Edge–Cloud Speculative DecodingDesk rejected2.00
[PDF]Easy-Kuant: Diagnosing and Mitigating KV-Cache Quantization Collapse with Selective Layer ProtectionDesk rejected