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
85 results for “keyword:"long context inference"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Never Evict Always Taper: A Static Logarithmic Bit-Width Schedule for KV Cache Quantization▲11.00
[PDF]Compression-Aware Fine-Tuning: Adapting Language Model Weights to a Frozen Cache Bottleneck▼4.3k2.00
[PDF]Quantize the Keys, Audit the Values: Retained-State Certificates for KV-Cache Compression▲3952.67
[PDF]RECAP-KV: Single-Prefill Approximation of Reconstruction Importance for Reusable KV Cache Eviction▲5.4k3.00
[PDF]Beyond Token Pruning: Prompt Compression via Minimum Description Length and Semantic Message Anchors▼1.3k1.75
[PDF]REPRISE: Efficient Long-Context Diffusion Inference via Distillation through Reused KV Caches▲5.4k3.00
[PDF]GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs▼4.3k2.00
[PDF]Where Does Attention Mass Live? A Matched-Budget Study of Query-Adaptive Attention Sparsification for Decoder LMs▼1361.33
[PDF]RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache▼1.2k3.00
[PDF]Byte Economics: Million-Token Inference of a 2.8-Trillion-Parameter MoE on a Consumer Desktop▼12k1.67
[PDF]StrideKV: Accelerating Batched Long-Context Decoding via Periodic Reuse of Retrieved KV Cache▲6.1k2.00
[PDF]Think Global, Act Local: Efficient KV Cache Quantization via Global Prefill Calibration of Early Decoding▲3952.67
Withdrawn or desk rejected (7)
[PDF]Certified Best-First Sparse Attention: Provable Early Termination via Admissible Block BoundsWithdrawn2.00
[PDF]When Is More Context Worth It? Risk-Controlled Expansion for Compressed-Context InferenceWithdrawn1.67