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
464 results for “keyword:"cache"” in ICLR 2027. 94 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving▼5.8k2.33
[PDF]The Context of Theseus: Learning Selective Discrete Recurrence in Autoregressive Transformers▲6.1k2.00
[PDF]HoltSeer: Stable Feature Forecasting under Sparse Anchors for Accelerated Diffusion Sampling▲3952.67
[PDF]Where Does Layer-Skip Fragility Live? A Matched-Harness Decomposition of Training-Free Adaptive Layer Skipping▲11.00
[PDF]Persistent-Cache Complexity: A Finite-State And Communication-Theoretic View of Causal Decoders▲3952.67
[PDF]GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs▼4.3k2.00
[PDF]Compressing KV-Cache Communication in Multi-Agent Systems with Collective Compensation▼1.2k1.67
[PDF]From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Accelerating Long-Context LLMs▼1.2k1.67
[PDF]Measuring, Predicting, and Diagnosing Compression-Induced Failures in Vision-Language Models▲3.0k2.33
[PDF]Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion▲3952.67
[PDF]When the Window Cannot See the Question: Token-Denominated Observation Windows Are Not Language-Neutral▼4.3k2.00
[PDF]BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration▲3952.67
[PDF]Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving▼4.5k2.67
Withdrawn or desk rejected (94)
[PDF]Certified Best-First Sparse Attention: Provable Early Termination via Admissible Block BoundsWithdrawn2.00
[PDF]Cross-Model KV Cache Construction in LLM Familiies: Residual-Stream Mapping Without Matched Head GeometryDesk rejected
[PDF]Trace Forcing: Anchor Tokens in the KV Cache for Training-Free Long Video GenerationWithdrawn2.00