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
145 results for “keyword:"v cache compression"” in ICLR 2027. 22 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Bridges over Heavy Hitters: A Causal-HITS Theory and Counterfactual Benchmark for Attention-Graph KV-Cache Compression▲502.75
[PDF]Lifetime: KV Cache Eviction from Attention Trajectories for Long-Context Language Models▼4.3k2.00
[PDF]KV Compression Cannot Double as a Jailbreak Defense: The Harmfulness-then-Refusal Trajectory Guides Token Deletion▼5.8k2.33
[PDF]VestigeKV: Query-Independent Sparse Attention with Certified Recall for NoPE-MLA Caches▼1601.50
[PDF]Deconfounding and Compressing History Memory in Streaming Vision-Language-Action Policies▼1.2k1.67
[PDF]Do We Need Learned Compressors? Adapting LLMs to Parameter-Free KV-Cache Compression for Long-Context Reasoning▼1.2k1.67
[PDF]IDEAL-KV: Inference-Aligned Codebook Learning and Calibrated Stage Allocation for KV-Cache Compression▲5.4k3.00
[PDF]Attention under Bounded Key–Query Similarity: Space Complexity and Transformer Anisotropy▲4012.67
[PDF]SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation▲5.7k2.00
[PDF]Keys Decide Attention, Values Decide Contribution: Value-Gated KV Cache Eviction at 20× Compression▼1351.33
Withdrawn or desk rejected (22)
[PDF]GeoKV: Geometry-Aware KV Cache Compression via Global Structural Contribution and Key RectificationWithdrawn1.67
[PDF]PureKV: Plug-and-Play KV Cache Optimization with Spatial-Temporal Sparse Attention for Vision-Language Large ModelsDesk rejected
[PDF]Kronecker Product Attention: Memory-Efficient KV Compression via Structured FactorizationWithdrawn2.00