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
428 results for “keyword:"kv cache"” in ICLR 2027. 76 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LAB-Sparse: Local Accumulative Boost for Adaptive Semantic-Block Retention in KV Cache▼4.3k2.00
[PDF]Bridges over Heavy Hitters: A Causal-HITS Theory and Counterfactual Benchmark for Attention-Graph KV-Cache Compression▲432.75
[PDF]Many Caches, Same Reasoning: Rethinking Importance Selection for Reasoning-Time KV Compression▼1.2k1.67
[PDF]Coarse KV Residency: Decoupling KV Reachability from GPU Memory in Long-Context RL Rollouts▲3952.67
[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]When to Wait Before Fan-Out: Warm-Up, Verification, and Residency in Cache-Aware LLM Evaluation▲9.2k2.67
[PDF]Entropy Forcing: Entropy-Routed Subset Selection for KV Cache in Streaming Video Generation▼5.8k2.33
[PDF]KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization▲5103.00
[PDF]OPQAD: Recovering Capability under KV-Cache Quantization via On-Policy Quantization-Aware Distillation▲5103.00
[PDF]PACER: Training-Free Phase-Scheduled Memory for Long-Horizon Vision-Language-Action Manipulation▼1361.33
Withdrawn or desk rejected (76)
[PDF]CACHECOHERENT: FREQUENCY-ALIGNED DOCUMENT ORDERING FOR PREFIX-CACHE-EFFICIENT MULTI-TENANT RAG SERVINGWithdrawn2.33
[PDF]StreamPrune: Causal and Query-Free Token Pruning for Accelerating Streaming Video MLLMsWithdrawn1.67