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428 results for “keyword:"kv cache"” in ICLR 2027. 76 withdrawn or desk rejected listed apart.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]Visual Tokens Should Not Be Pruned Forever: Budgeted Visual Token Refresh for Multi-Turn LVLMs▼1361.33
[PDF]Ranking Is Not Support Selection: Exact Marginals and Certified Headroom for Sparse Attention in LLMs▼1.2k1.67
[PDF]SearchTrimmer: Search-Selective KV Eviction and Loop Gating for Efficient Deep Research Agents▲3952.67
[PDF]To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse▲3.0k2.33
[PDF]Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression▲4.6k3.00
[PDF]ARI: Adaptive Rule-Interpolated KV Cache Migration Scheduling for Multi-GPU LLM Serving▼5.8k2.33
[PDF]Demystifying Cache-to-Cache Communication: When Latent Transfer Reduces to Output Calibration▼5.8k2.33
[PDF]What Rank Calibration Actually Measures: The Sparse, Repeatable, Query-Specific Response of Video LLMs to KV-Cache Compression▼4.5k2.67
[PDF]The Compression Square: Weight Quantization and KV-Cache Eviction Do Not Compose at the Operating Point▲143.33
[PDF]Ask the Masked Block: Predicting Denoised-State Relevance for KV Cache Eviction in Diffusion Language Models▼5.8k2.33
[PDF]MaskAhead: Unifying KV Cache Selection and Eviction in Block Diffusion Language Models▼1.2k1.67
[PDF]EXACT WARM-STATE REUSE FOR HYBRID DIFFUSION LANGUAGE MODELS: CONTRACTS, SPEEDUPS, AND FAILURE BOUNDARIES▲3.0k2.33
[PDF]TapKV: Accelerating Long-Horizon Speculative Decoding with Target-Aware Draft KV Caches Optimization▲3952.67
[PDF]Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression▼1361.33
Withdrawn or desk rejected (76)
[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
[PDF]EviStream: Evidence-Aligned Audio-Visual Decisions over Partially Observable Video StreamsWithdrawn2.00