key-value cache

CacheNotes: Task-Aware Key-Value Cache Compression for Reasoning-Intensive Knowledge Tasks EACL 2026 Dynamic Token Reweighting for Robust Vision-Language Models CVPR 2026 Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention ACL 2026 FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers CVPR 2026 Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech ACL 2026 HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference ACL 2026 Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction AAAI 2026 KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing CVPR 2026 LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning ACL 2026 Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving AAAI 2026 Lizard: An Efficient Linearization Framework for Large Language Models ACL 2026 LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026 No Buffer, No Bottleneck: Efficient Zero-Copy KV Cache Offloading for Long-Context LLMs OSDI 2026 Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models ACL 2026 Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models CVPR 2026 Progressive Supernet Training for Efficient Visual Autoregressive Modeling CVPR 2026 Q Cache: Visual Attention Is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model AAAI 2026 Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression ACL 2026 RetroLM: Retrieval-Augmented KVs for Long-Context Processing AAAI 2026 Scaling the Long Video Understanding of Multimodal Large Language Models via Visual Memory Mechanism CVPR 2026 Simple Is Better: Multiplication May Be All You Need for LLM Request Scheduling OSDI 2026 Sparse Attention Across Multiple-Context KV Cache AAAI 2026 STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction CVPR 2026 Strata: Hierarchical Context Caching for Long Context Language Model Serving OSDI 2026 TimeBill: Time-Budgeted Inference for Large Language Models AAAI 2026