kv cache

DroidSpeak: KV Cache Sharing Across Fine-tuned Model Variants NSDI 2026 EQUIP: EQUivariant preserving In-Place updates for Efficient Token Pruning ACL 2026 HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding ACL 2026 HitKV: Activation Frequency Knows Which Tokens Are Important AAAI 2026 Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout CVPR 2026 KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache AAAI 2026 KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference EACL 2026 Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving AAAI 2026 MHA2MLA-VLM: Enabling DeepSeek’s Economical Multi-Head Latent Attention Across Vision-Language Models AAAI 2026 OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs AAAI 2026 PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference EACL 2026 River-LLM: Large Language Model Seamless Exit Based on KV Share ACL 2026 Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys AAAI 2026 SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning AAAI 2026 SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning AAAI 2026 SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving ACL 2026 StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression AAAI 2026 SubGCache: Accelerating Graph-based RAG with Subgraph-level KV Cache AAAI 2026 SYMPHONY: Enabling Compute-Memory Disaggregation in LLM Serving Systems NSDI 2026 Thesis Proposal: Efficient KV Cache Reuse for Multi-Document Retrieval-Augmented Generation EACL 2026 Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models EACL 2026 D_2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models ICLR 2025 A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization ACL 2025 Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA EMNLP 2025 A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts ICLR 2025