The Gating Mechanism of KV Cache Eviction
cs.CL
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Titans: Learning to Memorize at Test Time
- R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression
- Native Hybrid Attention for Efficient Sequence Modeling
- What is Wrong with Perplexity for Long-context Language Modeling?
- Sliding Window Attention Training for Efficient Large Language Models
- Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory
- CentroidKV: Efficient Long-Context LLM Inference via KV Cache Clustering
- Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
- Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices
- KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
- Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
- SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
- Let's Verify Step by Step
- MoBA: Mixture of Block Attention for Long-Context LLMs
- TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
- Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
- Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data