GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/hideinsewer/GateSight
Sources
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
- R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
- A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression
- Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
- Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
- Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
- Kimi Linear: An Expressive, Efficient Attention Architecture
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- SCBench: A KV Cache-Centric Analysis of Long-Context Methods
- SnapKV: LLM Knows What You are Looking for Before Generation
- Jamba: A Hybrid Transformer-Mamba Language Model
- Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
- TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems