EchoKV: Self-Corrective KV Cache Eviction via Iterative Query Feedback
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- Longformer: The Long-Document Transformer
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Extending Context Window of Large Language Models via Positional Interpolation
- Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
- MemGPT: Towards LLMs as Operating Systems
- Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents