Error Certificates for KV-Cache Eviction via Randomized Design
cs.LG, cs.AI, cs.CL
Submitted: 2026-07-23
Updated: 2026-08-29
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
- PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
- Value-Aware Stochastic KV Cache Eviction for Reasoning Models
- MagicPIG: LSH Sampling for Efficient LLM Generation
- vAttention: Verified Sparse Attention
- Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
- Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
- CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction
- The Llama 3 Herd of Models
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- Mistral 7B
- MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference
- SnapKV: LLM Knows What You are Looking for Before Generation
- Transformers are Multi-State RNNs
- Qwen2.5 Technical Report
- Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
- Efficient Streaming Language Models with Attention Sinks
- When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression
- H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks