Copertina

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bui, Ngoc, Nguyen, Hieu Trung, Cohan, Arman, Ying, Rex
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
di: Bui, Ngoc, et al.
Pubblicazione: (2025)

Explaining Graph Neural Networks via Structure-aware Interaction Index
di: Bui, Ngoc, et al.
Pubblicazione: (2024)

MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference
di: Li, Yu, et al.
Pubblicazione: (2026)

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
di: Li, Kunxi, et al.
Pubblicazione: (2025)

A Simple Plug-in for Improving Eviction-Based KV Cache Compression
di: Lin, Yuping, et al.
Pubblicazione: (2026)

Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
di: Miao, Ruijie, et al.
Pubblicazione: (2026)

ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
di: Dong, Zican, et al.
Pubblicazione: (2026)

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation
di: Shen, Yiqun, et al.
Pubblicazione: (2025)

CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM
di: Li, Yubo, et al.
Pubblicazione: (2026)

Mixture-of-Personas Language Models for Population Simulation
di: Bui, Ngoc, et al.
Pubblicazione: (2025)

CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction
di: Goel, Raghavv, et al.
Pubblicazione: (2025)

LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
di: Wang, Guangtao, et al.
Pubblicazione: (2025)

In-context KV-Cache Eviction for LLMs via Attention-Gate
di: Zeng, Zihao, et al.
Pubblicazione: (2024)

LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction
di: Zhou, Enshuai, et al.
Pubblicazione: (2026)

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
di: Ahn, Jinwoo, et al.
Pubblicazione: (2026)

Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language Models
di: Ma, Xindian, et al.
Pubblicazione: (2026)

RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
di: Liu, Sihao, et al.
Pubblicazione: (2026)

LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
di: Zhang, Haoyue, et al.
Pubblicazione: (2025)

EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving
di: Feng, Shaoting, et al.
Pubblicazione: (2025)

RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache
di: Zhang, Junkai, et al.
Pubblicazione: (2026)

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
di: Yang, Jiaming, et al.
Pubblicazione: (2026)

KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference
di: Gokhale, Sai, et al.
Pubblicazione: (2025)

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
di: Chitty-Venkata, Krishna Teja, et al.
Pubblicazione: (2025)

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
di: Sun, Hanshi, et al.
Pubblicazione: (2024)

Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches
di: Fang, Shaoke, et al.
Pubblicazione: (2026)

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
di: Qi, Yanlin, et al.
Pubblicazione: (2026)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
di: Wu, Wei, et al.
Pubblicazione: (2024)

SCBench: A KV Cache-Centric Analysis of Long-Context Methods
di: Li, Yucheng, et al.
Pubblicazione: (2024)

KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
di: Nadali, Alireza, et al.
Pubblicazione: (2026)

RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
di: Behnam, Payman, et al.
Pubblicazione: (2025)

KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
di: Akulov, Dmitry, et al.
Pubblicazione: (2025)

XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference
di: Li, Weizhuo, et al.
Pubblicazione: (2024)

TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
di: Dzikanyanga, Gradwell, et al.
Pubblicazione: (2026)

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
di: Hooper, Coleman, et al.
Pubblicazione: (2024)

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
di: He, Yefei, et al.
Pubblicazione: (2024)

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
di: Chen, Chuangtao, et al.
Pubblicazione: (2026)

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression
di: Zhang, Ruijie, et al.
Pubblicazione: (2026)

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
di: Shi, Dachuan, et al.
Pubblicazione: (2025)

CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
di: Wang, Luning, et al.
Pubblicazione: (2024)

KV Cache Offloading for Context-Intensive Tasks
di: Bocharnikov, Andrey, et al.
Pubblicazione: (2026)