Cover Image

SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Jialong, Wang, Zhenglin, Zhang, Linhai, Lai, Yilong, He, Yulan, Zhou, Deyu
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation
by: Lai, Yilong, et al.
Published: (2025)

PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation
by: Zhang, Linhai, et al.
Published: (2025)

SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
by: Wang, Zhenglin, et al.
Published: (2024)

Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment
by: Zhang, Congzhi, et al.
Published: (2024)

Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generation
by: Zhang, Linhai, et al.
Published: (2025)

DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference
by: Wu, Jialong, et al.
Published: (2024)

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models
by: Zhang, Linhai, et al.
Published: (2024)

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization
by: Zhang, Yanyue, et al.
Published: (2024)

WebWalker: Benchmarking LLMs in Web Traversal
by: Wu, Jialong, et al.
Published: (2025)

RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering
by: Liang, Sichu, et al.
Published: (2025)

AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment
by: Lai, Yilong, et al.
Published: (2024)

Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties
by: Wang, Zhenglin, et al.
Published: (2025)

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
by: Peng, Junjie, et al.
Published: (2026)

SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching
by: Chen, Hong, et al.
Published: (2026)

Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment
by: Zhang, Congzhi, et al.
Published: (2024)

TreeKV: Smooth Key-Value Cache Compression with Tree Structures
by: He, Ziwei, et al.
Published: (2025)

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
by: Shen, Zhenyi, et al.
Published: (2025)

Depictor : Topic‐Guided Opinion Summarization for Product Reviews With Dual‐Perspective Topic Modeling
by: Yanyue Zhang, et al.
Published: (2026)

Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models
by: Zhang, Yanyue, et al.
Published: (2025)

SCOPE: A Generative Approach for LLM Prompt Compression
by: Zhang, Tinghui, et al.
Published: (2025)

Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques
by: Javidnia, Neusha, et al.
Published: (2025)

CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memories
by: Lai, Yilong, et al.
Published: (2025)

Slow Tuning and Low-Entropy Masking for Safe Chain-of-Thought Distillation
by: Ma, Ziyang, et al.
Published: (2025)

When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges
by: Liang, Sichu, et al.
Published: (2026)

Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity
by: Zhang, Xin, et al.
Published: (2024)

SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
by: Jie, Shibo, et al.
Published: (2025)

Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics
by: Ananthanarayanan, Samhruth, et al.
Published: (2026)

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens
by: Ma, Ziyang, et al.
Published: (2025)

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty
by: Zhong, Meizhi, et al.
Published: (2024)

MA$^{2}$P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion
by: Zhang, Dingyi, et al.
Published: (2026)

Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind
by: Zhang, Dingyi, et al.
Published: (2025)

SynGraph: A Dynamic Graph-LLM Synthesis Framework for Sparse Streaming User Sentiment Modeling
by: Zhang, Xin, et al.
Published: (2025)

Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning
by: Zhao, Shangziqi, et al.
Published: (2025)

LongFlow: Efficient KV Cache Compression for Reasoning Models
by: Su, Yi, et al.
Published: (2026)

Learning to Evict from Key-Value Cache
by: Moschella, Luca, et al.
Published: (2026)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
by: Zhou, Xiabin, et al.
Published: (2024)

WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models
by: Yuan, Jian, et al.
Published: (2025)

CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation
by: Zhang, Hongxuan, et al.
Published: (2024)

HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
by: Shi, Zhiyuan, et al.
Published: (2026)

Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs
by: Cui, Wanyun, et al.
Published: (2025)