Image de couverture de livre

ThinK: Thinner Key Cache by Query-Driven Pruning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Yuhui, Jie, Zhanming, Dong, Hanze, Wang, Lei, Lu, Xudong, Zhou, Aojun, Saha, Amrita, Xiong, Caiming, Sahoo, Doyen
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
par: Zhao, Zirui, et autres
Publié: (2024)

Scalable Chain of Thoughts via Elastic Reasoning
par: Xu, Yuhui, et autres
Publié: (2025)

MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
par: Wang, Lei, et autres
Publié: (2024)

Fractured Chain-of-Thought Reasoning
par: Liao, Baohao, et autres
Publié: (2025)

XForecast: Evaluating Natural Language Explanations for Time Series Forecasting
par: Aksu, Taha, et autres
Publié: (2024)

Reward-Guided Speculative Decoding for Efficient LLM Reasoning
par: Liao, Baohao, et autres
Publié: (2025)

Entropy-Based Block Pruning for Efficient Large Language Models
par: Yang, Liangwei, et autres
Publié: (2025)

Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
par: Hu, Zhiyuan, et autres
Publié: (2025)

Reward Models Identify Consistency, Not Causality
par: Xu, Yuhui, et autres
Publié: (2025)

A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
par: Xiong, Wei, et autres
Publié: (2025)

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
par: Xu, Yiheng, et autres
Publié: (2024)

RLHF Workflow: From Reward Modeling to Online RLHF
par: Dong, Hanze, et autres
Publié: (2024)

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
par: Le, Hung, et autres
Publié: (2024)

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
par: Lu, Xudong, et autres
Publié: (2024)

MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
par: Luo, Ziyang, et autres
Publié: (2025)

CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
par: Li, Jierui, et autres
Publié: (2024)

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
par: Le, Hung, et autres
Publié: (2023)

Unified Training of Universal Time Series Forecasting Transformers
par: Woo, Gerald, et autres
Publié: (2024)

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models
par: Lu, Xudong, et autres
Publié: (2024)

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
par: Liao, Huanxuan, et autres
Publié: (2025)

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
par: Peng, Yun, et autres
Publié: (2024)

BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
par: Pang, Bo, et autres
Publié: (2025)

Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions
par: Zhang, David Junhao, et autres
Publié: (2024)

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
par: Liu, Juncheng, et autres
Publié: (2024)

GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
par: Aksu, Taha, et autres
Publié: (2024)

Thinner Cortex, Sharper Attention? Paradoxical Links Between Cortical Thinning and Attentional Capacity in Cognitive Aging
par: Yi Jin Leow, et autres
Publié: (2025)

LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
par: Zhang, Yike, et autres
Publié: (2025)

Towards Threshold-Free KV Cache Pruning
par: Ni, Xuanfan, et autres
Publié: (2025)

Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models
par: Liu, Xu, et autres
Publié: (2025)

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
par: Liu, Xu, et autres
Publié: (2024)

Moirai 2.0: When Less Is More for Time Series Forecasting
par: Liu, Chenghao, et autres
Publié: (2025)

TerDiT: Ternary Diffusion Models with Transformers
par: Lu, Xudong, et autres
Publié: (2024)

On Secure Gradient Coding with Uncoded Groupwise Keys
par: You, Xudong, et autres
Publié: (2026)

Thinner Latent Spaces: Detecting Dimension and Imposing Invariance with Conformal Autoencoders
par: Kevrekidis, George A., et autres
Publié: (2024)

Thinner Tibial Spine Fracture Fragments Are Associated With Risk of Fixation Failure
par: Gregory Benes, et autres
Publié: (2024)

SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs
par: Jie, Shibo, et autres
Publié: (2025)

Beyond Uniform Query Distribution: Key-Driven Grouped Query Attention
par: Khan, Zohaib, et autres
Publié: (2024)

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
par: Xie, Tianbao, et autres
Publié: (2025)

GUI-KV: Efficient GUI Agents via KV Cache with Spatio-Temporal Awareness
par: Huang, Kung-Hsiang, et autres
Publié: (2025)

DiFache: Efficient and Scalable Caching on Disaggregated Memory using Decentralized Coherence
par: Zhang, Hanze, et autres
Publié: (2025)