Cover Image

Value-Guided KV Compression for LLMs via Approximated CUR Decomposition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sengupta, Ayan, Chaudhary, Siddhant, Chakraborty, Tanmoy
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Compression Laws for Large Language Models
by: Sengupta, Ayan, et al.
Published: (2025)

You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
by: Sengupta, Ayan, et al.
Published: (2025)

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

Position: Enough of Scaling LLMs! Lets Focus on Downscaling
by: Goel, Yash, et al.
Published: (2025)

The Art of Scaling Test-Time Compute for Large Language Models
by: Agarwal, Aradhye, et al.
Published: (2025)

First Finish Search: Efficient Test-Time Scaling in Large Language Models
by: Agarwal, Aradhye, et al.
Published: (2025)

How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines
by: Sengupta, Ayan, et al.
Published: (2025)

On the Generalization vs Fidelity Paradox in Knowledge Distillation
by: Ramesh, Suhas Kamasetty, et al.
Published: (2025)

Persona-aware Generative Model for Code-mixed Language
by: Sengupta, Ayan, et al.
Published: (2023)

From Images to Words: Efficient Cross-Modal Knowledge Distillation to Language Models from Black-box Teachers
by: Sengupta, Ayan, et al.
Published: (2026)

Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models
by: Agarwal, Aradhye, et al.
Published: (2024)

MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing
by: Agarwal, Siddhant, et al.
Published: (2024)

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation
by: Sengupta, Ayan, et al.
Published: (2024)

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

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

Multilingual Test-Time Scaling via Initial Thought Transfer
by: Bajpai, Prasoon, et al.
Published: (2025)

Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing
by: Tanwar, Eshaan, et al.
Published: (2025)

Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?
by: Bajpai, Ashutosh, et al.
Published: (2025)

KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
by: Chen, Jian, et al.
Published: (2026)

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache
by: Liu, Xiaoran, et al.
Published: (2025)

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

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
by: Ji, Shiyu, et al.
Published: (2026)

Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression
by: Liu, Peiyu, et al.
Published: (2024)

Compressing Transformer Language Models via Matrix Product Operator Decomposition: A Case Study on PicoGPT
by: Javanmard, Younes, et al.
Published: (2026)

KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head
by: Rehg, Isaac
Published: (2024)

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
by: Du, Wenjie, et al.
Published: (2025)

Understanding the Effects of Domain Finetuning on LLMs
by: Tanwar, Eshaan, et al.
Published: (2025)

Mitigating KV Cache Competition to Enhance User Experience in LLM Inference
by: Shen, Haiying, et al.
Published: (2025)

Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators
by: Bajpai, Prasoon, et al.
Published: (2024)

KV-Distill: Nearly Lossless Learnable Context Compression for LLMs
by: Chari, Vivek, et al.
Published: (2025)

Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages
by: Bajpai, Ashutosh, et al.
Published: (2024)

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
by: Ge, Suyu, et al.
Published: (2023)

Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues
by: Kumar, Shivani, et al.
Published: (2024)

Decoding Memes: Benchmarking Narrative Role Classification across Multilingual and Multimodal Models
by: Sharma, Shivam, et al.
Published: (2025)

HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs
by: Yang, Dongquan, et al.
Published: (2025)

Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks
by: Hengle, Amey, et al.
Published: (2025)

Compactor: Calibrated Query-Agnostic KV Cache Compression with Approximate Leverage Scores
by: Chari, Vivek, et al.
Published: (2025)

Latent Performance Profiling of Large Language Models
by: Chakraborty, Tanmoy, et al.
Published: (2026)

FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension
by: Kai, Jushi, et al.
Published: (2025)

Hate Personified: Investigating the role of LLMs in content moderation
by: Masud, Sarah, et al.
Published: (2024)