Copertina

Quantize What Counts: More for Keys, Less for Values

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hariri, Mohsen, Luo, Alan, Chen, Weicong, Zhong, Shaochen, Zhang, Tianyi, Wang, Qifan, Hu, Xia, Han, Xiaotian, Chaudhary, Vipin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
di: Zhang, Tianyi, et al.
Pubblicazione: (2025)

100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?
di: Yang, Wang, et al.
Pubblicazione: (2025)

$K^4$: Online Log Anomaly Detection Via Unsupervised Typicality Learning
di: Chen, Weicong, et al.
Pubblicazione: (2025)

Scorio.jl: A Julia package for ranking stochastic responses
di: Hariri, Mohsen, et al.
Pubblicazione: (2026)

Ranking Reasoning LLMs under Test-Time Scaling
di: Hariri, Mohsen, et al.
Pubblicazione: (2026)

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
di: Hariri, Mohsen, et al.
Pubblicazione: (2025)

Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
di: Wang, Shouren, et al.
Pubblicazione: (2025)

SELF: Self-Extend the Context Length With Logistic Growth Function
di: Dang, Phat Thanh, et al.
Pubblicazione: (2025)

Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
di: Singh, Vikash, et al.
Pubblicazione: (2026)

Medical Image Spatial Grounding with Semantic Sampling
di: Yu, Andrew Seohwan, et al.
Pubblicazione: (2026)

Thinking Preference Optimization
di: Yang, Wang, et al.
Pubblicazione: (2025)

Robust Ultra-High-Dimensional Variable Selection With Correlated Structure Using Group Testing
di: Guo, Wanru, et al.
Pubblicazione: (2026)

CausalGuard: Conformal Inference under Graph Uncertainty
di: Singh, Vikash, et al.
Pubblicazione: (2026)

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
di: Liu, Zirui, et al.
Pubblicazione: (2024)

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
di: Yang, Wang, et al.
Pubblicazione: (2025)

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
di: Liu, Zirui, et al.
Pubblicazione: (2023)

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification
di: Guo, Yiju, et al.
Pubblicazione: (2026)

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models
di: Luo, Feng, et al.
Pubblicazione: (2025)

FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
di: Han, Xiaotian, et al.
Pubblicazione: (2023)

WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
di: Yue, Yuxuan, et al.
Pubblicazione: (2024)

Trust The Typical
di: Ganguly, Debargha, et al.
Pubblicazione: (2026)

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion
di: Wang, Guanchu, et al.
Pubblicazione: (2024)

Novel adaptation of video segmentation to 3D MRI: efficient zero-shot knee segmentation with SAM2
di: Yu, Andrew Seohwan, et al.
Pubblicazione: (2024)

When Less is More: The LLM Scaling Paradox in Context Compression
di: Guo, Ruishan, et al.
Pubblicazione: (2026)

When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models
di: Zhang, Michael S., et al.
Pubblicazione: (2025)

Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
di: Yang, Wang, et al.
Pubblicazione: (2025)

Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning
di: Schulte, David, et al.
Pubblicazione: (2024)

Less is More: Improving LLM Alignment via Preference Data Selection
di: Deng, Xun, et al.
Pubblicazione: (2025)

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
di: Yang, Wang, et al.
Pubblicazione: (2026)

Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
di: Chang, Qian, et al.
Pubblicazione: (2026)

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
di: Dong, Andy, et al.
Pubblicazione: (2026)

Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
di: Hu, Chengming, et al.
Pubblicazione: (2023)

Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks
di: Ganguly, Debargha, et al.
Pubblicazione: (2024)

When Less is More: On the Value of "Co-training" for Semi-Supervised Software Defect Predictors
di: Majumder, Suvodeep, et al.
Pubblicazione: (2022)

Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
di: Shen, Yuhao, et al.
Pubblicazione: (2026)

SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
di: Duanmu, Haojie, et al.
Pubblicazione: (2024)

Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation
di: Tan, Jiayao, et al.
Pubblicazione: (2024)

When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning
di: Yang, Wang, et al.
Pubblicazione: (2026)

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem
di: Liu, Hongyi, et al.
Pubblicazione: (2024)

Transformer Multivariate Forecasting: Less is More?
di: Xu, Jingjing, et al.
Pubblicazione: (2023)