Image de couverture de livre

Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhuang, Zexin, Li, Yanhang, Fan, Zhichao
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries
par: Li, Yanhang, et autres
Publié: (2026)

SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks
par: Li, Yanhang, et autres
Publié: (2026)

Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice
par: Wang, Yingshuo, et autres
Publié: (2026)

4bit-Quantization in Vector-Embedding for RAG
par: Jeong, Taehee
Publié: (2025)

MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration
par: Wang, Jinguang, et autres
Publié: (2025)

SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization
par: Bai, Runsheng, et autres
Publié: (2024)

LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference
par: Elangovan, Reena, et autres
Publié: (2025)

LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization
par: Bouquet, Yann, et autres
Publié: (2026)

Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring
par: Lee, Dongyoung, et autres
Publié: (2025)

CCQ: Convolutional Code for Extreme Low-bit Quantization in LLMs
par: Zhou, Zhaojing, et autres
Publié: (2025)

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
par: Nielsen, Jacob, et autres
Publié: (2025)

OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
par: Li, Zhikai, et autres
Publié: (2026)

Low-bit Model Quantization for Deep Neural Networks: A Survey
par: Liu, Kai, et autres
Publié: (2025)

ICQuant: Index Coding enables Low-bit LLM Quantization
par: Li, Xinlin, et autres
Publié: (2025)

Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
par: Zhao, Yilong, et autres
Publié: (2023)

AAAC: Activation-Aware Adaptive Codebooks for 4-bit LLM Weight Quantization
par: IslamBouli, Beshr, et autres
Publié: (2026)

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
par: Zhou, Zhongzhu, et autres
Publié: (2026)

Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
par: Xia, Haojun, et autres
Publié: (2025)

DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
par: Sharify, Sayeh, et autres
Publié: (2026)

Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
par: Cho, Yoonjun, et autres
Publié: (2026)

Activation Quantization of Vision Encoders Needs Prefixing Registers
par: Kim, Seunghyeon, et autres
Publié: (2025)

Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
par: Hou, Zhichao, et autres
Publié: (2025)

BitNet a4.8: 4-bit Activations for 1-bit LLMs
par: Wang, Hongyu, et autres
Publié: (2024)

Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models
par: Hoang, Dung Anh, et autres
Publié: (2025)

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
par: Blumenberg, Patrick, et autres
Publié: (2025)

SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
par: Jia, Jinda, et autres
Publié: (2024)

D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
par: Yan, Xianglong, et autres
Publié: (2026)

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
par: Chen, Mengzhao, et autres
Publié: (2025)

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
par: Liu, Zirui, et autres
Publié: (2024)

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
par: Heo, Jung Hwan, et autres
Publié: (2023)

decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points
par: Guo, Yi, et autres
Publié: (2024)

BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment
par: Sajid, Md. Ashiq Ul Islam, et autres
Publié: (2026)

When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization
par: Nielsen, Jacob, et autres
Publié: (2024)

PID-Guided Partial Alignment for Multimodal Decentralized Federated Learning
par: Shi, Yanhang, et autres
Publié: (2026)

4-bit Shampoo for Memory-Efficient Network Training
par: Wang, Sike, et autres
Publié: (2024)

Combining the Strengths of Dutch Survey and Register Data in a Data Challenge to Predict Fertility (PreFer)
par: Sivak, Elizaveta, et autres
Publié: (2024)

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

1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit
par: Gao, Chang, et autres
Publié: (2024)

Metis: Training LLMs with FP4 Quantization
par: Cao, Hengjie, et autres
Publié: (2025)

Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization
par: Li, Jinhao, et autres
Publié: (2023)