Image de couverture de livre

Trust, but Verify: Peeling Low-Bit Transformer Networks for Training Monitoring

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Eamaz, Arian, Yeganegi, Farhang, Soltanalian, Mojtaba
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

Data-Aware Training Quality Monitoring and Certification for Reliable Deep Learning
par: Yeganegi, Farhang, et autres
Publié: (2024)

Physics-Inspired Binary Neural Networks: Interpretable Compression with Theoretical Guarantees
par: Eamaz, Arian, et autres
Publié: (2025)

Low-rank Matrix Sensing With Dithered One-Bit Quantization
par: Yeganegi, Farhang, et autres
Publié: (2023)

Matrix Completion from One-Bit Dither Samples
par: Eamaz, Arian, et autres
Publié: (2023)

Sample Abundance for Signal Processing: A Brief Introduction
par: Eamaz, Arian, et autres
Publié: (2025)

From Quasi-Isometric Embeddings to Finite-Volume Property: A Theoretical Framework for Quantized Matrix Completion
par: Eamaz, Arian, et autres
Publié: (2023)

Deep Learning-Enabled One-Bit DoA Estimation
par: Yeganegi, Farhang, et autres
Publié: (2024)

Harnessing the Power of Sample Abundance: Theoretical Guarantees and Algorithms for Accelerated One-Bit Sensing
par: Eamaz, Arian, et autres
Publié: (2023)

Automotive Radar Sensing with Sparse Linear Arrays Using One-Bit Hankel Matrix Completion
par: Eamaz, Arian, et autres
Publié: (2023)

Collaborative Automotive Radar Sensing via Mixed-Precision Distributed Array Completion
par: Eamaz, Arian, et autres
Publié: (2024)

Linearization Explains Fine-Tuning in Large Language Models
par: Afzal, Zahra Rahimi, et autres
Publié: (2026)

V-STaR: Training Verifiers for Self-Taught Reasoners
par: Hosseini, Arian, et autres
Publié: (2024)

PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time
par: Pourali, Alireza, et autres
Publié: (2024)

CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs
par: Wang, Haoyu, et autres
Publié: (2024)

FrameQuant: Flexible Low-Bit Quantization for Transformers
par: Adepu, Harshavardhan, et autres
Publié: (2024)

Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision
par: Huang, Xijie, et autres
Publié: (2023)

Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs
par: Xu, Binxing, et autres
Publié: (2026)

Generative Verifiers: Reward Modeling as Next-Token Prediction
par: Zhang, Lunjun, et autres
Publié: (2024)

TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction
par: Li, Yuhang, et autres
Publié: (2024)

Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks
par: Niu, Muqun, et autres
Publié: (2024)

Why ReLU? A Bit-Model Dichotomy for Deep Network Training
par: Doron-Arad, Ilan, et autres
Publié: (2026)

Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate
par: Kim, Jaemin, et autres
Publié: (2026)

LoCo: Low-Bit Communication Adaptor for Large-scale Model Training
par: Xie, Xingyu, et autres
Publié: (2024)

SplitQuant: Layer Splitting for Low-Bit Neural Network Quantization
par: Song, Jaewoo, et autres
Publié: (2025)

1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization
par: Maskey, Sohir, et autres
Publié: (2026)

BitSnap: Checkpoint Sparsification and Quantization in LLM Training
par: Peng, Yanxin, et autres
Publié: (2025)

Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
par: Yang, Zhicheng, et autres
Publié: (2025)

DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
par: Zhou, Jiajun, et autres
Publié: (2023)

True 4-Bit Quantized Convolutional Neural Network Training on CPU: Achieving Full-Precision Parity
par: Tathe, Shivnath
Publié: (2026)

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers
par: Sareen, Kusha, et autres
Publié: (2025)

Boundary Peeling: Outlier Detection Method Using One-Class Peeling
par: Arafat, Sheikh, et autres
Publié: (2023)

HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
par: Wang, Guoan, et autres
Publié: (2026)

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
par: Zhang, Tianao, et autres
Publié: (2025)

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
par: Ouyang, Xu, et autres
Publié: (2024)

Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks
par: Bernardelli, Ambrogio Maria, et autres
Publié: (2022)

BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks
par: Bührer, Simon, et autres
Publié: (2026)

LittleBit: Ultra Low-Bit Quantization via Latent Factorization
par: Lee, Banseok, et autres
Publié: (2025)

Constant Bit-size Transformers Are Turing Complete
par: Li, Qian, et autres
Publié: (2025)

Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding
par: Liu, Taowen, et autres
Publié: (2025)

Learning to Trust Experience: A Monitor-Trust-Regulator Framework for Learning under Unobservable Feedback Reliability
par: Zhang, Zhipeng, et autres
Publié: (2026)