Quantization Robustness

Follow this topic Ask about this topic

Latest papers

27 papers7 papers in the last four weeks, up 40% on the four weeks before. 0.0% of all new papers.

Beyond Accuracy: How Quantization Affects Coding Agents
Nov 2, 2026Areej Mehboob, Muhammad Ali Shafique, Muhammad Usman Qadeer +1AI Coding Agents Quantization Robustness
Traversaal AI · Kansas State University
Audit at the Precision You Deploy: Quantization Reshapes a Subliminally Learned Preference
Oct 31, 2026Md Rayhanul Masud, Mst Suraiya Akter ShefaQuantization Robustness LLM Quantization
University of California, Riverside
TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models
Oct 31, 2026Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg +4LLM Quantization Quantization Robustness
Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada · Applied Computer Education Department, Red River College Polytechnic, Winnipeg, MB, Canada · Bonn-Aachen International Center for IT (b-it), University of Bonn, Bonn, Germany +2
ORBITAL: Optimization of Robust Brain--Computer Inference Through Architecture-Aware Low-Precision Compression
Oct 26, 2026Saim Rehman, Muhammad ShafiqueAdversarial Robustness Brain-Computer Interfaces
eBRAIN Lab, New York University Abu Dhabi, Abu Dhabi, UAE
CrowdCC: Jointly Benchmarking Corruption Robustness and Deployment Quantization in Crowd Counting
Oct 26, 2026S Mahmudul Hasan, Lu PengCrowd Counting Image Corruption Robustness
Tulane University
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
Oct 8, 2026Yanlong Zhao, Xiaoyuan Cheng, Huihang Liu +6LLM Quantization Post-Training Quantization
University of Science and Technology of China · University College London · Shanghai University of Finance and Economics +5
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
Oct 5, 2026Yan Scholten, Rachel Lawrence, James Hensman +3LLM Quantization Quantization Robustness
Dept. of Computer Science & Munich Data Science Institute, Technical University of Munich · Microsoft Research Cambridge, UK
Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning
Oct 5, 2026Shen Ruan, Wenchang Gao, Jin Wang +4Vision-Language-Action Models OOD Generalization
Soochow University · Independent Researcher · Shanghai Jiao Tong University +2
Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization
Oct 4, 2026Hanzhang Wang, Tianqi Shen, Zonglin Liu +3LLM Quantization Quantization Robustness
City University of Hong Kong · The University of Hong Kong
PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers
Sep 27, 2026Yutong Wang, Xingtong Ge, Enhuai Liu +4Video Diffusion Models Diffusion Transformer
The University of Sydney · The Hong Kong University of Science and Technology · The Chinese University of Hong Kong +1
Quantization-Robust Unlearning through the Lens of Retain-Forget Loss Landscapes Interaction
Sep 23, 2026Jialu Wang, Jianing Deng, Shuqing Luo +6Machine Unlearning LLM Unlearning
University of North Carolina at Chapel Hill · University of Pittsburgh · University of Arizona +1
The Undetected Damage of Quantization on Retrieval and How to Fix It
Sep 21, 2026Luca Zhou, Alessandro Zirilli, Daniele Solombrino +2Mixed-Precision Quantization Information Retrieval
Sapienza University of Rome · Not Diamond · Paradigma
Why Does Post-Training Quantization Work?
Sep 10, 2026Yuxiang Chen, Michael Beyer, Jun Zhu +1LLM Quantization Quantization Robustness
Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University · College of AI, Tsinghua University · Bosch AI Research, Renningen, Germany
SandwichQuant: Which Parameters Matter Before and After Quantization?
Aug 25, 2026Peng Xia, Junbiao PangNeural Network Quantization Quantization Error Compensation
School of Information Science and Technology, Beijing University of Technology Beijing, China
Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models
Aug 21, 2026Deepanshu Pandey, Arnav Chavan, Nahush Lele +2Quantization Robustness Neural Network Quantization
Amazon
Which Decisions Low-Bit Quantization Breaks, and How to Predict Them
Aug 6, 2026Zekun Wu, Swati Dhiman, Adriano KoshiyamaPost-Training Quantization Low-Bit Quantization
Holistic AI · UCL Centre for Artificial Intelligence, University College London
Flat Score, Amplified Failures: How the Error Budget Masks Damage in Quantized LLM Agents
Jul 29, 2026Jiwon Jang, Kisu Yang, Heuiseok Lim +1Post-Training Quantization AI Agent Reliability
VAIV Company · Seoul National University · Korea University
GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries
Jul 22, 2026Miguel P. Bento, João F. SeabraLLM Quantization Rotation-Based Quantization
Independent Researcher, Lisbon, Portugal
Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Robotics
Jul 20, 2026Hamidreza Yaghoubi Araghi, Parastoo Pilevar, Ming C. LinNeural Network Robustness Image Corruption Robustness
University of Maryland, College Park, MD, USA
Trainable Smooth-Rotation Transforms with Learned Channel Scales for LLM Quantization
Jun 7, 2026Patrik Czakó, Gábor Kertész, Sándor SzénásiLLM Quantization 4-Bit Quantization
Doctoral School of Applied Informatics and Applied Mathematics, Obuda University Budapest, Hungary · John von Neumann Faculty of Informatics, Obuda University Budapest, Hungary
DocQT: Improving Document Forgery Localization Robustness via Diverse JPEG Quantization Tables
May 19, 2026Kylian Ronfleux-Corail, Guillaume Bernard, Mickaël Coustaty +1Image Corruption Robustness Image Forgery Detection
L3I · MAIF, Niort, France · L3i Laboratory, La Rochelle University, La Rochelle, France
Attention Sinks and Outliers in Attention Residuals
May 18, 2026Haozheng Luo, Haoran Dai, Shaoyang Zhang +10LLM Quantization Attention Residual Connections
Department of Computer Science, Northwestern University · Department of Computer Science, Illinois Institute of Technolog · Department of Computer Science and Engineering, University of Michigan +5
DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning
May 4, 2026Abdullah Ahmad Khan, Ferdous SohelQuantization-Aware Training 4-Bit Quantization
Murdoch University
On the Quantization Robustness of Diffusion Language Models in Coding Benchmarks
Apr 22, 2026Aarav Gupta, Gururaj Deshpande, Chandreyi ChakrabortyMixed-Precision Quantization Diffusion Model Quantization
College of Computing · Georgia Institute of Technology
Zero-Shot Quantization via Weight-Space Arithmetic
Apr 3, 2026Daniele Solombrino, Antonio Andrea Gargiulo, Alessandro Zirilli +3Quantization Robustness Quantization
Sapienza University of Rome · Sapienza University of Rome / Paradigma
RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks
Mar 16, 2026Ali Soltan Mohammadi, Samira Nazari, Ali Azarpeyvand +5Neural Network Fault Tolerance Adversarial Robustness
University of Zanjan, Zanjan, Iran · Brandenburg Technical University, Cottbus, Germany · Tallinn University of Technology, Tallinn, Estonia +1
Quantization Robustness of Monotone Operator Equilibrium Networks
Mar 11, 2026James Li, Philip H. W. Leong, Thomas ChaffeyQuantization Robustness Neural Network Quantization
School of Electrical and Computer Engineering, The University of Sydney, NSW, Australia

Nov 2, 2026J/K move · Enter open · S save

Beyond Accuracy: How Quantization Affects Coding Agents

Areej Mehboob, Muhammad Ali Shafique, Muhammad Usman Qadeer, Hamza Farooq

Traversaal AI · Kansas State University

AI Coding Agents Quantization Robustness LLM Quantization Post-Training Quantization

Open paper AskPDF arXiv

Agents are increasingly used for coding tasks, but the inference cost of large language models (LLMs) limits where they can run. Quantization reduces model size, but its effects on coding agents that execute and revise programs remain underexplored. We compare BF16 with 4-bit AWQ and GPTQ for Qwen2.5-Coder-Instruct (7B, 14B, and 32B) and Devstral-Small-2507 (24B) on OJBench coding problems across three seeds. We detect no statistically significant accuracy loss for any of the coding agents. However, final accuracy can conceal substantial behavioral changes: AWQ reduces Qwen-7B one-shot solves from 17 to 0 while increasing loop-based solves from 10 to 25. All Qwen-32B successes involve tool use, whereas Devstral rarely makes a valid executor call. Failure profiles also differ: Qwen-32B produces far more compilation errors than the smaller Qwen models, rising slightly under quantization, while Devstral's failures shift significantly from runtime errors toward wrong answers and timeouts. These findings indicate that quantization robustness in coding agents should be assessed through solution trajectories, tool use, and failure modes, in addition to final accuracy.