Precision-Critical Manipulation

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 17

All topics

When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs
Sep 21, 2026Yeji Kim, Mi-Young Kim, Randy GoebelClinical Reasoning Training Post-Training
University of Alberta
Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
Sep 16, 2026Alizishaan Khatri, Chiquita Prabhu, Omkar NeogiLarge Language Model Safety Guardrail
Wrynx Inc. · Independent Researcher
D3ARC: Time-Critical Distributed Disaster Detection for Asynchronous Cooperative Multi-Robot Systems
Sep 7, 2026Nikolaos Koursioumpas, Lina Magoula, Nancy Alonistioti +1Wildfire Detection Multi-Robot Systems
Dept. of Informatics and Telecommunications, National and Kapodistrian University of Athens, Greece · Huawei Heisenberg Research Center (Munich), Germany
FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Driving
Aug 10, 2026Guolei Huang, Tengfei She, Yuxuan Lu +3Causality-Aware End-To-End Autonomous Driving Autonomous Driving
1Southeast University · 2Universiti Malay · 3Ant Group +2
Multi-Agent Reinforcement Learning for Online Traffic Scheduling in Time-Sensitive Application
Aug 5, 2026Marcos Carvalho, Fatih Temiz, Shavbo Salehi +2Schedulers Multi-Agent Reinforcement Learning
Universidade Federal de Minas Gerais, Brazil · School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada
Explainable and Resource-Efficient Spatial Reasoning in Multimodal LLMs for Decision-Critical Applications
Jul 29, 2026Piyush Jain, Kousik Dasgupta, Rajarshi Roy +1Spatial Reasoning Multimodal Large Language Models
Heritage Institute of Technology, Kolkata, India · Kalyani Government Engineering College, Kalyani, India · IAIRO, India +1
A Sliding-Window-Based Reinforcement Learning for Dynamic Assembly Flow Shop Scheduling with Multi-Product Delivery
Jul 3, 2026Junhao Qiu, Jianjun Liu, Ting Liu +3Job Shop Scheduling Schedule
School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, China · Department of Computer Science, City University of Hong Kong, Hong Kong
Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
Jun 19, 2026Zhenting Zhu, Lucas Thai, Shan Yu +5LLM Inference Optimization Reproducibility
1UCLA · 2UC Berkeley · University of Chinese Academy of Sciences
Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition
Jun 5, 2026Tung X. Nguyen, Hieu Minh Truong, Giang Son Nguyen +3Code-Switching Automatic Speech Recognition
VinUniversity, Vietnam · University of Technology Sydney, Australia · Monash University, Australia
Explainable Runtime Dependency Tracking for AI-RAN Conflict Monitoring
Jun 4, 2026Christie Djidjev, Nicholas KaminskiOpen Radio Access Networks Runtime
Idaho National Laboratory Idaho Falls, United States
Less is MoE: Trimming Experts in Domain-Specialist Language Models
Jun 4, 2026Haoze He, Xinkai Zou, Xuan Jiang +4Mixture-Of-Experts Experts
Carnegie Mellon University · UCSD · MIT
STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System
May 15, 2026Zhen Luo, Yixuan Yang, Xudong Xu +5Physics Simulation Embodied Artificial Intelligence
1SII 2SUSTech · 2SUSTech · 3Shanghai AI Laboratory +4
GraphFlow: An Architecture for Formally Verifiable Visual Workflows Enabling Reliable Agentic AI Automation
May 14, 2026Drewry H. Morris, Luis Valles, Reza Hosseini GhomiAgentic Workflows Agentic Workflow Design
MedFlow, Inc.
HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds
May 11, 2026Honghan Wu, Tianyan Wang, Jiacong Mi +2Deep Semantic Representations Context-Awareness
University of Glasgow, Glasgow, UK · University of International Relations, Beijing, China · University College London, London, UK
TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains
May 5, 2026Serhii ZabolotniiTrustworthy Artificial Intelligence AI Trustworthiness
Cherkasy State Business College, Cherkasy 18028, Ukraine · State Scientific Research Institute of Armament and Military Equipment Testing and Certification, Cherkasy, Ukraine · healthPrecision, New York, NY, USA
AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models
Apr 20, 2026Tingzheng Jia, Kan Guo, Lanping Qian +6Diffusion-Based Vision-Language-Actions Trajectory Generation
Beijing University of Technology Beijing, China · Beihang University Beijing, China · Nanjing University of Science and Technology Nanjing, China
DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing
Jan 18, 2026Jinwei Hu, Shiyuan Meng, Yi Dong +1Precision-Critical Manipulation Spatiotemporal
University of Liverpool, Liverpool, UK · Shanghai Artificial Intelligence Laboratory, Shanghai, China

Sep 21, 2026, cs.CLJ/K move · Enter open · S save

When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs

Yeji Kim, Mi-Young Kim, Randy Goebel

University of Alberta

Clinical Reasoning Training Post-Training Precision-Critical Manipulation

Open paper AskPDF arXiv

Post-training quantization (PTQ) enables efficient deployment of large language models, and PTQ methods are usually optimized and evaluated with generic reconstruction, perplexity, or answer accuracy. But in explanation-critical domains, preserving only the final answer may be insufficient, since users may also inspect generated rationales to judge whether a prediction is trustworthy. We study this issue in medical multiple-choice question answering, where rationales should provide evidence that supports the selected answer. We propose an explanation-aware objective for transformation-based PTQ. Our method builds an offline faithfulness cache from full-precision teacher rationales and uses it during optimization to preserve answer-supporting evidence tokens and evidence-conditioned answer behavior. We instantiate it on OSTQuant under W4A4KV4 quantization and evaluate four 7B--8B medical and instruction-tuned LLMs on MedExQA, MedExpQA, and ChallengeClinicalQA. While a same-calibration OSTQuant baseline preserves task accuracy, it can substantially weaken answer-supporting rationales. Our objective is to preserve the full-precision model's answer-supporting behavior rather than improve gold-label accuracy, and our method better preserves the full-precision model's answer behavior and rationale-to-answer support. These results suggest that PTQ for explanation-critical settings should evaluate preservation of answer-supporting evidence, not only answer accuracy. Code and evaluation scripts are available at https://github.com/dut0817/EAQuant.

Momentum

Related topics

Latest papers 17