Model Calibration

Follow this topic Ask about this topic

Momentum

21 papers in the last four weeks, up 91% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 147

All topics

APIC: Amortized Physics-Informed Calibration using Neural Processes
Jun 2, 2026Aishwarya Venkataramanan, Sai Karthikeya Vemuri, Joachim DenzlerUncertainty Quantification Amortized Inference
Computer Vision Group, Friedrich Schiller University Jena, Germany
Calibration Data Trade-offs Across Capability Dimensions: Why Multi-Source Mixing Matters for High-Sparsity LLM Pruning
Jun 2, 2026Hu Xu, Zhaolong Xing, Congcong Liu +5LLM Pruning Model Calibration
Shanghai Jiao Tong University
Hierarchies of Calibration: Classification meets Regression
Jun 2, 2026Johannes Resin, Lu Yang, Tilmann GneitingProbability Calibration Model Calibration
1Goethe University Frankfurt · 3Heidelberg Institute for Theoretical Studies · University of Minnesota +1
Belief Consistency Between Foundation-Model Evidence and Geometric Perception in Persistent Robotic Maps
May 29, 2026Christoffer Heckman, Harel Biggie, Brendan Crowe +1Model Calibration Semantic Mapping
Department of Computer Science, University of Colorado, Boulder · Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology
Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictions
May 27, 2026Parsa Gooya, Reinel Sospedra-AlfonsoTime Series Forecasting Probabilistic Forecasting
Canadian Centre for Climate Modelling and Analysis, Environment and Climate Change Canada, Victoria, British Columbia, Canada
Multicalibration Boosting: Theory, Convergence, and Transferability
May 23, 2026Hanxuan Ye, Hongzhe LiPost-Hoc Calibration Model Calibration
Department of Biostatistics and Epidemiology University of Pennsylvania Philadelphia, PA 19104-6021, USA · Department of Biostatistics and Epidemiology University of Pennsylvania2026 Philadelphia, PA 19104-6021, USA
Smoothed Elicitation Complexity for Approximate $Γ$ -calibration of Discrete Classification Tasks
May 21, 2026Jessica Finocchiaro, Victor Ganson, Drona KhuranaModel Calibration Multiclass Classification
Computer Science, Boston College · Computer Science, University of Colorado Boulder
Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study
May 20, 2026Michael O. EnioladeUncertainty Quantification Conformal Prediction
University of the Cumberlands
Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction
May 20, 2026Zhenjiang Mao, Jiawen Wu, Gabriel Wagner +2Post-Hoc Calibration Autonomous Racing
Trustworthy Engineered Autonomy (TEA) Lab, Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL 32611, USA
Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
May 20, 2026Jinzong Dong, Zhaohui Jiang, Bo YangProbability Calibration Unsupervised Domain Adaptation
School of Automation, Central South University, Changsha, China.
Divide et Calibra: Multiclass Local Calibration via Vector Quantization
May 20, 2026Cesare Barbera, Lorenzo Perini, Giovanni De Toni +2Model Calibration
University of Pisa, Univeristy of Trento · Meta · Fondazione Bruno Kessler +1
Knowing When Not to Predict: Self Supervised Learning and Abstention for Safer DR Screening
May 18, 2026Muskaan Chopra, Lorenz Sparrenberg, Jan H. Terheyden +1Selective Prediction Self-Supervised Pre-Training
Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Germany · University Hospital Bonn - Department of Ophthalmology, Germany +1
HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL
May 18, 2026Zhi Li, Songkun Yan, Jie Cao +4Reinforcement Learning Model Calibration
Civil, Environmental, and Architectural Engineering, University of Colorado Boulder · Civil Engineering and Environmental Sciences, University of Oklahoma · Department of Computer Science, University of Oklahoma +3
Error-Decomposed Class-Conditional Fusion for Statistically Guaranteed Hard-Category Robust Perception
May 17, 2026Guowei Luo, Ziqi Shi, Zhao XieModel Calibration Object Detection
Hefei University of Technology, Hefei, China · Lishui University, Lishui, China
Discovery of Hidden Miscalibration Regimes
May 13, 2026Katarzyna Kobalczyk, Mihaela van der SchaarPost-Hoc Calibration Language Model Calibration
University of Cambridge
Hybrid Quantum-MambaVision: A Quantum-enhanced State Space Model for Calibrated Mixed-type Wafer Defect Detection
May 13, 2026Satwik Sai Prakash Sahoo, Jyoti Prakash Sahoo, Ting Wang +1Multi-Label Classification Hybrid Quantum-Classical ML
Odisha University of Technology and Research, Bhubaneswar, India · National Taiwan University of Science and Technology, Taipei, Taiwan · East China Normal University, Shanghai, China +1
FeatCal: Feature Calibration for Post-Merging Models
May 13, 2026Yanggan Gu, Shuo Cai, Zihao Wang +7Distribution Shift Model Calibration
The Hong Kong Polytechnic University (PolyU) · The Chinese University of Hong Kong · PolyU-Daya Bay Technology and Innovation Research Institute
Local Conformal Calibration of Dynamics Uncertainty from Semantic Images
May 13, 2026Luís Marques, Dmitry BerensonUncertainty Quantification Conformal Prediction
Robotics Department, University of Michigan, Ann Arbor, MI 48109, USA
Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration
May 12, 2026Mingtao Xian, Yifeng Yang, Qinying Gu +2Multimodal Large Language Models Cross-Modal Retrieval
Zhiyuan College, Shanghai Jiao Tong University, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China +1
VNDUQE: Information-Theoretic Novelty Detection using Deep Variational Information Bottleneck
May 12, 2026Aryan Gondkar, Hayder Radha, Yiming DengUncertainty Quantification Information Bottleneck
Nondestructive Evaluation Lab, Department of Electrical and Computer Engineering Michigan State University East Lansing, MI · Department of Electrical and Computer Engineering Michigan State University East Lansing, MI
Adaptive Calibration in Non-Stationary Environments
May 12, 2026Junyan Liu, Haipeng Luo, Lillian J. RatliffModel Calibration
University of Washington · University of Southern California
Unified Approach for Weakly Supervised Multicalibration
May 11, 2026Futoshi Futami, Takashi IshidaPost-Hoc Calibration Model Calibration
The University of Osaka / RIKEN AIP / The University of Tokyo · The University of Tokyo / RIKEN AIP
Instance-Adaptive Online Multicalibration
May 10, 2026Zhiming Huang, Jamie Morgenstern, Aaron Roth +1Probability Calibration Model Calibration
Paul G. Allen School of Computer Science and Engineering, University of Washington · Department of Computer and Information Sciences, University of Pennsylvania
Data-driven transport modelling without overfit
May 9, 2026Peter Vanya, Katarína Šimková, Rastislav FarkašIntelligent Transportation Systems Traffic Flow Estimation
Sev.en Global Investments, V Celnici 4, 11000 Prague, Czechia · Vrije Universiteit Brussels, Brussels, Belgium · Universit´e Libre de Bruxelles, Brussels, Belgium +1
A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
May 8, 2026Zhanliang Wang, Jiancong Xiao, Ruochen Jin +3LLM Evaluation Confidence Estimation in Language Models
University of Pennsylvania, Philadelphia, PA · Dartmouth College, Hanover, NH
The Minimax Rate of Perturbed Second-Order Calibration
May 8, 2026Kamil Ciosek, Banafsheh Rafiee, Sina Ghiassian +1Post-Hoc Calibration Minimax Estimation
Spotify
Online Bayesian Calibration under Gradual and Abrupt System Changes
May 7, 2026Yang Xu, Chiwoo ParkParticle Filtering Bayesian Filtering
Department of Industrial and Systems Engineering University of Washington Seattle, WA 98195
Log-Likelihood, Simpson's Paradox, and the Detection of Machine-Generated Text
May 7, 2026Tom Kempton, Viktor Drobnyi, Maeve Madigan +1AI-Generated Text Detection Language Model Calibration
Department of Mathematics University of Manchester · Risk and Security AI Lab Visa Inc.
Correcting heterogeneous diagnostic bias when developing clinical prediction models using causal hidden Markov models
May 7, 2026Jose Benitez-Aurioles, Ricardo Silva, Brian McMillan +1Counterfactual Prediction Model Calibration
Division of Informatics, Imaging & Data Sciences, University of Manchester, Manchester, United Kingdom · Department of Statistical Science, UCL, London, United Kingdom · Division of Population Health, Health Services Research & Primary Care, University of Manchester, Manchester, United Kingdom
The Manokhin Probability Matrix: A Diagnostic Framework for Classifier Probability Quality
May 5, 2026Valery ManokhinPost-Hoc Calibration Probability Calibration
Independent Researcher

Jun 2, 2026, cs.LGJ/K move · Enter open · S save

APIC: Amortized Physics-Informed Calibration using Neural Processes

Aishwarya Venkataramanan, Sai Karthikeya Vemuri, Joachim Denzler

Computer Vision Group, Friedrich Schiller University Jena, Germany

Uncertainty Quantification Amortized Inference Model Calibration Physics-Informed ML

Open paper AskPDF arXiv

Physics models are inherently imperfect due to misspecified or missing mechanisms, resulting in systematic discrepancies between model predictions and real-world observations. The Kennedy-O'Hagan (KOH) framework addresses this issue through explicit discrepancy modeling. However, its non-amortized, per-instance formulation limits scalability across families of related systems. We introduce Amortized Physics-Informed Calibration (APIC), a population-level extension of KOH that leverages Neural Processes to perform scalable Bayesian inference across realizations. Our framework employs a two-branch latent architecture to disentangle instance-specific physical parameters from shared, state-dependent structural discrepancies. By integrating differentiable physics into an amortized inference backbone, APIC enables rapid calibration of unseen realizations from sparse observations while quantifying uncertainty. Experiments on the damped spring oscillator, the Lotka-Volterra system, and the advection-diffusion PDE with misspecified physics demonstrate improved parameter recovery and consistent identification of the systemic discrepancy structure compared to other calibration approaches.

Momentum

Related topics

Latest papers 147