arXiv Computer Vision October 9, 2026 By Yutong Xie, Jiawei Tang, Zhenglin Hua, Yuxiang Ma, Si Qin, Yaxin Hou, Hui Liu, Junhui Hou, Yuheng Jia

Do Not Train Away Uncertainty: Early Uncertainty Anchored Calibration

Read the original on arXiv Computer Vision →

The paper introduces EUA‑Cal, a calibration method that preserves the early‑training uncertainty of deep neural networks. By regularizing predictions and feature prototypes based on the early model, EUA‑Cal mitigates overconfidence while maintaining accuracy. Experiments on image classification and multiple‑choice question answering across eight models show EUA‑Cal outperforms existing calibration techniques.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jul 3

An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms

arXiv:2603. 29466v2 Announce Type: replace-cross Abstract: Existing methods for quantifying predictive uncertainty in neural networks are either computationally intractable for large language models or require access to training data that is typically unavailable.

By Nils Gr\"unefeld, Jes Frellsen, Christian Hardmeier

llms nlp benchmarks

arXiv AI

Jun 30

When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning

arXiv:2601. 07965v2 Announce Type: replace Abstract: When a model knows when it does not know, many possibilities emerge.

By Chenjie Hao, Weyl Lu, Yuko Ishiwaka, Zengyi Li, Weier Wan, Yubei Chen

llms benchmarks

arXiv Machine Learning

Oct 3

Robust Evidential Learning Through Latent Consistency

The paper introduces CLEAR, a lightweight, task‑agnostic post‑hoc method that enhances evidential robustness in deep learning models without retraining. CLEAR uses held‑out calibration data to map the geometry of the model’s latent space, then generates perturbation views at inference to detect latent conflict. When high conflict is found, CLEAR selectively reduces evidential strength while preserving evidence for latent‑consistent inputs, achieving significant improvements in OOD and adversarial AUROC on ImageNet→CUB and running much faster than competing methods.

By Charmaine Barker, Daniel Bethell, Simos Gerasimou

diffusion computer-vision benchmarks safety

arXiv Machine Learning

Jun 30

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

arXiv:2606. 29951v1 Announce Type: new Abstract: Interpretable Mesomorphic Neural Networks (IMNs) offer a promising framework that combines the predictive power of deep neural networks with the interpretability of linear models.

By Hugo L. Hammer, Vajira Thambawita, Kristoffer Herland Hellton, P{\aa}l Halvorsen

benchmarks safety

arXiv AI

Jun 30

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

arXiv:2606. 28654v1 Announce Type: cross Abstract: Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods.

By Thiru Thillai Nadarasar Bahavan, Sachith Seneviratne, Saman Halgamuge

benchmarks

arXiv Machine Learning

Jul 23

Reading Calibrated Uncertainty from Language Model Trajectories

arXiv:2605. 22864v2 Announce Type: replace Abstract: The maximum softmax probability (MSP) represents a default approach when evaluating uncertainty quantification for language model generation with structured output.

By Aliai Eusebi, Alexander Herzog, Xiaoyu Liang, Marie Vasek, Enrico Mariconti, Lorenzo Cavallaro

llms

One email a morning, machine-written

Related stories

An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms

When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning

Robust Evidential Learning Through Latent Consistency

Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization

FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration

Reading Calibrated Uncertainty from Language Model Trajectories