Hugging Face Trending Papers June 11, 2026

Distributional Loss for Robust Classification

Read the original on Hugging Face Trending Papers →

This paper proposes a novel loss concept for supervised classification tasks. Rather than enforcing a direct mapping from each input sample to a single assigned label, we define an optimization objective over all classifier outputs as a bimodal Gaussian distribution.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jul 21

Robust Losses from Univariate Base Functions for Noisy-Label Learning

arXiv:2607. 16768v1 Announce Type: new Abstract: Learning with noisy labels is a fundamental problem in training reliable deep neural networks.

By Peng Hu, Jianwei Ma

benchmarks

arXiv Machine Learning

Jul 31

Distributions In, Distributions Out: The Case for Soft-Label Training

arXiv:2511. 14117v2 Announce Type: replace Abstract: Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotators into a majority vote.

By Agamdeep Singh, Ashish Tiwari, Hosein Hasanbeig, Priyanshu Gupta

nlp

arXiv Machine Learning

Jul 9

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

arXiv:2607. 06637v1 Announce Type: new Abstract: In this work, we propose a unified approach for diagnosing misclassification and assessing the robustness of black-box classifiers.

By Evgenii Kuriabov, David Miller, Jia Li

safety

arXiv AI

Jun 11

Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning

arXiv:2602. 08986v2 Announce Type: replace-cross Abstract: In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications.

By Isaac Xu, Martin Gillis, Ayushi Sharma, Benjamin Misiuk, Craig J. Brown, Thomas Trappenberg

benchmarks

arXiv Machine Learning

Aug 4

Benign Overfitting in Linear Classifiers with a Bias Term

arXiv:2511. 12840v2 Announce Type: replace-cross Abstract: Overparameterized models often generalize well even when they interpolate noisy training data.

By Yuta Kondo

safety

arXiv AI

Jul 15

Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite

arXiv:2607. 11947v1 Announce Type: cross Abstract: Typical semi-supervised learning (SSL) methods rely on distributional assumptions, and their performance degrades when these are violated.

By Yushi Hirose, Hiroo Irobe, Takafumi Kanamori

benchmarks

Related stories

Robust Losses from Univariate Base Functions for Noisy-Label Learning

Distributions In, Distributions Out: The Case for Soft-Label Training

Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers

Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning

Benign Overfitting in Linear Classifiers with a Bias Term

Generalized Distribution-Free Semi-Supervised Learning with Risk Rewrite