arXiv AI July 16, 2026 By Shiqi Zhang, Marius Fai{\ss}, Ariana Strandburg-Peshkin, Tuomas Virtanen

Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning

arXiv:2607. 13555v1 Announce Type: cross Abstract: Bioacoustic call-type classification relies on costly expert annotation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 14

A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition

arXiv:2607. 09832v1 Announce Type: new Abstract: Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes.

By Juan Terven, Diana Margarita C\'ordova Esparza, Julio Alejandro Romero Gonzalez, Edgar Arturo Ch\'avez Urbiola, Francisco Javier Willars Rodriguez, Juan Bautista Hurtado Ramos, Alfonso Ramirez Pedraza

arXiv AI

Aug 5

One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning

arXiv:2608. 03249v1 Announce Type: new Abstract: Cold-Start Active Learning (CSAL) aims to select a valuable subset from an unlabeled pool without any prior knowledge or human assistance.

By Ning Zhu, Xiaochuan Ma, Juntao Xu, Jingze Liang, Mengfei Zhao, An Chen, Liang-Jian Deng

benchmarks safety

arXiv AI

Jun 29

iCost: A Novel Instance-Complexity-Based Cost-Sensitive Learning Framework

arXiv:2409. 13007v3 Announce Type: replace-cross Abstract: Class imbalance poses a significant challenge in classification tasks, often causing standard learning algorithms to become biased toward the majority class.

By Asif Newaz, Asif Ur Rahman Adib, Taskeed Jabid

safety

arXiv Machine Learning

5d ago

Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection

arXiv:2608. 12573v1 Announce Type: new Abstract: Top-k selection is a fundamental computational primitive with applications spanning databases, information retrieval, signal processing, and modern machine learning workloads, including sparse activations and attention pruning.

By Tadeusz Dziarmaga, Witold Sikora, {\L}ukasz Struski, Jacek Tabor, Marcin Mazur

efficiency safety

arXiv AI

Jul 16

Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification

arXiv:2607. 13571v1 Announce Type: cross Abstract: Sound event detection relies on frame-level strong labels whose annotation is expensive.

By Shiqi Zhang, Tuomas Virtanen

arXiv Machine Learning

Jul 3

Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning

arXiv:2607. 01474v1 Announce Type: new Abstract: Class imbalance poses a critical challenge in federated learning (FL), where underrepresented classes suffer from poor predictive performance yet cannot be addressed by standard centralized techniques due to privacy and heterogeneity constraints.

By Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan

reinforcement-learning benchmarks safety

Related stories

A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition

One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning

iCost: A Novel Instance-Complexity-Based Cost-Sensitive Learning Framework

Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection

Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification

Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning