C NL: Collapse-Based Active Neural Learning with Objective-Aligned Representation Control

cs.LG, cs.CV

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: Code and numerical reproduction: https://github.com/alqithami/CANL

Code: https://github.com/alqithami/CANL

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• A Geometric Analysis of Neural Collapse with Unconstrained Features
• Neural collapse in the orthoplex regime
• Active Learning Using Aggregated Acquisition Functions: Accuracy and Sustainability Analysis
• Labeled TrustSet Guided: Batch Active Learning with Reinforcement Learning
• On the Robustness of Neural Collapse and the Neural Collapse of Robustness
• Denoising Diffusion Probabilistic Models
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Demystifying MMD GANs

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks