arXiv AI
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 14
ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning
arXiv:2608. 13190v1 Announce Type: new Abstract: Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable.
Hugging Face Trending Papers
Jun 21
Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation
Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupted inputs also destabilize online updates. We study robust test-time adaptation (RTTA) in the adversarial-stream setting, which remains comparatively underexplored relative to standard TTA, and propose SAFER (Stochastic Augmentation Framework for Enhanced Robustness), a training-free reliability-guided augmentation wrapper for RTTA.
arXiv Machine Learning
Aug 11
ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning
arXiv:2608. 09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken.
arXiv Machine Learning
Aug 6
Robustness Emerges Early in Training Dynamics, but Is Not Preserved
arXiv:2608. 04442v1 Announce Type: new Abstract: Robustness to natural corruptions remains a fundamental challenge for deep neural networks.
arXiv Machine Learning
Sep 16
Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
arXiv:2609.16380v1 Announce Type: new Abstract: Class-balanced learning and label noise create a coupled failure mode: frequency correction prevents majority classes from dominating the decision rule...
arXiv AI
Aug 17
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.