arXiv:2608. 00632v1 Announce Type: new Abstract: Modern machine learning pipelines increasingly rely on reusing pretrained and foundation models across downstream tasks.
arXiv:2601. 11670v3 Announce Type: replace-cross Abstract: Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance.
arXiv:2608. 12100v1 Announce Type: cross Abstract: In high-stakes applications, reliable confidence estimates are as important as the predictions themselves.
arXiv:2608. 12035v1 Announce Type: cross Abstract: Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship.
arXiv:2606. 20115v1 Announce Type: new Abstract: Conformal risk control (CRC) provides distribution-free guarantees on segmentation quality by calibrating a prediction-set threshold on held-out data.
The paper introduces a label‑free method called AURCC for selecting the best foundational model for medical image classification when the target domain lacks labels. AURCC uses a pseudo‑label discrepancy computed by the SUDO framework to score models without fine‑tuning. Experiments on chest X‑ray data across three inter‑hospital shifts show that AURCC closely matches the true model ranking, outperforming simple source‑accuracy baselines especially when source data are limited.
arXiv:2511. 22823v2 Announce Type: replace-cross Abstract: Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire.
arXiv:2607. 16675v1 Announce Type: cross Abstract: A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its use in downstream decision-making.
arXiv:2602. 14913v2 Announce Type: replace Abstract: Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts.
arXiv:2505. 08784v2 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety.
arXiv:2607. 28125v2 Announce Type: replace-cross Abstract: Numerous unsupervised domain adaptation (UDA) algorithms exist, but for clinical practice, selecting the best-suited one along with proper hyperparameters often remains unclear, as the unlabeled deployment (target) domain prevents direct evaluation.
arXiv:2606. 28598v1 Announce Type: cross Abstract: Prediction sets should have high coverage to be useful, but some coverage notions are more practically relevant than others.