Decoupled PFNs use controllable synthetic priors to train separate latent-signal and noise heads, making epistemic-aleatoric decomposition identifiable and improving acquisition in noisy settings.
Advances in neural information processing systems , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
DoTS decouples SFT and RLVR training then synthesizes their task vectors at inference time to match integrated training results at ~3% compute cost.
On five tabular security datasets at 10% labels, tuning only the classifier with Bayesian optimization recovers a median 86% of the gains from full joint SSL-classifier optimization.
citing papers explorer
-
Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors
Decoupled PFNs use controllable synthetic priors to train separate latent-signal and noise heads, making epistemic-aleatoric decomposition identifiable and improving acquisition in noisy settings.
-
Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors
DoTS decouples SFT and RLVR training then synthesizes their task vectors at inference time to match integrated training results at ~3% compute cost.
-
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
On five tabular security datasets at 10% labels, tuning only the classifier with Bayesian optimization recovers a median 86% of the gains from full joint SSL-classifier optimization.