Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
hub
In search of lost domain generalization
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 1
citation-polarity summary
representative citing papers
Conditional computational barrier exists for learning k=1 invariant subspaces in samplable multi-environment instances under sparse recovery hardness; minimax risk is Theta(k(d-k)/(n|E|)) with phase transition at n* ~ k(d-k)/(|E| gamma^2).
Behavioral INR adapts INRs to behavior by mapping states to actions with FiLM-modulated episode latents for self-supervised policy inference in unlabeled data, with new policy OOD definitions.
FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.
GS-DIFF detects changes in 3D Gaussian Splatting scenes by direct primitive attribute comparison with anisotropic drift models and observability terms, outperforming render-then-compare baselines by ~17% mIoU.
A large-scale benchmark finds that recent multimodal domain generalization methods give only marginal gains over a plain ERM baseline, with no method winning consistently and all degrading sharply under corruption or missing modalities.
A cross-population framework for EEG Parkinson's detection using exhaustive 75 directional evaluations and nested validation shows asymmetric transfer and accuracy up to 94.1% when training diversity increases, supported by mixture risk theory.
Inter-laboratory measurement variance dominates the generalization gap in PROTAC activity prediction, capping LOTO AUROC near 0.67 across models and architectures.
TabICL scales in-context learning to large tabular data via column-then-row attention for row embeddings followed by a transformer, matching TabPFNv2 speed and performance while outperforming it and CatBoost on datasets over 10K samples.
FGMix learns instance weights via gradient compatibilities to perform mixup with extrapolation toward flatter minima, outperforming prior DG methods on DomainBed.
MEDIC uses dualistic meta-learning with joint domain-class matching to balance decision boundaries in open set domain generalization.
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
Domain generalization via gradient reversal on the BreaKHis dataset produces magnification-invariant histopathology classifiers with three-fold smaller sparse embeddings and near-perfect cross-magnification signature reproducibility.
A cross-machine anomaly detection framework disentangles MOMENT embeddings using random forests to create machine-invariant condition features that improve generalization to unseen machines on industrial data.
citing papers explorer
-
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
-
Is Spurious Correlation Removal Always Learnable?
Conditional computational barrier exists for learning k=1 invariant subspaces in samplable multi-environment instances under sparse recovery hardness; minimax risk is Theta(k(d-k)/(n|E|)) with phase transition at n* ~ k(d-k)/(|E| gamma^2).
-
Implicit Neural Representations of Individual Behavior
Behavioral INR adapts INRs to behavior by mapping states to actions with FiLM-modulated episode latents for self-supervised policy inference in unlabeled data, with new policy OOD definitions.
-
FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.
-
From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting
GS-DIFF detects changes in 3D Gaussian Splatting scenes by direct primitive attribute comparison with anisotropic drift models and observability terms, outperforming render-then-compare baselines by ~17% mIoU.
-
Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
A large-scale benchmark finds that recent multimodal domain generalization methods give only marginal gains over a plain ERM baseline, with no method winning consistently and all degrading sharply under corruption or missing modalities.
-
Robust and Clinically Reliable EEG Biomarkers: A Cross Population Framework for Generalizable Parkinson's Disease Detection
A cross-population framework for EEG Parkinson's detection using exhaustive 75 directional evaluations and nested validation shows asymmetric transfer and accuracy up to 94.1% when training diversity increases, supported by mixture risk theory.
-
Decomposing the Generalization Gap in PROTAC Activity Prediction: Variance Attribution and the Inter-Laboratory Ceiling
Inter-laboratory measurement variance dominates the generalization gap in PROTAC activity prediction, capping LOTO AUROC near 0.67 across models and architectures.
-
TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
TabICL scales in-context learning to large tabular data via column-then-row attention for row embeddings followed by a transformer, matching TabPFNv2 speed and performance while outperforming it and CatBoost on datasets over 10K samples.
-
Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization
FGMix learns instance weights via gradient compatibilities to perform mixup with extrapolation toward flatter minima, outperforming prior DG methods on DomainBed.
-
Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios
MEDIC uses dualistic meta-learning with joint domain-class matching to balance decision boundaries in open set domain generalization.
-
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
-
Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures
Domain generalization via gradient reversal on the BreaKHis dataset produces magnification-invariant histopathology classifiers with three-fold smaller sparse embeddings and near-perfect cross-magnification signature reproducibility.
-
Cross-Machine Anomaly Detection Leveraging Pre-trained Time-series Model
A cross-machine anomaly detection framework disentangles MOMENT embeddings using random forests to create machine-invariant condition features that improve generalization to unseen machines on industrial data.