PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
hub
Journal of machine learning research , volume=
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 14roles
background 1polarities
background 1representative citing papers
A zero-shot machine learning decoder for handwriting BCIs achieves 64% hits@3 retrieval on unseen letters by exploiting conserved kinematic neural representations.
PULSE is a physics-informed plug-and-play framework that uses phase-anchored disentanglement, a Phase Router, and statistic-aware mixup to mitigate Phase Amnesia in non-stationary forecasting and achieve strong results with simple backbones.
FastUMAP speeds up UMAP by 15x on 70k-point datasets via bipartite landmark sampling and Nystrom initialization while retaining 96% of the kNN accuracy of stronger baselines.
PAMod models cyclical distribution shifts in non-stationary time series via phase-amplitude modulation in normalized space, proving equivalence to dynamic denormalization and achieving SOTA on twelve benchmarks.
CleanBase identifies malicious documents in RAG databases by detecting cliques in a semantic similarity graph constructed using embedding models and a statistical threshold.
Dual-Glob applies supervised contrastive learning to classify fine-grained pitch accent patterns from F0 contours in Seoul Korean, achieving 77.75% accuracy and 51.54% F1 on a new dataset of 10,093 manually annotated accentual phrases.
TabTransformer uses Transformer self-attention to generate contextual embeddings from categorical features in tabular data, outperforming prior deep learning methods by at least 1% mean AUC and matching tree-based ensembles on 15 public datasets while showing robustness to missing and noisy features
A generative framework using geometric diffusion for brain networks and tabular diffusion for other organs integrates ICD-coded SDoH proxies to improve disease reasoning on UK Biobank data.
SCGFM creates transferable graph representations by aligning heterogeneous topologies to shared learnable geometric bases via Gromov-Wasserstein distances and re-encoding features accordingly.
Annotation disagreement on toxic language can be moderately predicted from textual features, with high-opposition items proving harder for models to estimate accurately.
Hyperparameter-optimized generative models augment scarce flight diversion records and substantially improve prediction accuracy over real data alone.
Socio-Contrastive Learning jointly learns socio-demographic representations and textual features via contrastive objectives to predict annotator perspectives more accurately than concatenation baselines.
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.
citing papers explorer
-
What Makes a Representation Good for Single-Cell Perturbation Prediction?
PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
-
Conserved Kinematic Representations enable Zero-Shot Decoding in Handwriting BCIs
A zero-shot machine learning decoder for handwriting BCIs achieves 64% hits@3 retrieval on unseen letters by exploiting conserved kinematic neural representations.
-
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
PULSE is a physics-informed plug-and-play framework that uses phase-anchored disentanglement, a Phase Router, and statistic-aware mixup to mitigate Phase Amnesia in non-stationary forecasting and achieve strong results with simple backbones.
-
FastUMAP: Scalable Dimensionality Reduction via Bipartite Landmark Sampling
FastUMAP speeds up UMAP by 15x on 70k-point datasets via bipartite landmark sampling and Nystrom initialization while retaining 96% of the kNN accuracy of stronger baselines.
-
PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting
PAMod models cyclical distribution shifts in non-stationary time series via phase-amplitude modulation in normalized space, proving equivalence to dynamic denormalization and achieving SOTA on twelve benchmarks.
-
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
CleanBase identifies malicious documents in RAG databases by detecting cliques in a semantic similarity graph constructed using embedding models and a statistical threshold.
-
Deep Supervised Contrastive Learning of Pitch Contours for Robust Pitch Accent Classification in Seoul Korean
Dual-Glob applies supervised contrastive learning to classify fine-grained pitch accent patterns from F0 contours in Seoul Korean, achieving 77.75% accuracy and 51.54% F1 on a new dataset of 10,093 manually annotated accentual phrases.
-
TabTransformer: Tabular Data Modeling Using Contextual Embeddings
TabTransformer uses Transformer self-attention to generate contextual embeddings from categorical features in tabular data, outperforming prior deep learning methods by at least 1% mean AUC and matching tree-based ensembles on 15 public datasets while showing robustness to missing and noisy features
-
Marrying Generative Model of Healthcare Events with Digital Twin of Social Determinants of Health for Disease Reasoning
A generative framework using geometric diffusion for brain networks and tabular diffusion for other organs integrates ICD-coded SDoH proxies to improve disease reasoning on UK Biobank data.
-
Structure-Centric Graph Foundation Model via Geometric Bases
SCGFM creates transferable graph representations by aligning heterogeneous topologies to shared learnable geometric bases via Gromov-Wasserstein distances and re-encoding features accordingly.
-
Quantifying and Predicting Disagreement in Graded Human Ratings
Annotation disagreement on toxic language can be moderately predicted from textual features, with high-opposition items proving harder for models to estimate accurately.
-
Generative Augmentation of Imbalanced Flight Records for Flight Diversion Prediction: A Multi-objective Optimisation Framework
Hyperparameter-optimized generative models augment scarce flight diversion records and substantially improve prediction accuracy over real data alone.
-
Modeling Human Perspectives with Socio-Demographic Representations
Socio-Contrastive Learning jointly learns socio-demographic representations and textual features via contrastive objectives to predict annotator perspectives more accurately than concatenation baselines.
-
Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.