Count-FM is a new flow-matching method for count data based on birth-death processes that achieves better sample quality with fewer parameters than baselines on simulations and real scRNA-seq and spike-train data.
Cole, Michael I
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
MEDAL distills manifold embeddings into autoencoders to enable out-of-sample extension and held-out validation of dimension reduction methods.
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
Sparse autoencoders resolve superposition in image-based neural representations of neurons, recovering metric geometry and enabling de novo cross-modal alignment to scRNA-seq via Gromov-Wasserstein transport.
A GMM-based embedding remix technique generates augmented patients for data-scarce medical MIL, improving performance in missing-class and low-data regimes.
scHelix uses explicit gene-level partitioning into Anchors and Variants plus an asymmetric Align-Refine-Fuse dual-stream architecture to improve batch correction in scRNA-seq without over-correcting biological signals.
Donor-aware benchmarks show AUROCs up to 0.978 for IBD classification from scRNA-seq using CLR cell-type compositions and GatedStructuralCFN embeddings, with compartment stratification improving both performance and feature stability.
citing papers explorer
-
Flow Matching for Count Data
Count-FM is a new flow-matching method for count data based on birth-death processes that achieves better sample quality with fewer parameters than baselines on simulations and real scRNA-seq and spike-train data.
-
MEDAL: Manifold Embedding Distillation via Autoencoder Learning
MEDAL distills manifold embeddings into autoencoders to enable out-of-sample extension and held-out validation of dimension reduction methods.
-
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
-
Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images
Sparse autoencoders resolve superposition in image-based neural representations of neurons, recovering metric geometry and enabling de novo cross-modal alignment to scRNA-seq via Gromov-Wasserstein transport.
-
Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning
A GMM-based embedding remix technique generates augmented patients for data-scarce medical MIL, improving performance in missing-class and low-data regimes.
-
scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement
scHelix uses explicit gene-level partitioning into Anchors and Variants plus an asymmetric Align-Refine-Fuse dual-stream architecture to improve batch correction in scRNA-seq without over-correcting biological signals.
-
Donor-Aware scRNA-seq Benchmarks for IBD Classification
Donor-aware benchmarks show AUROCs up to 0.978 for IBD classification from scRNA-seq using CLR cell-type compositions and GatedStructuralCFN embeddings, with compartment stratification improving both performance and feature stability.