Prototype Guided Post-pretraining for Single-Cell Representation Learning

arXiv:2605.07938 · cs.LG · Submitted 2026-05-08 · Read on arXiv

cs.LG

Submitted: 2026-05-08

Updated: 2026-09-29

Terminology

• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Computational Biology — 1× in this paper · explained in 2 episodes
• Covariate Shift — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes

Sources

• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Decoupling Representation and Classifier for Long-Tailed Recognition
• Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT
• Long-tail learning via logit adjustment
• REFINEPPO: Learning Continuous Control Policies by Iterative Action Refinement
• LangCell: Language-Cell Pre-training for Cell Identity Understanding

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks