Jumping up and down: Denoiser diffusion models for discrete ordinal data
cs.LG, stat.ME
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- RecFusion: A Binomial Diffusion Process for 1D Data for Recommendation
- Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
- Variable-Length Generative Protein Design via Generalized Poisson Flow
- Language Modeling with Hyperspherical Flows
- ELF: Embedded Language Flows
- Blind denoising diffusion models and the blessings of dimensionality
- Sampling, Diffusions, and Stochastic Localization
- Unlocking Guidance for Discrete State-Space Diffusion and Flow Models
- Binomial flows: Denoising and flow matching for discrete ordinal data
- ScDiVa: Masked Discrete Diffusion for Joint Modeling of Single-Cell Identity and Expression
- Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
- Stochastic Flow Map for Count Data
- Flow Matching for Count Data
- Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models
- Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
- Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
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