discrete diffusion models
Generative models that simulate the process of diffusion in a discrete data space, often used to create or reconstruct data samples through iterative refinement techniques.
- Constrained Discrete Diffusion
- Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-based Decoding
- Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
- Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
- Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms
- Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
- Information-Theoretic Discrete Diffusion
- LaViDa: A Large Diffusion Model for Vision-Language Understanding
- Learnable Sampler Distillation for Discrete Diffusion Models
- Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
- Non-Markovian Discrete Diffusion with Causal Language Models
- Reinforced Context Order Recovery for Adaptive Reasoning and Planning
- Split Gibbs Discrete Diffusion Posterior Sampling
- Steering Generative Models with Experimental Data for Protein Fitness Optimization
- Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion