IDRF: Inverse-Distilled Reward Fine-tuning of Masked Discrete Diffusion Models

arXiv:2610.03641 · cs.LG · Submitted 2026-10-02 · Read on arXiv

cs.LG

Submitted: 2026-10-02

Updated: 2026-10-02

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 1× in this paper · explained in 9 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes

Sources

• Preference-Based Alignment of Discrete Diffusion Models
• Discrete Tilt Matching
• Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
• Categorical Reparameterization with Denoising Diffusion models
• Classifier-Free Diffusion Guidance
• Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD
• Reinforcing Few-step Generators via Reward-Tilted Distribution Matching
• TUBE: Tangent Upper Bound on Evidence for Discrete Diffusion Language Models
• Distribution Matching Distillation Meets Reinforcement Learning
• IDLM: Inverse-distilled Diffusion Language Models
• Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences
• Unlocking Guidance for Discrete State-Space Diffusion and Flow Models
• Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
• Simple and Effective Masked Diffusion Language Models
• The Diffusion Duality
• Proximal Policy Optimization Algorithms
• Simplified and Generalized Masked Diffusion for Discrete Data
• wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
• Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
• SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

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