DOHF: Online Diffusion Fine-tuning with Doob's h-transform Guidance
cs.LG, cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- Understanding Sampler Stochasticity in Training Diffusion Models for RLHF
- Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review
- DanceGRPO: Unleashing GRPO on Visual Generation
- Scores as Actions: a framework of fine-tuning diffusion models by continuous-time reinforcement learning
- DiffusionNFT: Online Diffusion Reinforcement with Forward Process
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks