iADD: Improving Alignment and Diversity in Diffusion Policy Optimization
cs.LG, cs.AI
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/Saugat2002/iADD
Project page: https://saugat2002.github.io/iadd
Terminology
Sources
- Hindsight Experience Replay
- Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning
- Training Diffusion Models with Reinforcement Learning
- Directly Fine-Tuning Diffusion Models on Differentiable Rewards
- Convergence of denoising diffusion models under the manifold hypothesis
- 3D-FUTURE: 3D Furniture shape with TextURE
- Inferring Compositional 4D Scenes without Ever Seeing One
- Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
- Dealing with Sparse Rewards in Reinforcement Learning
- Gaussian Error Linear Units (GELUs)
- Imagen Video: High Definition Video Generation with Diffusion Models
- Video Diffusion Models
- Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping
- Rethinking Direct Preference Optimization in Diffusion Models
- Self-Supervised Online Reward Shaping in Sparse-Reward Environments
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
- Data-Efficient Hierarchical Reinforcement Learning
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- Steerable Scene Generation with Post Training and Inference-Time Search
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
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