Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew
cs.LG, cs.AI, stat.ML
Submitted: 2026-05-18
Updated: 2026-10-13
Comments: Accepted at NeurIPS26; 21 pages, 5 figures, 9 tables (includes appendix)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems
- The Principles of Diffusion Models
- Nonparametric Data Attribution for Diffusion Models
- Ablation Based Counterfactuals
- Distributional Training Data Attribution: What do Influence Functions Sample?
- Fast Data Attribution for Text-to-Image Models
- ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
- LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
- The ArtBench Dataset: Benchmarking Generative Models with Artworks
- Revisiting Methods for Finding Influential Examples
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