Conservation Laws for Diffusion Models

arXiv:2607.10067 · cs.LG, cs.IT, stat.ML · Submitted 2026-07-11 · Read on arXiv

Ziv Aharoni, Henry D. Pfister

cs.LG, cs.IT, stat.ML

Submitted: 2026-07-11

Code: https://github.com/zivaharoni/conservation-laws-diffusion-models

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

Terminology

• Diffusion Model — 20× in this paper · explained in 10 episodes
• Diffusion Models — 17× in this paper · explained in 9 episodes
• Transformer — 11× in this paper · explained in 2 episodes
• Conservation Laws — 9× in this paper · explained in 3 episodes
• Transformers — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Mutual Information — 3× in this paper · explained in 2 episodes
• Parameterization — 3× in this paper · explained in 2 episodes
• Score Function — 3× in this paper · explained in 4 episodes
• Weight Decay — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 3 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Inception Score — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• Absorb — 1× in this paper · explained in 1 episode
• Concatenated codes — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decoder — 1× in this paper · explained in 2 episodes
• Discrete Diffusion Model — 1× in this paper · explained in 2 episodes
• Hyperparameters — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Neural Network Approximation — 1× in this paper · explained in 2 episodes
• Papers — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Signal-to-Noise Ratio (SNR) — 1× in this paper · explained in 6 episodes
• Training Objective — 1× in this paper · explained in 3 episodes
• Transformer Architecture — 1× in this paper · explained in 4 episodes
• Unsupervised Learning — 1× in this paper · explained in 2 episodes

Sources

• WaveNet: A Generative Model for Raw Audio
• Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion
• Simplified and Generalized Masked Diffusion for Discrete Data

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