Key papers

• Combining complex Langevin dynamics with score-based and energy-based diffusion models (2025)
  Gert Aarts et al.
  3.04
• On learning higher-order cumulants in diffusion models (2024)
  Gert Aarts et al.
  2.49
• Exponential Capacity in Multilayer Hetero-Associative Neural Networks (2026)
  Elena Agliari et al.
  1.94
• Escaping Mode Collapse in LLM Generation via Geometric Regulation (2026)
  Xin Du et al.
  1.83
• Diffusion Operator Geometry of Feedforward Representations (2026)
  Kanishka Reddy
  1.83
• The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models (2026)
  Flavio Nicoletti et al.
  1.83
• The critical slowing down in diffusion models (2026)
  Luca Maria Del Bono et al.
  1.83
• Memorisation, convergence and generalisation in generative models (2026)
  Antoine Maillard and Sebastian Goldt
  1.83
• Sampling Data with Chains of Forward-Backward Diffusion Steps (2026)
  Hyunmo Kang et al.
  1.83
• Biased Generalization in Diffusion Models (2026)
  Jerome Garnier-Brun et al.
  1.72
• A theory of learning data statistics in diffusion models, from easy to hard (2026)
  Lorenzo Bardone et al.
  1.72
• Interpreting the Synchronization Gap: The Hidden Mechanism Inside Diffusion Transformers (2026)
  Emil Albrychiewicz et al.
  1.72
• Emergence of Distortions in High-Dimensional Guided Diffusion Models (2026)
  Enrico Ventura et al.
  1.67
• Theory of Speciation Transitions in Diffusion Models with General Class Structure (2026)
  Beatrice Achilli and Marco Benedetti and Giulio Biroli and Marc M\'ezard
  1.67
• Dynamical Regimes of Multimodal Diffusion Models (2026)
  Emil Albrychiewicz et al.
  1.67
• Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks (2026)
  Ram\'on Nartallo-Kaluarachchi and Renaud Lambiotte and Alain Goriely
  1.67
• Fisher Information, Training and Bias in Fourier Regression Models (2025)
  Lorenzo Pastori et al.
  1.44
• A Generative Diffusion Model for Amorphous Materials (2025)
  Kai Yang et al.
  1.28
• Associative Memory and Generative Diffusion in the Zero-noise Limit (2025)
  Joshua Hess and Quaid Morris
  1.22
• Neural Langevin Machine: a local asymmetric learning rule can be creative (2025)
  Zhendong Yu and Weizhong Huang and Haiping Huang
  1.22
• Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training (2025)
  Tony Bonnaire et al.
  1.17
• Memorization to Generalization: Emergence of Diffusion Models from Associative Memory (2025)
  Bao Pham et al.
  1.17
• Generalization Dynamics of Linear Diffusion Models (2025)
  Claudia Merger and Sebastian Goldt
  1.17
• Generalization through variance: how noise shapes inductive biases in diffusion models (2025)
  John J. Vastola
  1.11
• Analysis of Diffusion Models for Manifold Data (2025)
  Anand Jerry George et al.
  1.00
• Generative diffusion for perceptron problems: statistical physics analysis and efficient algorithms (2025)
  Elizaveta Demyanenko et al.
  1.00
• A solvable model of learning generative diffusion: theory and insights (2025)
  Hugo Cui et al.
  0.94
• Generative diffusion model with inverse renormalization group flows (2025)
  Kanta Masuki and Yuto Ashida
  0.94
• Probing the Latent Hierarchical Structure of Data via Diffusion Models (2024)
  Antonio Sclocchi et al.
  0.89
• Nonequilbrium physics of generative diffusion models (2024)
  Zhendong Yu and Haiping Huang
  0.61
• A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data (2024)
  Antonio Sclocchi et al.
  —
• Discrete generative diffusion models without stochastic differential equations: a tensor network approach (2024)
  Luke Causer et al.
  —
• Non-equilibrium active noise enhances generative memory in diffusion models (2024)
  Agnish Kumar Behera et al.
  —
• The effect of priors on Learning with Restricted Boltzmann Machines (2024)
  Gianluca Manzan and Daniele Tantari
  —
• An analytic theory of creativity in convolutional diffusion models (2024)
  Mason Kamb et al.
  —