Closed-Form Diffusion Policies enable training-free imitation learning by using closed-form scores derived from demonstration data, achieving competitive benchmark performance with millisecond inference and composable editing of pre-trained policies.
hub
An analytic theory of creativity in convolutional diffusion models
15 Pith papers cite this work, alongside 4 external citations. Polarity classification is still indexing.
15
Pith papers citing it
4
external citations · external index
hub tools
representative citing papers
Symmetry breaking and nonlocality phase transitions occur nearly simultaneously during diffusion model generation in modern transformers.
A minimal embedding model shows representation collapse arises from frustrated samples through slow dynamics and is prevented by stop-gradient.
Presents SimA, a score-based single-query membership inference attack for diffusion models and LDMs that uses denoiser output norm to reveal training set proximity and outperforms multi-query baselines on eight datasets.
Analytic solution of full-batch gradient flow for linear and convolutional denoisers in diffusion models yields a universal inverse-variance spectral law for learning times of eigenmodes.
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
Flow-Direct constructs a reusable non-parametric guidance field from the log-density ratio of base and target distributions using all accumulated reward samples for feedback-efficient guidance in flow models.
Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
Uniform-based discrete diffusion models behave as associative memories that retrieve unseen data, with a dataset-size-driven memorization-to-generalization transition detectable via conditional entropy of token predictions.
LLMs show strong spatial generalization to unseen maps in shortest-path tasks but fail length scaling due to recursive instability, with data coverage setting hard limits.
Diffusion models overfit denoising loss at intermediate noise but generalize in inference as model error smooths the flow field and sampling paths avoid memorized noisy training data.
In an asymmetric visible-hidden Markov-chain generative model, likelihood-type training spontaneously produces nonequilibrium latent cycles, and models with stronger cycles reproduce digit-class frequencies more faithfully.
The paper introduces a phase framework for data distributions connected by local denoisers and demonstrates that reverse diffusion consists of trivial and data phases separated by a transition where local score functions must fail, tied to spatial Markovianity.
The book presents principles from optimization and information theory to explain deep network architectures and enable new interpretable models.
citing papers explorer
-
Training-Free Imitation Learning with Closed-Form Diffusion Policies
Closed-Form Diffusion Policies enable training-free imitation learning by using closed-form scores derived from demonstration data, achieving competitive benchmark performance with millisecond inference and composable editing of pre-trained policies.
-
Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
Symmetry breaking and nonlocality phase transitions occur nearly simultaneously during diffusion model generation in modern transformers.
-
A Minimal Model of Representation Collapse: Frustration, Stop-Gradient, and Dynamics
A minimal embedding model shows representation collapse arises from frustrated samples through slow dynamics and is prevented by stop-gradient.
-
Score-based Membership Inference on Diffusion Models
Presents SimA, a score-based single-query membership inference attack for diffusion models and LDMs that uses denoiser output norm to reveal training set proximity and outperforms multi-query baselines on eight datasets.
-
An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
Analytic solution of full-batch gradient flow for linear and convolutional denoisers in diffusion models yields a universal inverse-variance spectral law for learning times of eigenmodes.
-
Unsupervised Causal Abstractions Discovery
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
-
Mechanisms of Misgeneralization in Physical Sequence Modeling
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
-
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
Flow-Direct constructs a reusable non-parametric guidance field from the log-density ratio of base and target distributions using all accumulated reward samples for feedback-efficient guidance in flow models.
-
When Do Diffusion Models learn to Generate Multiple Objects?
Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
-
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Uniform-based discrete diffusion models behave as associative memories that retrieve unseen data, with a dataset-size-driven memorization-to-generalization transition detectable via conditional entropy of token predictions.
-
Generalization in LLM Problem Solving: The Case of the Shortest Path
LLMs show strong spatial generalization to unseen maps in shortest-path tasks but fail length scaling due to recursive instability, with data coverage setting hard limits.
-
Diffusion Models Memorize in Training -- and Generalize in Inference
Diffusion models overfit denoising loss at intermediate noise but generalize in inference as model error smooths the flow field and sampling paths avoid memorized noisy training data.
-
Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
In an asymmetric visible-hidden Markov-chain generative model, likelihood-type training spontaneously produces nonequilibrium latent cycles, and models with stronger cycles reproduce digit-class frequencies more faithfully.
-
Local Diffusion Models and Phases of Data Distributions
The paper introduces a phase framework for data distributions connected by local denoisers and demonstrates that reverse diffusion consists of trivial and data phases separated by a transition where local score functions must fail, tied to spatial Markovianity.
-
Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory
The book presents principles from optimization and information theory to explain deep network architectures and enable new interpretable models.