Search Results for author:
Found 22 papers, 8 papers with code
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
In this paper, we propose Direct Unlearning Optimization (DUO), a novel framework for removing Not Safe For Work (NSFW) content from T2I models while preserving their performance on unrelated topics.
Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment
Identifying the relevant input features that have a critical influence on the output results is indispensable for the development of explainable artificial intelligence (XAI).
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Upsample Guidance: Scale Up Diffusion Models without Training
We demonstrate that upsample guidance can be applied to various models, such as pixel-space, latent space, and video diffusion models.
Resolution Chromatography of Diffusion Models
In this paper, we introduce "resolution chromatography" that indicates the signal generation rate of each resolution, which is very helpful concept to mathematically explain this coarse-to-fine behavior in generation process, to understand the role of noise schedule, and to design time-dependent modulation.
GNRK: Graph Neural Runge-Kutta method for solving partial differential equations
Neural networks have proven to be efficient surrogate models for tackling partial differential equations (PDEs).
Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry
Remarkably, our discovered local latent basis enables image editing capabilities by moving $\mathbf{x}_t$, the latent space of DMs, along the basis vector at specific timesteps.
Tradeoff of generalization error in unsupervised learning
In this study, we propose that unsupervised learning generally exhibits a two-component tradeoff of the GE, namely the model error and the data error -- using a more complex model reduces the model error at the cost of the data error, with the data error playing a more significant role for a smaller training dataset.
Unsupervised Discovery of Semantic Latent Directions in Diffusion Models
Despite the success of diffusion models (DMs), we still lack a thorough understanding of their latent space.
Mirror descent of Hopfield model
Mirror descent is an elegant optimization technique that leverages a dual space of parametric models to perform gradient descent.
Scale-invariant representation of machine learning
We observe that the frequency of internal codes or labels follows power laws in both supervised and unsupervised learning models.
Information flows of diverse autoencoders
Thus, we conclude that the compression phase is not necessary for generalization in representation learning.
Inference of stochastic time series with missing data
At the initial iteration of the EM algorithm, the model inference shows better model-data consistency with observed data points than with missing data points.
Tractable loss function and color image generation of multinary restricted Boltzmann machine
The restricted Boltzmann machine (RBM) is a representative generative model based on the concept of statistical mechanics.
Machine learning for the diagnosis of early stage diabetes using temporal glucose profiles
Here we apply the machine learning (ML) for the diagnosis of early stage diabetes, which is known as a challenging task in medicine.
Inverse Ising inference from high-temperature re-weighting of observations
Maximum Likelihood Estimation (MLE) is the bread and butter of system inference for stochastic systems.
Data-driven inference of hidden nodes in networks
Finally, an important hidden variable problem is to find the number of clusters in a dataset.
Data Analysis, Statistics and Probability Physics and Society
Immunological recognition by artificial neural networks
To address this problem, we examine whether the affinity-based discrimination of peptide sequences is learnable and generalizable by artificial neural networks (ANNs) that process the digital experimental amino acid sequence information of receptors and peptides.
Broad cross-reactivity of the T-cell repertoire achieves specific and sufficiently rapid target searching
We examine sequences of 10, 000 human T-cell receptors and 10, 000 antigenic peptides, and obtain a full spectrum of cross-reactivity of the receptor-peptide binding.
Resolution and Relevance Trade-offs in Deep Learning
The fraction of inputs that are associated to the same state is a natural measure of similarity and is simply related to the cost in bits required to represent these inputs.
Causality inference in stochastic systems from neurons to currencies: Profiting from small sample size
We introduce a data-driven statistical physics approach to model inference based on minimizing a free energy of data and show superior model recovery for small sample sizes.
Data Analysis, Statistics and Probability Quantitative Methods
A Local Counter-Regulatory Motif Modulates the Global Phase of Hormonal Oscillations
By testing all possible motifs governing the interactions of these three cell types, we found that a unique set of positive/negative intra-islet interactions between different islet cell types functions not only to reduce the superficially wasteful zero-sum action of glucagon and insulin but also to enhance/suppress the synchronization of hormone secretions between islets under high/normal glucose conditions.
Minimal Perceptrons for Memorizing Complex Patterns
We developed a new complexity measure of binary patterns, and estimated the minimal network size for memorizing them as a function of their complexity.
