Picture for Tony Chiang

Tony Chiang

Token embeddings violate the manifold hypothesis

Add code
Apr 01, 2025
Figure 1 for Token embeddings violate the manifold hypothesis
Figure 2 for Token embeddings violate the manifold hypothesis
Figure 3 for Token embeddings violate the manifold hypothesis
Figure 4 for Token embeddings violate the manifold hypothesis
Viaarxiv icon

Assessing Generative Models for Structured Data

Add code
Mar 26, 2025
Figure 1 for Assessing Generative Models for Structured Data
Figure 2 for Assessing Generative Models for Structured Data
Figure 3 for Assessing Generative Models for Structured Data
Figure 4 for Assessing Generative Models for Structured Data
Viaarxiv icon

Understanding Generative AI Content with Embedding Models

Add code
Aug 19, 2024
Viaarxiv icon

Measuring model variability using robust non-parametric testing

Add code
Jun 12, 2024
Figure 1 for Measuring model variability using robust non-parametric testing
Figure 2 for Measuring model variability using robust non-parametric testing
Figure 3 for Measuring model variability using robust non-parametric testing
Figure 4 for Measuring model variability using robust non-parametric testing
Viaarxiv icon

Efficient kernel surrogates for neural network-based regression

Add code
Oct 28, 2023
Figure 1 for Efficient kernel surrogates for neural network-based regression
Figure 2 for Efficient kernel surrogates for neural network-based regression
Figure 3 for Efficient kernel surrogates for neural network-based regression
Figure 4 for Efficient kernel surrogates for neural network-based regression
Viaarxiv icon

Foundation Model's Embedded Representations May Detect Distribution Shift

Add code
Oct 20, 2023
Figure 1 for Foundation Model's Embedded Representations May Detect Distribution Shift
Figure 2 for Foundation Model's Embedded Representations May Detect Distribution Shift
Figure 3 for Foundation Model's Embedded Representations May Detect Distribution Shift
Figure 4 for Foundation Model's Embedded Representations May Detect Distribution Shift
Viaarxiv icon

Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks

Add code
Oct 01, 2023
Figure 1 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks
Figure 2 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks
Figure 3 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks
Figure 4 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks
Viaarxiv icon

Exploring Learned Representations of Neural Networks with Principal Component Analysis

Add code
Sep 27, 2023
Viaarxiv icon

Robust Explanations for Deep Neural Networks via Pseudo Neural Tangent Kernel Surrogate Models

Add code
May 23, 2023
Figure 1 for Robust Explanations for Deep Neural Networks via Pseudo Neural Tangent Kernel Surrogate Models
Figure 2 for Robust Explanations for Deep Neural Networks via Pseudo Neural Tangent Kernel Surrogate Models
Figure 3 for Robust Explanations for Deep Neural Networks via Pseudo Neural Tangent Kernel Surrogate Models
Figure 4 for Robust Explanations for Deep Neural Networks via Pseudo Neural Tangent Kernel Surrogate Models
Viaarxiv icon

Spectral evolution and invariance in linear-width neural networks

Add code
Nov 11, 2022
Figure 1 for Spectral evolution and invariance in linear-width neural networks
Figure 2 for Spectral evolution and invariance in linear-width neural networks
Figure 3 for Spectral evolution and invariance in linear-width neural networks
Figure 4 for Spectral evolution and invariance in linear-width neural networks
Viaarxiv icon