Picture for Alexander Ku

Alexander Ku

Using the Tools of Cognitive Science to Understand Large Language Models at Different Levels of Analysis

Add code
Mar 17, 2025
Viaarxiv icon

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem

Add code
Oct 31, 2024
Figure 1 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Figure 2 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Figure 3 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Figure 4 for Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Viaarxiv icon

DOCCI: Descriptions of Connected and Contrasting Images

Add code
Apr 30, 2024
Figure 1 for DOCCI: Descriptions of Connected and Contrasting Images
Figure 2 for DOCCI: Descriptions of Connected and Contrasting Images
Figure 3 for DOCCI: Descriptions of Connected and Contrasting Images
Figure 4 for DOCCI: Descriptions of Connected and Contrasting Images
Viaarxiv icon

Prompt Expansion for Adaptive Text-to-Image Generation

Add code
Dec 27, 2023
Figure 1 for Prompt Expansion for Adaptive Text-to-Image Generation
Figure 2 for Prompt Expansion for Adaptive Text-to-Image Generation
Figure 3 for Prompt Expansion for Adaptive Text-to-Image Generation
Figure 4 for Prompt Expansion for Adaptive Text-to-Image Generation
Viaarxiv icon

Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

Add code
May 29, 2023
Figure 1 for Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
Figure 2 for Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
Figure 3 for Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
Figure 4 for Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
Viaarxiv icon

A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning

Add code
Oct 06, 2022
Figure 1 for A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning
Figure 2 for A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning
Figure 3 for A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning
Figure 4 for A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning
Viaarxiv icon

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Add code
Jun 22, 2022
Figure 1 for Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Figure 2 for Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Figure 3 for Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Figure 4 for Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Viaarxiv icon

Vector-quantized Image Modeling with Improved VQGAN

Add code
Oct 09, 2021
Figure 1 for Vector-quantized Image Modeling with Improved VQGAN
Figure 2 for Vector-quantized Image Modeling with Improved VQGAN
Figure 3 for Vector-quantized Image Modeling with Improved VQGAN
Figure 4 for Vector-quantized Image Modeling with Improved VQGAN
Viaarxiv icon

PanGEA: The Panoramic Graph Environment Annotation Toolkit

Add code
Mar 23, 2021
Figure 1 for PanGEA: The Panoramic Graph Environment Annotation Toolkit
Figure 2 for PanGEA: The Panoramic Graph Environment Annotation Toolkit
Viaarxiv icon

On the Evaluation of Vision-and-Language Navigation Instructions

Add code
Jan 26, 2021
Figure 1 for On the Evaluation of Vision-and-Language Navigation Instructions
Figure 2 for On the Evaluation of Vision-and-Language Navigation Instructions
Figure 3 for On the Evaluation of Vision-and-Language Navigation Instructions
Figure 4 for On the Evaluation of Vision-and-Language Navigation Instructions
Viaarxiv icon