research
∙
09/08/2023
Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
Vision-language models (VLMs) have recently demonstrated strong efficacy...
share
research
∙
04/07/2023
Probing Conceptual Understanding of Large Visual-Language Models
We present a novel framework for probing and improving relational, compo...
research
∙
09/29/2022
Unpacking Large Language Models with Conceptual Consistency
If a Large Language Model (LLM) answers "yes" to the question "Are mount...
research
∙
06/08/2021
Comprehension Based Question Answering using Bloom's Taxonomy
Current pre-trained language models have lots of knowledge, but a more l...
research
∙
07/24/2020
Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data
Can we develop visually grounded dialog agents that can efficiently adap...
research
∙
04/19/2019
Emergence of Compositional Language with Deep Generational Transmission
Consider a collaborative task that requires communication. Two agents ar...
research
∙
11/22/2016
Grad-CAM: Why did you say that?
We propose a technique for making Convolutional Neural Network (CNN)-bas...
research
∙
10/07/2016
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
Neural sequence models are widely used to model time-series data in many...
research
∙
10/07/2016
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
We propose a technique for producing "visual explanations" for decisions...
research
∙
06/24/2016
Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
Many practical perception systems exist within larger processes that inc...
research
∙
11/19/2015
Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
Convolutional Neural Networks have achieved state-of-the-art performance...
research
∙
11/19/2015
Reducing Overfitting in Deep Networks by Decorrelating Representations
One major challenge in training Deep Neural Networks is preventing overf...
research
∙
12/14/2014