Foundations & trends in multimodal machine learning: Principles, challenges, and open questions
Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design
computer agents with intelligent capabilities such as understanding, reasoning, and learning …
computer agents with intelligent capabilities such as understanding, reasoning, and learning …
[HTML][HTML] Artificial intelligence and business value: A literature review
Artificial Intelligence (AI) are a wide-ranging set of technologies that promise several
advantages for organizations in terms off added business value. Over the past few years …
advantages for organizations in terms off added business value. Over the past few years …
From pretraining data to language models to downstream tasks: Tracking the trails of political biases leading to unfair NLP models
Language models (LMs) are pretrained on diverse data sources, including news, discussion
forums, books, and online encyclopedias. A significant portion of this data includes opinions …
forums, books, and online encyclopedias. A significant portion of this data includes opinions …
On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Dealing with disagreements: Looking beyond the majority vote in subjective annotations
Majority voting and averaging are common approaches used to resolve annotator
disagreements and derive single ground truth labels from multiple annotations. However …
disagreements and derive single ground truth labels from multiple annotations. However …
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
A key limitation in current datasets for multi-hop reasoning is that the required steps for
answering the question are mentioned in it explicitly. In this work, we introduce StrategyQA …
answering the question are mentioned in it explicitly. In this work, we introduce StrategyQA …
Shortcut learning in deep neural networks
Deep learning has triggered the current rise of artificial intelligence and is the workhorse of
today's machine intelligence. Numerous success stories have rapidly spread all over …
today's machine intelligence. Numerous success stories have rapidly spread all over …
The alignment problem from a deep learning perspective
In coming decades, artificial general intelligence (AGI) may surpass human capabilities at
many critical tasks. We argue that, without substantial effort to prevent it, AGIs could learn to …
many critical tasks. We argue that, without substantial effort to prevent it, AGIs could learn to …
Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions
Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design
computer agents with intelligent capabilities such as understanding, reasoning, and learning …
computer agents with intelligent capabilities such as understanding, reasoning, and learning …
Dataperf: Benchmarks for data-centric ai development
Abstract Machine learning research has long focused on models rather than datasets, and
prominent datasets are used for common ML tasks without regard to the breadth, difficulty …
prominent datasets are used for common ML tasks without regard to the breadth, difficulty …