Search Results

Pre-trained language models (LMs) have shown remarkable success in diverse tasks and domains. An LM trained on the document of a specific area (e.g., biomedicine, education, and finance) provides expert-level knowledge about that domain, and there ...

This paper addresses a machine learning problem often challenged by differences in the distributions of training and real-world data. We propose a framework that addresses the problem of underfitting in the ensembling method using pre-trained ...

• We generalized the model via weight ensembling under an extreme distribution shift.
• Our framework solves the underfitting problem of ensembles of pre-trained models.
• We achieved up to 16.3% AUROC improvement over the baseline on ...

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to ...

Test-time adaptation (TTA) aims to address distributional shifts between training and testing data using only unlabeled test data streams for continual model adaptation. However, most TTA methods assume benign test streams, while test samples could be ...

Many applications utilize sensors in mobile devices and machine learning to provide novel services. However, various factors such as different users, devices, and environments impact the performance of such applications, thus making the domain shift (...

We argue for research on identifying opportune moments for remote computer-mediated interactions with home-alone dogs. We analyze the behavior of home-alone pet dogs to find specific situations where positive interaction between the dog and toys is more ...

We propose a multi-singer emotional singing voice synthesizer, Muse-SVS, that expresses emotion at various intensity levels by controlling subtle changes in pitch, energy, and phoneme duration while accurately following the score. To control multiple ...

Test-time adaptation (TTA) is an emerging paradigm that addresses distributional shifts between training and testing phases without additional data acquisition or labeling cost; only unlabeled test data streams are used for continual model adaptation. ...

This paper studies strategic consumer shopping behavior in response to a macroeconomic policy and quantifies its unintended consequences for retailers vis-à-vis the policy goal. Using transaction-level data from a large retail chain in India, we document ...

Learning fair representation is crucial for achieving fairness or debiasing sensitive information. Most existing works rely on adversarial representation learning to inject some invariance into representation. However, adversarial learning methods are ...

I study why many firms face low retention rates among new customers. In particular, I examine whether customer churn at the firm level after a single product experience is solely driven by heterogeneous preferences or is affected by incomplete ...