Related papers: View Distillation with Unlabeled Data for Extracti…
Side effects of prescribed medications are a common occurrence. Electronic healthcare databases present the opportunity to identify new side effects efficiently but currently the methods are limited due to confounding (i.e. when an…
Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet challenging setting, where transferable knowledge is limited to the predictions of a…
Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this paradigm and was…
As Artificial Intelligence models, such as Large Video-Language models (VLMs), grow in size, their deployment in real-world applications becomes increasingly challenging due to hardware limitations and computational costs. To address this,…
This paper explores whether the use of drug reviews and social media could be leveraged as potential alternative sources for pharmacovigilance of adverse drug reactions (ADRs). We examined the performance of BERT alongside two variants that…
Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. To address this, we extend Inverse Distillation, a technique…
In today's fast-paced world, the rates of stress and depression present a surge. Social media provide assistance for the early detection of mental health conditions. Existing methods mainly introduce feature extraction approaches and train…
Users of social platforms often perceive these sites as supportive spaces to post about their mental health issues. Those conversations contain important traces about individuals' health risks. Recently, researchers have exploited this…
Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground language to observations is difficult due to…
Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…
The success of automated medical image analysis depends on large-scale and expert-annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a promising approach to alleviate the burden of labeled data collection.…
Drug-drug interaction (DDI) is a vital information when physicians and pharmacists intend to co-administer two or more drugs. Thus, several DDI databases are constructed to avoid mistakenly combined use. In recent years, automatically…
Social media plays a significant role in sharing essential information, which helps humanitarian organizations in rescue operations during and after disaster incidents. However, developing an efficient method that can provide rapid analysis…
Unsupervised representation learning has proved to be a critical component of anomaly detection/localization in images. The challenges to learn such a representation are two-fold. Firstly, the sample size is not often large enough to learn…
We propose a technique that tackles action detection in multimodal videos under a realistic and challenging condition in which only limited training data and partially observed modalities are available. Common methods in transfer learning…
The goal of this work is to train strong models for visual speech recognition without requiring human annotated ground truth data. We achieve this by distilling from an Automatic Speech Recognition (ASR) model that has been trained on a…
Personalized optimal decision making, finding the optimal decision rule (ODR) based on individual characteristics, has attracted increasing attention recently in many fields, such as education, economics, and medicine. Current ODR methods…
Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks. Despite the success of these methods, their large memory…
With the deployment of Large Language Models (LLMs) in interactive applications, online malicious intent detection has become increasingly critical. However, existing approaches fall short of handling diverse and complex user queries in…
With exponential increase in the availability oftelemetry / streaming / real-time data, understanding contextualbehavior changes is a vital functionality in order to deliverunrivalled customer experience and build high performance andhigh…