Related papers: CSTRL: Context-Driven Sequential Transfer Learning…

Transformer-based sequential recommendation (SR) models excel at modeling long-range dependencies in user behavior via self-attention. However, updating them with continuously arriving behavior sequences incurs high computational costs or…

Pre-trained sequence-to-sequence (seq-to-seq) models have significantly improved the accuracy of several language generation tasks, including abstractive summarization. Although the fluency of abstractive summarization has been greatly…

The rise of In-Context Learning (ICL) for universal medical image segmentation has introduced an unprecedented demand for large-scale, diverse datasets for training, exacerbating the long-standing problem of data scarcity. While data…

We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization, which calibrates long-range dependencies from topic-level features with globally salient content. The idea is to incorporate neural…

We evaluate the character-level translation method for neural semantic parsing on a large corpus of sentences annotated with Abstract Meaning Representations (AMRs). Using a sequence-to-sequence model, and some trivial preprocessing and…

In-context learning (ICL) is an effective approach to help large language models (LLMs) adapt to various tasks by providing demonstrations of the target task. Considering the high cost of labeling demonstrations, many methods propose…

Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first,…

We develop a set of methods to improve on the results of self-supervised learning using context. We start with a baseline of patch based arrangement context learning and go from there. Our methods address some overt problems such as…

A key challenge in training neural networks for a given medical imaging task is often the difficulty of obtaining a sufficient number of manually labeled examples. In contrast, textual imaging reports, which are often readily available in…

The realm of scientific text summarization has experienced remarkable progress due to the availability of annotated brief summaries and ample data. However, the utilization of multiple input modalities, such as videos and audio, has yet to…

Recent advances in text-conditioned image generation diffusion models have begun paving the way for new opportunities in modern medical domain, in particular, generating Chest X-rays (CXRs) from diagnostic reports. Nonetheless, to further…

Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text…

Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot capabilities in various computer vision tasks. However, their application to medical imaging remains challenging due to the high variability and complexity…

Self-supervised learning (SSL) has emerged as a powerful paradigm for Chest X-ray (CXR) analysis under limited annotations. Yet, existing SSL strategies remain suboptimal for medical imaging. Masked image modeling allocates substantial…

Deploying multimodal large language models (MLLMs) for clinical summarization demands not only fluent generation but also transparency about where each statement originates-and a mechanism to flag when statements lack evidential support. We…

Continuous-time reinforcement learning (CTRL) provides a principled framework for sequential decision-making in environments where interactions evolve continuously over time. Despite its empirical success, the theoretical understanding of…

We propose a summarization approach for scientific articles which takes advantage of citation-context and the document discourse model. While citations have been previously used in generating scientific summaries, they lack the related…

While there has been recent progress in abstractive summarization as applied to different domains including news articles, scientific articles, and blog posts, the application of these techniques to clinical text summarization has been…

Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason…

In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST)…