Related papers: UniMASK: Unified Inference in Sequential Decision …

A fine-grained data recipe is crucial for pre-training large language models, as it can significantly enhance training efficiency and model performance. One important ingredient in the recipe is to select samples based on scores produced by…

Masking tokens uniformly at random constitutes a common flaw in the pretraining of Masked Language Models (MLMs) such as BERT. We show that such uniform masking allows an MLM to minimize its training objective by latching onto shallow local…

Machine learning has emerged as a powerful tool for time series analysis. Existing methods are usually customized for different analysis tasks and face challenges in tackling practical problems such as partial labeling and domain shift. To…

Recent works propose complex multi-modal models that handle both time series and language, ultimately claiming high performance on complex tasks like time series reasoning and cross-modal question answering. However, they skip foundational…

Decoding human brain activity from electroencephalography (EEG) signals is a central challenge at the intersection of neuroscience and artificial intelligence, enabling diverse applications in mental state assessment, clinical monitoring,…

The universal model emerges as a promising trend for medical image segmentation, paving up the way to build medical imaging large model (MILM). One popular strategy to build universal models is to encode each task as a one-hot vector and…

Many classification problems require decisions among a large number of competing classes. These tasks, however, are not handled well by general purpose learning methods and are usually addressed in an ad-hoc fashion. We suggest a general…

Recent studies have proposed unified user modeling frameworks that leverage user behavior data from various applications. Many of them benefit from utilizing users' behavior sequences as plain texts, representing rich information in any…

Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing…

As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data. Among these varied…

Personalized mobile artificial intelligence applications are widely deployed, yet they are expected to infer user behavior from sparse and irregular histories under a continuously evolving spatio-temporal context. This setting induces a…

Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of…

Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones to achieve consistency, thus…

Recommender systems have long been built upon the modeling of interactions between users and items, while recent studies have sought to broaden this paradigm by generalizing to new users and items, incorporating diverse information sources,…

Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare, which involves various tasks, such as forecasting and classification. To handle the inherent complexities of time-series data,…

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple…

Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involves research into the architecture and a long period of…

Self-supervised learning models have revolutionized the field of speech processing. However, the process of fine-tuning these models on downstream tasks requires substantial computational resources, particularly when dealing with multiple…

Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related tasks. While current unified frameworks based on large language…

In-context learning provides a new perspective for multi-task modeling for vision and NLP. Under this setting, the model can perceive tasks from prompts and accomplish them without any extra task-specific head predictions or model…