Related papers: PETRA: Pretrained Evolutionary Transformer for SAR…
Understanding the learning process and the embedded computation in transformers is becoming a central goal for the development of interpretable AI. In the present study, we introduce a hierarchical filtering procedure for data models of…
We introduce a novel sequence-to-sequence (seq2seq) voice conversion (VC) model based on the Transformer architecture with text-to-speech (TTS) pretraining. Seq2seq VC models are attractive owing to their ability to convert prosody. While…
Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings.…
Compartmental models provide simple and efficient tools to analyze the relevant transmission processes during an outbreak, to produce short-term forecasts or transmission scenarios, and to assess the impact of vaccination campaigns.…
Gene expression profiling provides critical insights into cellular heterogeneity, biological processes and disease mechanisms. There has been an increasing interest in computational approaches that can predict gene expression directly from…
Plant phenotyping (Guo et al. 2021; Pieruschka et al. 2019) focuses on studying the diverse traits of plants related to the plants' growth. To be more specific, by accurately measuring the plant's anatomical, ontogenetical, physiological…
Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…
Nowadays, our mobility systems are evolving into the era of intelligent vehicles that aim to improve road safety. Due to their vulnerability, pedestrians are the users who will benefit the most from these developments. However, predicting…
In practical time series forecasting, covariates provide rich contextual information that can potentially enhance the forecast of target variables. Although some covariates extend into the future forecasting horizon (e.g., calendar events,…
We present Self-Adaptive Robust Attention for Robotics Transformers (SARA-RT): a new paradigm for addressing the emerging challenge of scaling up Robotics Transformers (RT) for on-robot deployment. SARA-RT relies on the new method of…
Synthesizing medical images, such as PET, is a challenging task due to the fact that the intensity range is much wider and denser than those in photographs and digital renderings and are often heavily biased toward zero. Above all,…
The emerging global infectious COVID-19 coronavirus disease by novel Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) presents critical threats to global public health and the economy since it was identified in late December…
Visual Place Recognition (VPR) localizes a query image by matching it against a database of geo-tagged reference images, making it essential for navigation and mapping in robotics. Although Vision Transformer (ViT) solutions deliver high…
High-quality text data has become an important data source for social scientists. We have witnessed the success of pretrained deep neural network models, such as BERT and RoBERTa, in recent social science research. In this paper, we propose…
In this paper, we propose Singular Values and Orthonormal Regularized Singular Vectors Adaptation, or SORSA, a novel parameter efficient fine-tuning (PEFT) method. Each SORSA adapter consists of two main parts: trainable principal singular…
A syntactic language model (SLM) incrementally generates a sentence with its syntactic tree in a left-to-right manner. We present Generative Pretrained Structured Transformers (GPST), an unsupervised SLM at scale capable of being…
One regards spaces of trees as stratified spaces, to study distributions of phylogenetic trees. Stratified spaces with may have cycles, however spaces of trees with a fixed number of leafs are contractible. Spaces of trees with three leafs,…
Consistency Training (CT) has recently emerged as a strong alternative to diffusion models for image generation. However, non-distillation CT often suffers from high variance and instability, motivating ongoing research into its training…
Personalization of natural language generation plays a vital role in a large spectrum of tasks, such as explainable recommendation, review summarization and dialog systems. In these tasks, user and item IDs are important identifiers for…
This research introduces a novel text generation model that combines BERT's semantic interpretation strengths with GPT-4's generative capabilities, establishing a high standard in generating coherent, contextually accurate language. Through…