Related papers: Customizing Sequence Generation with Multi-Task Dy…

Deep learning (DL) in general and Recurrent neural networks (RNNs) in particular have seen high success levels in sequence based applications. This paper pertains to RNNs for time series modelling and forecasting. We propose a novel RNN…

Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e.g., BART and T5), have exhibited compelling performance on various natural language generation tasks. However, the black-box nature of these models…

Neural-based multi-task learning (MTL) has gained significant improvement, and it has been successfully applied to recommendation system (RS). Recent deep MTL methods for RS (e.g. MMoE, PLE) focus on designing soft gating-based…

While session-based recommender systems (SBRSs) have shown superior recommendation performance, multi-task learning (MTL) has been adopted by SBRSs to enhance their prediction accuracy and generalizability further. Hierarchical MTL (H-MTL)…

Classical methods of solving spatiotemporal dynamical systems include statistical approaches such as autoregressive integrated moving average, which assume linear and stationary relationships between systems' previous outputs. Development…

Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning data is generally sequentially concatenated from a specific…

Safety-critical controllers of complex systems are hard to construct manually. Automated approaches such as controller synthesis or learning provide a tempting alternative but usually lack explainability. To this end, learning decision…

Existing Natural Language Generation (NLG) systems are weak AI systems and exhibit limited capabilities when language generation tasks demand higher levels of creativity, originality and brevity. Effective solutions or, at least evaluations…

Synthetic data has the potential to improve the performance, training efficiency, and privacy of real training examples. Nevertheless, existing approaches for synthetic text generation are mostly heuristics and cannot generate…

The quality of datasets is one of the key factors that affect the accuracy of aerodynamic data models. For example, in the uniformly sampled Burgers' dataset, the insufficient high-speed data is overwhelmed by massive low-speed data.…

The availability of large datasets is crucial for the development of new power system applications and tools; unfortunately, very few are publicly and freely available. We designed an end-to-end generative framework for the creation of…

Mesh is a fundamental representation of 3D assets in various industrial applications, and is widely supported by professional softwares. However, due to its irregular structure, mesh creation and manipulation is often time-consuming and…

Session-based recommendation plays a central role in a wide spectrum of online applications, ranging from e-commerce to online advertising services. However, the majority of existing session-based recommendation techniques (e.g.,…

Program synthesis is the task of automatically generating a program consistent with a given specification. A natural way to specify programs is to provide examples of desired input-output behavior, and many current program synthesis…

This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of…

Established recurrent neural networks are well-suited to solve a wide variety of prediction tasks involving discrete sequences. However, they do not perform as well in the task of dynamical system identification, when dealing with…

Modular robots can be tailored to achieve specific tasks and rearranged to achieve previously infeasible ones. The challenge is choosing an appropriate design from a large search space. In this work, we describe a framework that…

The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…

Neural architectures such as Recurrent Neural Networks (RNNs), Transformers, and State-Space Models have shown great success in handling sequential data by learning temporal dependencies. Decision Trees (DTs), on the other hand, remain a…

System Level Synthesis (SLS) parametrization facilitates controller synthesis for large, complex, and distributed systems by incorporating system level constraints (SLCs) into a convex SLS problem and mapping its solution to stable…