Related papers: Non-reducible Modal Transition Systems
A Mendelsohn triple system of order $v$ (or MTS$(v)$) is a decomposition of the complete graph into directed 3-cyles. We denote the directed 3-cycle with edges $(x,y)$, $(y,z)$ and $(z,x)$ by $(x,y,z)$, $(y,z,x)$ or $(z,x,y)$. An…
We aim to improve the performance of Multiple Object Tracking and Segmentation (MOTS) by refinement. However, it remains challenging for refining MOTS results, which could be attributed to that appearance features are not adapted to target…
Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…
This paper introduces different views for understanding problems and faults with the goal of defining a method for the formal specification of systems. The idea of Layered Fault Tolerant Specification (LFTS) is proposed to make the method…
Partition refinement is a method for minimizing automata and transition systems of various types. Recently, we have developed a partition refinement algorithm that is generic in the transition type of the given system and matches the run…
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…
Time series datasets are often composed of a variety of sequences from the same domain, but from different entities, such as individuals, products, or organizations. We are interested in how time series models can be specialized to…
Multi-task learning (MTL) algorithms typically rely on schemes that combine different task losses or their gradients through weighted averaging. These methods aim to find Pareto stationary points by using heuristics that require access to…
The development of complex component software systems can be made more manageable by first creating an abstract model and then incrementally adding details. Model transformation is an approach to add such details in a controlled way. In…
Behavior Trees (BTs) provide designers an intuitive graphical interface to construct long-horizon plans for autonomous systems. To ensure their correctness and safety, rigorous formal models and verification techniques are essential.…
Multi-modal recommendation systems aim to enhance performance by integrating an item's content features across various modalities with user behavior data. Effective utilization of features from different modalities requires addressing two…
We propose a relaxation to the definition of well-structured transition systems (\WSTS) while retaining the decidability of boundedness and non-termination. In this class, the well-quasi-ordered (wqo) condition is relaxed such that it is…
For Finite State Machines (FSMs) a rich testing theory has been developed to discover aspects of their behavior and ensure their correct functioning. Although this theory is widely used, e.g., to check conformance of protocol…
In this work, we introduce instruction finetuning for Neural Machine Translation (NMT) models, which distills instruction following capabilities from Large Language Models (LLMs) into orders-of-magnitude smaller NMT models. Our…
Multimodal video understanding is crucial for analyzing egocentric videos, where integrating multiple sensory signals significantly enhances action recognition and moment localization. However, practical applications often grapple with…
We formalise some aspects of the neural-symbol design patterns of van Bekkum et al., such that we can formally define notions of refinement of patterns, as well as modular combination of larger patterns from smaller building blocks. These…
Modular and reconfigurable robotic systems have been designed to provide a customized solution for the non-repetitive tasks to be performed in a constrained environment. Customized solutions are normally extracted from task-based…
Foundation models have revolutionized general-purpose problem-solving, offering rapid task adaptation through pretraining, meta-training, and finetuning. Recent crucial advances in these paradigms reveal the importance of challenging task…
Non-volatile memory (NVM), aka persistent memory, is a new paradigm for memory that preserves its contents even after power loss. The expected ubiquity of NVM has stimulated interest in the design of novel concepts ensuring correctness of…
This paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to constrain the output to include…