Related papers: Developing Modular Grasping and Manipulation Pipel…
Existing benchmarks for computational materials discovery primarily evaluate static predictive tasks or isolated computational sub-tasks. While valuable, these evaluations neglect the inherently iterative and adaptive nature of scientific…
Data is a valuable asset, and sharing it as a product across organizations is key to building comprehensive and useful insights in fields such as science and industry. Before sharing, data often requires transformation to comply with…
Animal behavior analysis plays a crucial role in understanding animal welfare, health status, and productivity in agricultural settings. However, traditional manual observation methods are time-consuming, subjective, and limited in…
The formation of biomolecular materials via dynamical interfacial processes such as self-assembly and fusion, for diverse compositions and external conditions, can be efficiently probed using ensemble Molecular Dynamics. However, this…
We formulate a control system model for the distributed flow of mixtures of highly heterogeneous gases through large-scale pipeline networks with time-varying injections of constituents, withdrawals, and control actions of compressors. This…
The increasing adoption of low-cost environmental sensors and AI-enabled applications has accelerated the demand for scalable and resilient data infrastructures, particularly in data-scarce and resource-constrained regions. This paper…
This survey paper focuses on quadrotor- and multirotor- based cooperative aerial manipulation. Emphasis is first given on comparing and evaluating prototype systems that have been implemented and tested in real-time in diverse application…
Many studies have proposed methods for optimizing the dialogue performance of an entire pipeline task-oriented dialogue system by jointly training modules in the system using reinforcement learning. However, these methods are limited in…
Evolutionary change over time in the context of data pipelines is certain, especially with regard to the structure and semantics of data as well as to the pipeline operators. Dealing with these changes, i.e. providing long-term maintenance,…
In order to achieve state-of-the-art performance, modern machine learning techniques require careful data pre-processing and hyperparameter tuning. Moreover, given the ever increasing number of machine learning models being developed, model…
Nowadays, neural networks act as a synonym for artificial intelligence. Present neural network models, although remarkably powerful, are inefficient both in terms of data and energy. Several alternative forms of neural networks have been…
To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…
Benchmarking, which involves collecting reference datasets and demonstrating method performances, is a requirement for the development of new computational tools, but also becomes a domain of its own to achieve neutral comparisons of…
We describe a challenging robotics deployment in a complex ecosystem to monitor a rich plant community. The study site is dominated by dynamic grassland vegetation and is thus visually ambiguous and liable to drastic appearance change over…
Spatial architecture is a high-performance architecture that uses control flow graphs and data flow graphs as the computational model and producer/consumer models as the execution models. However, existing spatial architectures suffer from…
Polymers play a crucial role in the development of engineering materials, with applications ranging from mechanical to biomedical fields. However, the limited polymerization processes constrain the variety of organic building blocks that…
This work contains the details and results of my master's project on testing the IMAGINE pipeline for Galactic magnetic field estimation. The project was carried out from early 2016 to early 2017. For it, an unpublished early development…
Previous work has suggested that the structural restrictions of graphs from classes of bounded expansion--locally dense pockets in a globally sparse graph--naturally coincide with common properties of real-world networks such as clustering…
Many interesting datasets ubiquitous in machine learning and deep learning can be described via graphs. As the scale and complexity of graph-structured datasets increase, such as in expansive social networks, protein folding, chemical…
Advanced imitation learning with structures like the transformer is increasingly demonstrating its advantages in robotics. However, deploying these large-scale models on embedded platforms remains a major challenge. In this paper, we…