no code implementations • 12 Dec 2023 • Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jorg S. Wicker
With the advancement in robotics, it is becoming increasingly common for large factories and warehouses to incorporate visual SLAM (vSLAM) enabled automated robots that operate closely next to humans.
no code implementations • 21 Nov 2023 • Tim Hartill, Joshua Bensemann, Michael Witbrock, Patricia J. Riddle
We train two Language Models in a multitask fashion whereby the second model differs from the first only in that it has two additional datasets added to the training regime that are designed to impart simple numerical reasoning strategies of a sort known to improve performance on some of our evaluation datasets but not on others.
no code implementations • 9 Aug 2023 • Tim Hartill, Diana Benavides-Prado, Michael Witbrock, Patricia J. Riddle
When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training.
1 code implementation • 2 Aug 2023 • Tim Hartill, Neset Tan, Michael Witbrock, Patricia J. Riddle
We equip a smaller Language Model to generalise to answering challenging compositional questions that have not been seen in training.
no code implementations • 24 Sep 2022 • Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jörg S. Wicker
However, they are unable to exploit spatial information of local visual features and lack a structure that unifies semantic objects and visual features, therefore limiting the symbiosis between the two components.
no code implementations • 21 Oct 2021 • Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jörg S. Wicker
Many state-of-the-art loop closure detection (LCD) algorithms use visual Bag-of-Words (vBoW), which is robust against partial occlusions in a scene but cannot perceive the semantics or spatial relationships between feature points.
Loop Closure Detection Simultaneous Localization and Mapping