Thesis - Evaluation of small language models for user guidance

In the ever-evolving landscape of conversational AI, our company is interested in what it can be used for in terms of improving usability. Since the inception of ChatGPT, we've witnessed remarkable advancements in language models. In this thesis, we're exploring the potential of smaller-scale models as an aid to our configurable software.

SICK Nova simplifies vision applications, allowing end-users without programming expertise to effortlessly tackle complex tasks through a user-friendly interface. Imagine enhancing Nova with an intelligent chatbot interface that answers queries about its features, suggests tools, or aids users in developing their applications using our API. This is the goal we're working towards.

The master thesis work focuses on the following/example of research questions

1. Can a small-scale model be effectively trained using data from existing operating instructions written for end-users?
2. Among various models, which performs best across different tasks, including question answering, application solving, and programming tasks?
3. Is it possible to achieve multimodal understanding, encompassing text and images, with small-scale models?

You will benefit a lot from having experience in:

Deep Learning, Natural Language Processing, Network Quantization, Data Analysis

 In addition, proficiency in programming languages and tool relevant to the research is highly advantageous.

Contact

For more information about the position, contact:

John Stynsberg, SW Developer, john.stynsberg@sick.se

or

Charlotte Axelsson, HR Manager, +46 739 20 99 50.

Welcome with your application 15th of October at the latest! We make ongoing selections and offer our thesis opportunity as soon as we have found the right person.

If you would like to write your thesis in a pair, please provide us with one application where you  attach both your CVs  and extracts of study results and one mutual cover letter.

SICK is a world-leading supplier of sensors and sensor solutions for industrial applications. We are 11 000 employees in 50 countries and our headquarter is located in Freiburg, Germany. SICK in Linköping is an innovation center for Machine Vision and we are 80 committed employees with a big interest in image processing and visualization. For more than 35 years, our team at SICK Linköping has successfully developed and delivered software for technically leading products within the field of 2D and 3D vision, as well as system solutions for i.e. robot guidance and quality control.

At SICK in Linköping, we are very proud of being a healthy and attractive workplace. For many years, we have been elected as one of the best workplaces in Sweden according to the survey Great Place to Work, the latest award is from 2023. We work actively to reduce our climate footprint and we are active in various ways to contribute to the society and to increase diversity at our workplace.