Ponedeljkov seminar računalništva in informatike - Arhiv

V ponedeljek, 13. aprila 2026, bo ob 16:00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 13. april 2026 ob 16.00 v FAMNIT-VP3.

-------------------------------------------------
PREDAVATELJICA: Kaja PRAPROTNIK
-------------------------------------------------

Kaja Praprotnik is a PhD student at UP FAMNIT under the supervision of Prof. Jernej Vičič. Her research focuses on natural language processing with a strong focus on artificial intelligence.

-------------------------------------------------------------------------------------------------------------------------------
NASLOV: Fine-Tuning Small Language Models for Sign Language Gloss-to-German Translation
-------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Sign language is to some people the first language and in some cases even the only language they know. Writing in spoken language might present some challenges in everyday life. To prevent further isolation for people who already struggle to live in a world designed for hearing people, the translation from sign language to spoken language is necessary.
Without compromising user privacy, the translation system should enable accessibility to essential applications, such as healthcare communication systems. 
Large language models are because of their computational needs usually hosted in the cloud, which can pose a risk of leakage of sensitive personal data. 
Small language models can run locally on the user's device, which protects privacy of the sensitive data.
Our research focuses on fine-tuning a small language model, for translating written sign language into spoken language.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.

Vabljeni!

V ponedeljek, 30. marca 2026, bo ob 16:00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 30. marec 2026 ob 16.00 v FAMNIT-VP3.

------------------------------------------------------------------------------------
PREDAVATELJICI: Karolina TRAJKOVSKA in Michelle FERNANDO
------------------------------------------------------------------------------------

Karolina Trajkovska is a PhD student and researcher at UP FAMNIT. She is a young researcher in HCI/UX, contributing to research on how people interact with digital systems, especially using modern techniques like eye-tracking and augmented reality.

Michelle Fernando is a PhD student and teaching assistant at UP FAMNIT, where she works with the HICUP Lab. She received the B.Sc. (Hons) degree in computer science from the University of Colombo, Sri Lanka. Her research focuses on human-computer interaction, extended reality, and human motion analysis in the context of sports training and skill acquisition.

-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Beyond Rote Memorisation: The Impact of AI-Generated Visuals and Personalised Mnemonics on Vocabulary Retention
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

Mnemonics, such as the keyword method, are effective for vocabulary learning, where learners form a mental image cues linking a foreign word to a phonetically similar word in a familiar language. However, many avoid mnemonics because generating these cues is cognitively demanding. The first aim of this study is to examine whether non-personalised (pre-generated) cues can decrease cognitive effort while maintaining performance compared with personalised (self-generated) cues. The second aim is to compare externalised cues in image and video formats, using novel text-to-images/video generation. We built an interactive tool and ran a mixed-design study with 32 participants, manipulating PERSONALISATION (personalised vs non-personalised mnemonic cues) and MODALITY (images vs videos). The analysis is presented in two parts:
Part I (presented by Karolina Trajkovska):
Performance & Efficiency.  Personalised cues produced significantly better immediate and delayed recall but took more time and increased perceived workload, whereas non-personalised cues were more efficient in recall per unit time. Despite this, participants preferred personalised cues, suggesting subjective benefits beyond performance. Finally, modality showed no significant differences, though images had a modest advantage.
Part II (presented by Michelle Fernando):
Biometric data collection & Emotional Engagement. We detail the collection and analysis of biometric data to evaluate physiological correlates of the "personalisation effect." This explores how self-generation influences emotional arousal and cognitive investment compared to passive consumption of cues. The statistical analysis shows a significant main effect of PERSONALISATION on emotional engagement.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.

Vabljeni!

V ponedeljek, 23. marca 2026, bo ob 16:00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 23. marec 2026 ob 16.00 v FAMNIT-VP3.

-----------------------------------------------------
PREDAVATELJICA: Karolina TRAJKOVSKA
-----------------------------------------------------

Karolina Trajkovska is a PhD student and researcher at UP FAMNIT. She is a young researcher in HCI/UX, contributing to research on how people interact with digital systems, especially using modern techniques like eye-tracking and augmented reality.

----------------------------------------------------------------------------------------------------------------------------------------------------------------------------
NASLOV: Can Immersion Protect us From Distraction? The Impact of Real-World Distractions on Learning in Augmented Reality
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------

POVZETEK:

While many digital distractions can be managed, real-world interruptions, such as phone calls, notifications, and office noise, are harder to control and can harm productivity, well-being, and learning. Mixed reality systems like Augmented Reality (AR) are often described as immersive—a property which might protect users from such disruptions. We tested this assumption by comparing a head-mounted AR interface that overlays digital annotations on physical objects with a traditional flat screen during vocabulary learning under common office distractions. In a user study (n = 32), AR users reported feeling less distracted and recalled less task-irrelevant information, but their learning performance did not improve. Instead, distraction-related performance decline was greater in AR. Physiological and self-report measures showed no reduction in effort or workload, and participants with higher auditory distractibility did not benefit. Overall, AR annotation alone may not sufficiently shield learners from real-world distractions, motivating new design approaches.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.

Vabljeni!

V ponedeljek, 12. januarja 2026, bo ob 16:00 uri izvedeno
predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 12. januar 2026 ob 16.00 v FAMNIT-VP3.

-----------------------------------------------
PREDAVATELJ: Marko GRGUROVIĆ
-----------------------------------------------

Marko Grgurovič is the CEO and founder of Triternion, the independent studio behind the medieval multiplayer hit Mordhau. Today, he leads a team of approximately 35 developers based in Ljubljana focused on creating high-fidelity, skill-based multiplayer experiences that prioritize deep combat mechanics and fluid, realistic character movement.

-----------------------------------------------------------------
NASLOV: Smoothing & Motion in Video Games
-----------------------------------------------------------------

POVZETEK:

In this talk we will explore the evolution of game development through the lens of a smaller indie studio that has to "do more with less". The talk bridges the gap between high-level industry trends and the under-the-hood technical challenges of creating fluid, responsive motion in modern video games. We will look at smoothing functions and springs, and how they can be used in both error correction and procedural animation techniques.

Seminar bo potekal v angleškem jeziku v predavalnici FAMNIT-VP3 s pričetkom ob 16:00 uri.

Vabljeni!