Zobrazeno 1 - 10
of 1 501
pro vyhledávání: '"ROBERTS, JONATHAN"'
Large Language Models (LLMs) are increasingly deployed in real-world applications that demand complex reasoning. To track progress, robust benchmarks are required to evaluate their capabilities beyond superficial pattern recognition. However, current
Externí odkaz:
http://arxiv.org/abs/2412.13602
As the context limits of Large Language Models (LLMs) increase, the range of possible applications and downstream functions broadens. In many real-world tasks, decisions depend on details scattered across collections of often disparate documents cont
Externí odkaz:
http://arxiv.org/abs/2411.05000
Autor:
Owen, Aron E., Roberts, Jonathan C.
The need for innovative ideas in data visualisation drives us to explore new creative approaches. Combining two or more creative words, particularly those that contradict each other, can positively impact the creative process, sparking novel ideas an
Externí odkaz:
http://arxiv.org/abs/2409.02823
Autor:
Owen, Aron E, Roberts, Jonathan C
Creativity in visualisation design is essential for designers and data scientists who need to present data in innovative ways. It is often achieved through sketching or drafting low-fidelity prototypes. However, judging this innovation is often diffi
Externí odkaz:
http://arxiv.org/abs/2409.02036
Autor:
Roberts, Jonathan C.
Data-art exhibitions offer a unique and real-world setting to foster creative visualisation skills among students. They serve as real-world platform for students to display their work, bridging the gap between classroom learning and professional prac
Externí odkaz:
http://arxiv.org/abs/2408.16479
Large multimodal models (LMMs) have exhibited proficiencies across many visual tasks. Although numerous well-known benchmarks exist to evaluate model performance, they increasingly have insufficient headroom. As such, there is a pressing need for a n
Externí odkaz:
http://arxiv.org/abs/2408.11817
Autor:
Owen, Aron E., Roberts, Jonathan C.
Traditional visualisation designers often start with sketches before implementation. With generative AI, these sketches can be turned into AI-generated visualisations using specific prompts. However, guiding AI to create compelling visuals can be cha
Externí odkaz:
http://arxiv.org/abs/2409.01283
Autor:
Owen, Rhiannon, Roberts, Jonathan
We present a design study of developing a visualisation poster. Posters can be difficult to create, and the story on a poster is not always clear. Using a case-study approach we propose three important aspects: the poster should have a clear focus (e
Externí odkaz:
http://arxiv.org/abs/2408.10439
Autor:
Roberts, Jonathan C.
We present an authentic learning task designed for computing students, centred on the creation of data-art visualisations from chosen datasets for a public exhibition. This exhibition was showcased in the cinema foyer for two weeks in June, providing
Externí odkaz:
http://arxiv.org/abs/2408.07590
Autor:
Roberts, Jonathan C.
Data-art blends visualisation, data science, and artistic expression. It allows people to transform information and data into exciting and interesting visual narratives. Hosting a public data-art hands-on workshop enables participants to engage with
Externí odkaz:
http://arxiv.org/abs/2408.04750