Related papers: How Panel Layouts Define Manga: Insights from Visu…
The circuits framework in mechanistic interpretability aims to identify causally important sparse subgraphs of model components, typically evaluated by measuring necessity and sufficiency. We measure circuit reuse, the proportion of…
Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…
In this paper, we propose MAGICSTYLEGAN and MAGICSTYLEGAN-ADA - both incarnations of the state-of-the-art models StyleGan2 and StyleGan2 ADA - to experiment with their capacity of transfer learning into a rather different domain: creating…
Learning meaningful representations is at the heart of many tasks in the field of modern machine learning. Recently, a lot of methods were introduced that allow learning of image representations without supervision. These representations…
Multi-object representation learning aims to represent complex real-world visual input using the composition of multiple objects. Representation learning methods have often used unsupervised learning to segment an input image into…
This work addresses the scarcity of high-quality, large-scale resources for Japanese Vision-and-Language (V&L) modeling. We present a scalable and reproducible pipeline that integrates large-scale web collection with rigorous…
Decoding brain imaging data are gaining popularity, with applications in brain-computer interfaces and the study of neural representations. Decoding is typicallysubject-specific and does not generalise well over subjects, due to high…
Diagram question answering (DQA) requires models to interpret structured visual representations such as charts, maps, infographics, circuit schematics, and scientific diagrams. Recent vision-language models (VLMs) often achieve high answer…
Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth…
Context: Software programs can be written in different but functionally equivalent ways. Even though previous research has compared specific formatting elements to find out which alternatives affect code legibility, seeing the bigger…
In this work, a new way to represent Japanese animation (anime) is presented. We applied a minimum spanning tree to show the relation between anime. The distance between anime is calculated through three similarity measurements, namely…
The rise of 3D anime-style avatars in gaming, virtual reality, and other digital media has driven significant interest in automated generation methods capable of capturing their distinctive visual characteristics. These include stylized…
Deep learning-based approaches for automatic document layout analysis and content extraction have the potential to unlock rich information trapped in historical documents on a large scale. One major hurdle is the lack of large datasets for…
While multi-modal large language models (MLLMs) have shown significant progress on many popular visual reasoning benchmarks, whether they possess abstract visual reasoning abilities remains an open question. Similar to the Sudoku puzzles,…
One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature…
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations…
This paper introduces the human-curated PandasPlotBench dataset, designed to evaluate language models' effectiveness as assistants in visual data exploration. Our benchmark focuses on generating code for visualizing tabular data - such as a…
The Computer-aided Diagnosis or Detection (CAD) approach for skin lesion analysis is an emerging field of research that has the potential to alleviate the burden and cost of skin cancer screening. Researchers have recently indicated…
The medical image analysis field has traditionally been focused on the development of organ-, and disease-specific methods. Recently, the interest in the development of more 20 comprehensive computational anatomical models has grown,…
On-screen game footage contains rich contextual information that players process when playing and experiencing a game. Learning pixel representations of games can benefit artificial intelligence across several downstream tasks including…