Related papers: Disagreeing about Crocs and socks: Creating profou…
Current research on visual analytics systems largely follows the research paradigm of interactive system design in the field of Human-Computer Interaction (HCI), and includes key methodologies including design requirement development based…
Imitation learning enables robots to learn new tasks from human examples. One fundamental limitation while learning from humans is causal confusion. Causal confusion occurs when the robot's observations include both task-relevant and…
A recent experiment suggests that neural circuits may alternatively implement continuous or discrete attractors, depending on the training set up. In recurrent neural network models, continuous and discrete attractors are separately modeled…
Recommender systems suffer from confounding biases when there exist confounders affecting both item features and user feedback (e.g., like or not). Existing causal recommendation methods typically assume confounders are fully observed and…
Neural representations of visual perception are affected by mental imagery and attention. Although attention is known to modulate neural representations, it is unknown how imagery changes neural representations when imagined and perceived…
Recent advances in generative recommenders adopt a two-stage paradigm: items are first tokenized into semantic IDs using a pretrained tokenizer, and then large language models (LLMs) are trained to generate the next item via…
Consider edge colorings of digraphs where edges $v_1 v_2$ and $v_2 v_3$ have different colors. This coloring induces a vertex coloring by sets of edge colors, in which edge $v_1 v_2$ in the graph implies that the set color of $v_1$ contains…
The concept of color transparency is introduced. This new feature of QCD is characteristic of a gauge theory. It enables strong interactions to be studied in a new domain: scattering amplitudes of transversally small color singlet objects.…
Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…
Language is ambiguous; many terms and expressions can convey the same idea. This is especially true in creative practice, where ideas and design intents are highly subjective. We present a dataset, Ambiguous Descriptions of Art Images…
Concept induction requires the extraction and naming of concepts from noisy perceptual experience. For supervised approaches, as the number of concepts grows, so does the number of required training examples. Philosophers, psychologists,…
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate…
Magri (2016) investigates two puzzles arising from conjunction. Although Magri has proposed a solution to the second puzzle, the first remains unresolved. This first puzzle reveals a hidden interaction among quantification,…
Survey researchers face the problem of sensitivity bias: since people are reluctant to reveal socially undesirable or otherwise risky traits, aggregate estimates of these traits will be biased. List experiments offer a solution by…
Statistics is sometimes described as the science of reasoning under uncertainty. Statistical models provide one view of this uncertainty, but what is frequently neglected is the 'invisible' portion of uncertainty: that assumed not to exist…
It is a fact of our existence, that no matter where we are, we most often find ourselves either hearing, seeing, talking, or even engaged in design related activities. Despite this reality, the notion of 'design', and in particular…
With the widespread dissemination of user-generated content on different social networks, and online consumer systems such as Amazon, the quantity of opinionated information available on the Internet has been increased. One of the main…
Recommender systems aim to recommend new items to users by learning user and item representations. In practice, these representations are highly entangled as they consist of information about multiple factors, including user's interests,…
Dark patterns are (evil) design nudges that steer people's behaviour through persuasive interface design. Increasingly found in cookie consent requests, they possibly undermine principles of EU privacy law. In two preregistered online…
Understanding how humans and AI systems interpret ambiguous visual stimuli offers critical insight into the nature of perception, reasoning, and decision-making. This paper examines image labeling performance across human participants and…