Related papers: Turing Video-based Cognitive Tests to Handle Entan…
Quantifying unknown quantum entanglement experimentally is a difficult task, but also becomes more and more necessary because of the fast development of quantum engineering. Machine learning provides practical solutions to this fundamental…
Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and…
Quantum correlations that violate the Bell inequality cannot be explained by any (measurement independent) local hidden variable theory. However, the violation only implies incompatibility of the underlying assumptions of reality, locality,…
Human intelligence effortlessly interprets visual scenes along a rich spectrum of semantic dimensions. However, existing approaches to language-grounded visual concept learning are limited to a few predefined primitive axes, such as color…
Quantum entanglement is the key resource for quantum information processing. Device-independent certification of entangled states is a long standing open question, which arouses the concept of self-testing. The central aim of self-testing…
An experimental test of Bell's inequality allows ruling out any local-realistic description of nature by measuring correlations between distant systems. While such tests are conceptually simple, there are strict requirements concerning the…
Multi-view learning methods often focus on improving decision accuracy, while neglecting the decision uncertainty, limiting their suitability for safety-critical applications. To mitigate this, researchers propose trusted multi-view…
We show that Bell inequalities can be violated in the macroscopic world. The macroworld violation is illustrated using an example involving connected vessels of water. We show that whether the violation of inequalities occurs in the…
Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models. At the same time, the disentanglement learning literature has focused on extracting similar…
Violation of a Bell-like inequality for a spin-energy entangled neutron state has been confirmed in a polarimetric experiment. The proposed inequality, in Clauser-Horne-Shimony-Holt (CHSH) formalism, relies on correlations between the spin…
Motivation: Combining the results of different experiments to exhibit complex patterns or to improve statistical power is a typical aim of data integration. The starting point of the statistical analysis often comes as sets of p-values…
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other. In this process, one can induce event complexes that organize multi-granular events with temporal order…
A remarkable ability of human beings resides in compositional reasoning, i.e., the capacity to make "infinite use of finite means". However, current large vision-language foundation models (VLMs) fall short of such compositional abilities…
Video-LLMs have improved steadily on semantic perception, but they still fall short on predictive world modeling, which is central to physically grounded intelligence. We introduce HOCA-Bench, a benchmark that frames physical anomalies…
The creation and detection of entanglement in solid state electronics is of fundamental importance for quantum information processing. We prove that second-order quantum correlations can be always interpreted classically and propose a…
Much recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic…
Video Question Answering (VideoQA) is a very attractive and challenging research direction aiming to understand complex semantics of heterogeneous data from two domains, i.e., the spatio-temporal video content and the word sequence in…
Visual Language Models (VLMs) show remarkable performance in visual reasoning tasks, successfully tackling college-level challenges that require high-level understanding of images. However, some recent reports of VLMs struggling to reason…
The field of natural language understanding has experienced exponential progress in the last few years, with impressive results in several tasks. This success has motivated researchers to study the underlying knowledge encoded by these…
Over the years, performance evaluation has become essential in computer vision, enabling tangible progress in many sub-fields. While talking-head video generation has become an emerging research topic, existing evaluations on this topic…