Related papers: ZIA: A Theoretical Framework for Zero-Input AI
Effective human-agent interaction (HAI) relies on accurate and adaptive perception of human emotional states. While multimodal deep learning models - leveraging facial expressions, speech, and textual cues - offer high accuracy in emotion…
We consider the problem of Visual Question Answering (VQA). Given an image and a free-form, open-ended, question, expressed in natural language, the goal of VQA system is to provide accurate answer to this question with respect to the…
Quantizing deep models prior to deployment is a widely adopted technique to speed up inference for various real-time applications, such as autonomous driving. However, quantized models often suffer from severe performance degradation in…
The vision of the upcoming 6G technologies, characterized by ultra-dense network, low latency, and fast data rate is to support Pervasive AI (PAI) using zero-touch solutions enabling self-X (e.g., self-configuration, self-monitoring, and…
Anticipating future actions based on spatiotemporal observations is essential in video understanding and predictive computer vision. Moreover, a model capable of anticipating the future has important applications, it can benefit…
In recent years, the integration of vision and language understanding has led to significant advancements in artificial intelligence, particularly through Vision-Language Models (VLMs). However, existing VLMs face challenges in handling…
In minimally invasive surgery, clinical decisions depend on real-time visual interpretation, yet intraoperative perception varies substantially across surgeons and procedures. This variability limits consistent assessment, training, and the…
The integration of Artificial Intelligence (AI) into automation systems has the potential to enhance efficiency and to address currently unsolved existing technical challenges. However, the industry-wide adoption of AI is hindered by the…
Transformers have achieved remarkable success in medical image analysis owing to their powerful capability to use flexible self-attention mechanism. However, due to lacking intrinsic inductive bias in modeling visual structural information,…
Training robust world models requires large-scale, precisely labeled multimodal datasets, a process historically bottlenecked by slow and expensive manual annotation. We present a production-tested GAZE pipeline that automates the…
Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a…
Learning predictive world models from unlabelled video is a foundational challenge in artificial intelligence. While Joint Embedding Predictive Architectures (JEPA) have set new benchmarks in semantic classification, they often remain…
Developing effective multimodal data fusion strategies has become increasingly essential for improving the predictive power of statistical machine learning methods across a wide range of applications, from autonomous driving to medical…
Integrated sensing and communication (ISAC) is a promising solution to accelerate edge inference via the dual use of wireless signals. However, this paradigm needs to minimize the inference error and latency under ISAC co-functionality…
As AI becomes embedded in customer-facing systems, ethical scrutiny has largely focused on models, data, and governance. Far less attention has been paid to how AI is experienced through user-facing design. This commentary argues that many…
To efficiently process visual data at scale, researchers have proposed two techniques for lowering the computational overhead associated with the underlying deep learning models. The first approach consists of leveraging a specialized,…
The proliferation of artificial intelligence provides an opportunity to create psychological spaciousness in society. Spaciousness is defined as the ability to hold diverse interpersonal interactions and forms the basis for vulnerability…
To model real-world software systems, modelling paradigms should support a form of compositionality. In interface theory and model-based testing with inputs and outputs, conjunctive operators have been introduced: the behaviour allowed by…
Information comes in diverse modalities. Multimodal native AI models are essential to integrate real-world information and deliver comprehensive understanding. While proprietary multimodal native models exist, their lack of openness imposes…
Cloud-based Artificial Intelligence (AI) inference is increasingly latency- and context-sensitive, yet today's AI-as-a-Service is typically consumed as an application-chosen endpoint, leaving the network to provide only best-effort…