Related papers: Perception Matters: Enhancing Embodied AI with Unc…

We introduce uncertainty-aware object instance segmentation (UncOS) and demonstrate its usefulness for embodied interactive segmentation. To deal with uncertainty in robot perception, we propose a method for generating a hypothesis…

Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physical bodies that enable them to perceive, reason, and interact…

We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet. Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is…

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the…

A few decades of work in the AI field have focused efforts on developing a new generation of systems which can acquire knowledge via interaction with the world. Yet, until very recently, most such attempts were underpinned by research which…

Embodied AI development significantly lags behind large foundation models due to three critical challenges: (1) lack of systematic understanding of core capabilities needed for Embodied AI, making research lack clear objectives; (2) absence…

Embodied AI (EAI) agents continuously interact with the physical world, generating vast, heterogeneous multimodal data streams that traditional management systems are ill-equipped to handle. In this survey, we first systematically evaluate…

Multimodal Language Analysis is a demanding area of research, since it is associated with two requirements: combining different modalities and capturing temporal information. During the last years, several works have been proposed in the…

Deep-learning and large scale language-image training have produced image object detectors that generalise well to diverse environments and semantic classes. However, single-image object detectors trained on internet data are not optimally…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

Our brain can effortlessly recognize objects even when partially hidden from view. Seeing the visible of the hidden is called amodal completion; however, this task remains a challenge for generative AI despite rapid progress. We propose to…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

The widespread adoption of machine learning surrogate models has significantly improved the scale and complexity of systems and processes that can be explored accurately and efficiently using atomistic modeling. However, the inherently…

Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete optimization of text prompts through prompt engineering, or…

The diffusion of AI and big data is reshaping decision-making processes by increasing the amount of information that supports decisions while reducing direct interaction with data and empirical evidence. This paradigm shift introduces new…

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…

Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General Intelligence (AGI) and serves as a foundation for various applications (e.g., intelligent mechatronics systems, smart manufacturing) that bridge…

Unsupervised object discovery is commonly interpreted as the task of localizing and/or categorizing objects in visual data without the need for labeled examples. While current object recognition methods have proven highly effective for…