Data processing in robotics is currently challenged by the effective building of multimodal and common representations. Tremendous volumes of raw data are available and their smart management is the core concept of multimodal learning in a new paradigm for data fusion. Although several techniques for building multimodal representations have been proven successful, they have not yet been analyzed and compared in a given production setting. This paper explored three of the most common techniques, (1) the late fusion, (2) the early fusion, and (3) the sketch, and compared them in classification tasks. Our paper explored different types of data (modalities) that could be gathered by sensors serving a wide range of sensor applications. Our experiments were conducted on Amazon Reviews, MovieLens25M, and Movie-Lens1M datasets. Their outcomes allowed us to confirm that the choice of fusion technique for building multimodal representation is crucial to obtain the highest possible model performance resulting from the proper modality combination. Consequently, we designed criteria for choosing this optimal data fusion technique.

In this work, we have prepared a series of polydimethylsiloxane (PDMS) composites containing various graphene flakes loadings (0.02–2 wt%), and their broadband optical properties are being investigated. We demonstrate the tunability and evolution of transmittance and reflection spectra of the composites in a wide spectral range (0.4–200 μm) as a function of graphene content. Using these data we derive the broadband wavelength-dependent absorption coefficient (α) values. Our results show that α is roughly constant in the visible and IR ranges, and, surprisingly, is approximately one order of magnitude lower in the terahertz regime, suggesting different terahertz radiation scattering mechanism in our composite. Our material could be useful for applications in optical communication, sensing or ultrafast photonics.

We propose a method for monitoring the large-scale homogeneity of the reduction process of graphene oxide. For this purpose, a Raman mapping technique is employed to probe the evolution of the phonon properties of two different graphene oxide (GO) thin films upon controllable thermal reduction. The reduction of GO is reflected by the upshift of the statistical distribution of the relative intensity ratio of the G and D peaks ( I _D / I _G ) of the Raman spectra and is consistent with the ratio obtained for chemically reduced GO. In addition, the shifts of the position distributions of the main Raman modes ( ω D , ω G ) and their cross-correlation with the I _D / I _G ratio provides evidence of a change of the doping level, demonstrating the influence of reduction processes on GO films.

Research into fake news detection has a long history, although it gained significant attention following the 2016 US election. During this time, the widespread use of social media and the resulting increase in interpersonal communication led to the extensive spread of ambiguous and potentially misleading news. Traditional approaches, relying solely on pre- LLM (large language model) techniques and addressing the issue as a simple classification problem, have shown to be insufficient for improving detection accuracy. In this context, large language models have become crucial, as their advanced architectures overcome the limitations of pre-LLM methods, which often fail to capture the subtleties of fake news. This literature review aims to shed light on the field of fake news detection by providing a brief historical overview, defining fake news, reviewing detection methods used before the advent of large language models, and discussing the strengths and weaknesses of these models in an increasingly complex landscape. Furthermore, it will emphasize the importance of using multimodal datasets in the effort to detect fake news.