Search

Multiple Sclerosis (MS) is a chronic disease characterized by progressive or alternate impairment of neurological functions (motor, sensory, visual, and cognitive). Predicting disease progression with a probabilistic and time-dependent approach might help in suggesting interventions that can delay the progression of the disease. However, extracting informative knowledge from irregularly collected longitudinal data is difficult, and missing data pose significant challenges. MS progression is measured through the Expanded Disability Status Scale (EDSS), which quantifies and monitors disability in MS over time. EDSS assesses impairment in eight functional systems (FS). Frequently, only the EDSS score assigned by clinicians is reported, while FS sub-scores are missing. Imputing these scores might be useful, especially to stratify patients according to their phenotype assessed over the disease progression. This study aimed at i) exploring different methodologies for imputing missing FS sub-scores, and ii) predicting the EDSS score using complete clinical data. Results show that Exponential Weighted Moving Average achieved the lowest error rate in the missing data imputation task; furthermore, the combination of Classification and Regression Trees for the imputation and SVM for the prediction task obtained the best accuracy., Comment: 6 pages, 3 tables

Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to specific robotic embodiments. To address this, Visual-Language-Action (VLA) models have emerged, yet they face challenges in long-horizon spatial reasoning and grounded task planning. In this work, we propose the Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning, Emma-X. Emma-X leverages our constructed hierarchical embodiment dataset based on BridgeV2, containing 60,000 robot manipulation trajectories auto-annotated with grounded task reasoning and spatial guidance. Additionally, we introduce a trajectory segmentation strategy based on gripper states and motion trajectories, which can help mitigate hallucination in grounding subtask reasoning generation. Experimental results demonstrate that Emma-X achieves superior performance over competitive baselines, particularly in real-world robotic tasks requiring spatial reasoning., Comment: https://github.com/declare-lab/Emma-X, https://huggingface.co/declare-lab/Emma-X

This paper proposes a metalens designed to work in 3.3 {\mu}m wavelength which resides in the mid-IR region. The metasurface was created using MoS2 nanopillars taking advantage of high refractive index and low loss. It could be used to make compact optical Methane gas sensors.

In recent years, drone detection has quickly become a subject of extreme interest: the potential for fast-moving objects of contained dimensions to be used for malicious intents or even terrorist attacks has posed attention to the necessity for precise and resilient systems for detecting and identifying such elements. While extensive literature and works exist on object detection based on RGB data, it is also critical to recognize the limits of such modality when applied to UAVs detection. Detecting drones indeed poses several challenges such as fast-moving objects and scenes with a high dynamic range or, even worse, scarce illumination levels. Neuromorphic cameras, on the other hand, can retain precise and rich spatio-temporal information in situations that are challenging for RGB cameras. They are resilient to both high-speed moving objects and scarce illumination settings, while prone to suffer a rapid loss of information when the objects in the scene are static. In this context, we present a novel model for integrating both domains together, leveraging multimodal data to take advantage of the best of both worlds. To this end, we also release NeRDD (Neuromorphic-RGB Drone Detection), a novel spatio-temporally synchronized Event-RGB Drone detection dataset of more than 3.5 hours of multimodal annotated recordings., Comment: Accepted at NeVi Workshop at ECCV24

Multimodal key information extraction (KIE) models have been studied extensively on semi-structured documents. However, their investigation on unstructured documents is an emerging research topic. The paper presents an approach to adapt a multimodal transformer (i.e., ViBERTgrid previously explored on semi-structured documents) for unstructured financial documents, by incorporating a BiLSTM-CRF layer. The proposed ViBERTgrid BiLSTM-CRF model demonstrates a significant improvement in performance (up to 2 percentage points) on named entity recognition from unstructured documents in financial domain, while maintaining its KIE performance on semi-structured documents. As an additional contribution, we publicly released token-level annotations for the SROIE dataset in order to pave the way for its use in multimodal sequence labeling models., Comment: Accepted in MIDAS (The 8th Workshop on MIning DAta for financial applicationS) workshop of ECML PKDD 2023 conference

Access to mental health support remains limited, particularly in marginalized communities where structural and cultural barriers hinder timely care. This paper explores the potential of AI-enabled chatbots as a scalable solution, focusing on advanced large language models (LLMs)-GPT v4, Mistral Large, and LLama V3.1-and assessing their ability to deliver empathetic, meaningful responses in mental health contexts. While these models show promise in generating structured responses, they fall short in replicating the emotional depth and adaptability of human therapists. Additionally, trustworthiness, bias, and privacy challenges persist due to unreliable datasets and limited collaboration with mental health professionals. To address these limitations, we propose a federated learning framework that ensures data privacy, reduces bias, and integrates continuous validation from clinicians to enhance response quality. This approach aims to develop a secure, evidence-based AI chatbot capable of offering trustworthy, empathetic, and bias-reduced mental health support, advancing AI's role in digital mental health care., Comment: 17 pages, 9 Figures

The stacking order of two-dimensional transition metal dichalcogenides (TMDs) is attracting tremendous interest as an essential component of van der Waals heterostructures. A common and fast approach to distinguish between the AAprime (2H) and AB (3R) configurations uses the relative edge orientation of each triangular layer (theta) from optical images. Here, we highlight that this method alone is not sufficient to fully identify the stacking order. Instead we propose a model and methodology to accurately determine the bilayer configuration of WSe2 using second harmonic generation (SHG) and Raman spectroscopy. We demonstrate that the SHG response of the AB phase (theta = 0) deg layers is more intense than the signal from the single layer structure. However, the SHG totally vanishes in the AAprime and ABprime phases (theta = 60 deg) and 0 deg respectively) of homo-bilayer WSe2. Also, several optical features of homo-bilayer WSe2 are found to depend on the details of the stacking order, with the difference being the clearest in the low frequency (LF) Raman frequencies, as confirmed by DFT simulation. This allows unambiguous, high-throughput, nondestructive identification of stacking order in TMDs, which is not robustly addressed in this emerging research area.

We present volume-limited samples of cataclysmic variables (CVs) and AM CVn binaries jointly selected from SRG/eROSITA eRASS1 and \textit{Gaia} DR3 using an X-ray + optical color-color diagram (the ``X-ray Main Sequence"). This tool identifies all CV subtypes, including magnetic and low-accretion rate systems, in contrast to most previous surveys. We find 23 CVs, 3 of which are AM CVns, out to 150 pc in the Western Galactic Hemisphere. Our 150 pc sample is spectroscopically verified and complete down to $L_X = 1.3\times 10^{29} \;\textrm{erg s}^{-1}$ in the 0.2--2.3 keV band, and we also present CV candidates out to 300 pc and 1000 pc. We discovered two previously unknown systems in our 150 pc sample: the third nearest AM CVn and a magnetic period bouncer. We find the mean $L_X$ of CVs to be $\langle L_X \rangle \approx 4.6\times 10^{30} \;\textrm{erg s}^{-1}$, in contrast to previous surveys which yielded $\langle L_X \rangle \sim 10^{31}-10^{32} \;\textrm{erg s}^{-1}$. We construct X-ray luminosity functions that, for the first time, flatten out at $L_X\sim 10^{30} \; \textrm{erg s}^{-1}$. We find average number, mass, and luminosity densities of $\rho_\textrm{N, CV} = (3.7 \pm 0.7) \times 10^{-6} \textrm{pc}^{-3}$, $\rho_M = (5.0 \pm 1.0) \times 10^{-5} M_\odot^{-1}$, and $\rho_{L_X} = (2.3 \pm 0.4) \times 10^{26} \textrm{erg s}^{-1}M_\odot^{-1}$, respectively, in the solar neighborhood. Our uniform selection method also allows us to place meaningful estimates on the space density of AM CVns, $\rho_\textrm{N, AM CVn} = (5.5 \pm 3.7) \times 10^{-7} \textrm{pc}^{-3}$. Magnetic CVs and period bouncers make up $35\%$ and $25\%$ of our sample, respectively. This work, through a novel discovery technique, shows that the observed number densities of CVs and AM CVns, as well as the fraction of period bouncers, are still in tension with population synthesis estimates., Comment: Submitted to PASP, comments welcome

In today's era, where large language models (LLMs) are integrated into numerous real-world applications, ensuring their safety and robustness is crucial for responsible AI usage. Automated red-teaming methods play a key role in this process by generating adversarial attacks to identify and mitigate potential vulnerabilities in these models. However, existing methods often struggle with slow performance, limited categorical diversity, and high resource demands. While Rainbow Teaming, a recent approach, addresses the diversity challenge by framing adversarial prompt generation as a quality-diversity search, it remains slow and requires a large fine-tuned mutator for optimal performance. To overcome these limitations, we propose Ferret, a novel approach that builds upon Rainbow Teaming by generating multiple adversarial prompt mutations per iteration and using a scoring function to rank and select the most effective adversarial prompt. We explore various scoring functions, including reward models, Llama Guard, and LLM-as-a-judge, to rank adversarial mutations based on their potential harm to improve the efficiency of the search for harmful mutations. Our results demonstrate that Ferret, utilizing a reward model as a scoring function, improves the overall attack success rate (ASR) to 95%, which is 46% higher than Rainbow Teaming. Additionally, Ferret reduces the time needed to achieve a 90% ASR by 15.2% compared to the baseline and generates adversarial prompts that are transferable i.e. effective on other LLMs of larger size. Our codes are available at https://github.com/declare-lab/ferret.

With the proliferation of domain-specific models, model merging has emerged as a set of techniques that combine the capabilities of multiple models into one that can multitask without the cost of additional training. In this paper, we propose a new model merging technique, Drop and rEscaLe via sampLing with mAgnitude (DELLA-Merging), that employs a novel pruning technique, MAGPRUNE, which shows significant advantages over DARE and TIES. MAGPRUNE first ranks the parameters in order of their magnitude and assigns higher dropout probabilities (p) to parameters with lower ranks corresponding to lower magnitudes. To approximate the original embeddings, MAGPRUNE employs a rescaling operation on the parameters that survive the random dropping by 1/(1 - p). On three different expert models considered for merging (LM, Math, Code) and corresponding benchmark datasets (AlpacaEval, GSM8K, MBPP), DELLA shows an average improvement of 2.4 points over baseline methods employing delta parameter pruning (an improvement of 3.6 points over TIES, 1.2 points over DARE), and 11.1 points over the no-pruning baseline (TA). We release the source code at: https://github.com/declare-lab/della.

The Wide-field Spectroscopic Telescope (WST) is proposed as a new facility dedicated to the efficient delivery of spectroscopic surveys. This white paper summarises the initial concept as well as the corresponding science cases. WST will feature simultaneous operation of a large field-of-view (3 sq. degree), a high multiplex (20,000) multi-object spectrograph (MOS) and a giant 3x3 sq. arcmin integral field spectrograph (IFS). In scientific capability these requirements place WST far ahead of existing and planned facilities. Given the current investment in deep imaging surveys and noting the diagnostic power of spectroscopy, WST will fill a crucial gap in astronomical capability and work synergistically with future ground and space-based facilities. This white paper shows that WST can address outstanding scientific questions in the areas of cosmology; galaxy assembly, evolution, and enrichment, including our own Milky Way; origin of stars and planets; time domain and multi-messenger astrophysics. WST's uniquely rich dataset will deliver unforeseen discoveries in many of these areas. The WST Science Team (already including more than 500 scientists worldwide) is open to the all astronomical community. To register in the WST Science Team please visit https://www.wstelescope.com/for-scientists/participate, Comment: 194 pages, 66 figures. Comments are welcome (wstelescope@gmail.com)

The notion of robustness in XAI refers to the observed variations in the explanation of the prediction of a learned model with respect to changes in the input leading to that prediction. Intuitively, if the input being explained is modified slightly subtly enough so as to not change the prediction of the model too much, then we would expect that the explanation provided for that new input does not change much either. We argue that a combination through discriminative averaging of ensembles weak learners explanations can improve the robustness of explanations in ensemble methods.This approach has been implemented and tested with post-hoc SHAP method and Random Forest ensemble with successful results. The improvements obtained have been measured quantitatively and some insights into the explicability robustness in ensemble methods are presented., Comment: 8 pages, 10 figures

Straintronics involves the manipulation and regulation of the electronic characteristics of 2D materials through the use of macro- and nano-scale strain engineering. In this study, we utilized an atomic force microscope (AFM) coupled with an optical system to perform indentation measurements and tip-enhanced photoluminescence (TEPL), allowing us to extract the local optical response of a suspended monolayer membrane of ternary WSSe at various levels of deformation, up to strains of 10%. The photoluminescence signal is modelled considering the deformation, stress distribution and strain dependence of the WSSe band structure. We observe an additional TEPL signal that exhibits significant variation under strain, with 64 meV per percent of elongation. This peak is linked to the highly strained 2D material lying right underneath the tip. We discuss the amplification of the signal and its relation to the excitonic funnelling effect in a more comprehensive model. We will also compare the diffusion caused by Auger recombination against the radiative excitonic decay. We use TEPL to examine and comprehend the local physics of 2D semi-conducting materials subjected to extreme mechanical strain. Chemical vapour deposition-fabricated 2D ternaries possess high strain resistance, comparable to the benchmark MoS2, and a high Young's modulus of 273 GPa.

Large Language Models (LLMs), as the case of OpenAI ChatGPT-4 Turbo, are revolutionizing several industries, including higher education. In this context, LLMs can be personalized through a fine-tuning process to meet the student demands on every particular subject, like statistics. Recently, OpenAI has launched the possibility to fine-tune their model with a natural language web interface, enabling the possibility to create customized GPT version deliberately conditioned to meet the demands of a specific task. The objective of this research is to assess the potential of the customized GPTs that have recently been launched by OpenAI. After developing a Business Statistics Virtual Professor (BSVP), tailored for students at the Universidad Pontificia Comillas, its behavior was evaluated and compared with that of ChatGPT-4 Turbo. The results lead to several conclusions. Firstly, a substantial modification in the style of communication was observed. Following the instructions it was trained with, BSVP provided responses in a more relatable and friendly tone, even incorporating a few minor jokes. Secondly, and this is a matter of relevance, when explicitly asked for something like, "I would like to practice a programming exercise similar to those in R practice 4," BSVP was capable of providing a far superior response: having access to contextual documentation, it could fulfill the request, something beyond ChatGPT-4 Turbo's capabilities. On the downside, the response times were generally higher. Lastly, regarding overall performance, quality, depth, and alignment with the specific content of the course, no statistically significant differences were observed in the responses between BSVP and ChatGPT-4 Turbo. It appears that customized assistants trained with prompts present advantages as virtual aids for students, yet they do not constitute a substantial improvement over ChatGPT-4 Turbo., Comment: 9 pages, 1 figure, 1 table

Conditional Imitation learning is a common and effective approach to train autonomous driving agents. However, two issues limit the full potential of this approach: (i) the inertia problem, a special case of causal confusion where the agent mistakenly correlates low speed with no acceleration, and (ii) low correlation between offline and online performance due to the accumulation of small errors that brings the agent in a previously unseen state. Both issues are critical for state-aware models, yet informing the driving agent of its internal state as well as the state of the environment is of crucial importance. In this paper we propose a multi-task learning agent based on a multi-stage vision transformer with state token propagation. We feed the state of the vehicle along with the representation of the environment as a special token of the transformer and propagate it throughout the network. This allows us to tackle the aforementioned issues from different angles: guiding the driving policy with learned stop/go information, performing data augmentation directly on the state of the vehicle and visually explaining the model's decisions. We report a drastic decrease in inertia and a high correlation between offline and online metrics., Comment: Submitted to IEEE Transactions on Intelligent Vehicles

Sophorolipids are well-known scaled-up microbial glycolipid biosurfactants with a strong potential for commercialization due to their biological origin and mildness in contact with the skin and the environment compared to classical surfactants. However, their association properties in water are still poorly understood, they cannot be predicted and their behavior in solution challenges half a century of knowledge generated in the field of surfactant science. By studying forty different types of sophorolipids and sophorosides in water using small angle X-ray scattering, and optical and cryogenic transmission electron microscopy, this work provides better understanding of their structure-property relationship and identifies which chemical groups in their molecular structure have a critical influence on their self-assembly properties. Structural features like the number of sugar headgroups, acetylation, end-chain functional group, (un)saturation, lactonization and length of chain are adjusted to both rationalize their impact and understand their effect on self-assembly. The number of sugar groups, pH, (un)saturation and lactonization were found to have a critical impact on sophorolipid self-assembly. The chemical nature of the end-chain functional group and chain length were also found to have a possibly critical impact, depending on the specific type of chemical function (COOH and long chains are critical). Mono- and diacetylation, as well as the position of sophorose in the fatty acid ($\omega$, $\omega$-1), are not critical, i.e., they did not significantly influence sophorolipid self-assembly.

The growth of bilayers of two-dimensional (2D) materials on conventional 3D semiconductors results in 2D/3D hybrid heterostructures, which can provide additional advantages over more established 3D semiconductors while retaining some specificities of 2D materials. Understanding and exploiting these phenomena hinge on knowing the electronic properties and the hybridization of these structures. Here, we demonstrate that rhombohedral-stacked bilayer (AB stacking) can be obtained by molecular beam epitaxy growth of tungsten diselenide (WSe2) on gallium phosphide (GaP) substrate. We confirm the presence of 3R-stacking of the WSe2 bilayer structure using scanning transmission electron microscopy (STEM) and micro-Raman spectroscopy. Also, we report high-resolution angle-resolved photoemission spectroscopy (ARPES) on our rhombohedral-stacked WSe2 bilayer grown on GaP(111)B substrate. Our ARPES measurements confirm the expected valence band structure of WSe2 with the band maximum located at the gamma point of the Brillouin zone. The epitaxial growth of WSe2 on GaP(111)B heterostructures paves the way for further studies of the fundamental properties of these complex materials, as well as prospects for their implementation in devices to exploit their promising electronic and optical properties., Comment: 5 figures

Recently, intriguing physical properties have been unraveled in anisotropic semiconductors, in which the in-plane electronic band structure anisotropy often originates from the low crystallographic symmetry. The atomic chain is the ultimate limit in material downscaling for electronics, a frontier for establishing an entirely new field of one-dimensional quantum materials. Electronic and structural properties of chain-like InTe are essential for better understanding of device applications such as thermoelectrics. Here, we use scanning tunneling microscopy/spectroscopy (STM/STS) measurements and density functional theory (DFT) calculations to directly image the in-plane structural anisotropy in tetragonal Indium Telluride (InTe). As results, we report the direct observation of one-dimensional In1+ chains in InTe. We demonstrate that InTe exhibits a band gap of about 0.40 +-0.02 eV located at the M point of the Brillouin zone. Additionally, line defects are observed in our sample, were attributed to In1+ chain vacancy along the c-axis, a general feature in many other TlSe-like compounds. Our STS and DFT results prove that the presence of In1+ induces localized gap state, located near the valence band maximum (VBM). This acceptor state is responsible for the high intrinsic p-type doping of InTe that we also confirm using angle-resolved photoemission spectroscopy., Comment: no

Two-dimensional (2D) ferroelectric (FE) materials are promising compounds for next-generation nonvolatile memories, due to their low energy consumption and high endurance. Among them, {\alpha}-In$_{2}$Se$_{3}$ has drawn particular attention due to its in- and out-of-plane ferroelectricity, whose robustness has been demonstrated down to the monolayer limit. This is a relatively uncommon behavior since most bulk FE materials lose their ferroelectric character at the 2D limit due to depolarization field. Using angle resolved photoemission spectroscopy (ARPES), we unveil another unusual 2D phenomena appearing in 2H \alpha-In$_{2}$Se$_{3}$ single crystals, the occurrence of a highly metallic two-dimensional electron gas (2DEG) at the surface of vacuum-cleaved crystals. This 2DEG exhibits two confined states which correspond to an electron density of approximatively 10$^{13}$ electrons/cm$^{3}$, also confirmed by thermoelectric measurements. Combination of ARPES and density functional theory (DFT) calculations reveals a direct band gap of energy equal to 1.3 +/- 0.1 eV, with the bottom of the conduction band localized at the center of the Brillouin zone, just below the Fermi level. Such strong n-type doping further supports the quantum confinement of electrons and the formation of the 2DEG., Comment: 20 pages, 12 figures