Bridging the sim-to-real gap remains a fundamental challenge in robotics, as accurate dynamic parameter estimation is essential for reliable model-based control, realistic simulation, and safe deployment of manipulators. Traditional analytical approaches often fall short when faced with complex robot structures and interactions. Data-driven methods offer a promising alternative, yet conventional neural networks such as recurrent models struggle to capture long-range dependencies critical for accurate estimation. In this study, we propose a Transformer-based approach for dynamic parameter estimation, supported by an automated pipeline that generates diverse robot models and enriched trajectory data using Jacobian-derived features. The dataset consists of 8,192 robots with varied inertial and frictional properties. Leveraging attention mechanisms, our model effectively captures both temporal and spatial dependencies. Experimental results highlight the influence of sequence length, sampling rate, and architecture, with the best configuration (sequence length 64, 64 Hz, four layers, 32 heads) achieving a validation R2 of 0.8633. Mass and inertia are estimated with near-perfect accuracy, Coulomb friction with moderate-to-high accuracy, while viscous friction and distal link center-of-mass remain more challenging. These results demonstrate that combining Transformers with automated dataset generation and kinematic enrichment enables scalable, accurate dynamic parameter estimation, contributing to improved sim-to-real transfer in robotic systems

Automatic Sign Language Recognition (ASLR) has emerged as a vital field for bridging the gap between deaf and hearing communities. However, the problem of sign-to-sign retrieval or detecting a specific sign within a sequence of continuous signs remains largely unexplored. We define this novel task as Sign Language Spotting. In this paper, we present a first step toward sign language retrieval by addressing the challenge of detecting the presence or absence of a query sign video within a sentence-level gloss or sign video. Unlike conventional approaches that rely on intermediate gloss recognition or text-based matching, we propose an end-to-end model that directly operates on pose keypoints extracted from sign videos. Our architecture employs an encoder-only backbone with a binary classification head to determine whether the query sign appears within the target sequence. By focusing on pose representations instead of raw RGB frames, our method significantly reduces computational cost and mitigates visual noise. We evaluate our approach on the Word Presence Prediction dataset from the WSLP 2025 shared task, achieving 61.88\% accuracy and 60.00\% F1-score. These results demonstrate the effectiveness of our pose-based framework for Sign Language Spotting, establishing a strong foundation for future research in automatic sign language retrieval and verification. Code is available at https://github.com/EbimoJohnny/Pose-Based-Sign-Language-Spotting

Predicting protein secondary structures such as alpha helices, beta sheets, and coils from amino acid sequences is essential for understanding protein function. This work presents a transformer-based model that applies attention mechanisms to protein sequence data to predict structural motifs. A sliding-window data augmentation technique is used on the CB513 dataset to expand the training samples. The transformer shows strong ability to generalize across variable-length sequences while effectively capturing both local and long-range residue interactions.

Stock market prediction is a long-standing challenge in finance, as accurate forecasts support informed investment decisions. Traditional models rely mainly on historical prices, but recent work shows that financial news can provide useful external signals. This paper investigates a multimodal approach that integrates companies' news articles with their historical stock data to improve prediction performance. We compare a Graph Neural Network (GNN) model with a baseline LSTM model. Historical data for each company is encoded using an LSTM, while news titles are embedded with a language model. These embeddings form nodes in a heterogeneous graph, and GraphSAGE is used to capture interactions between articles, companies, and industries. We evaluate two targets: a binary direction-of-change label and a significance-based label. Experiments on the US equities and Bloomberg datasets show that the GNN outperforms the LSTM baseline, achieving 53% accuracy on the first target and a 4% precision gain on the second. Results also indicate that companies with more associated news yield higher prediction accuracy. Moreover, headlines contain stronger predictive signals than full articles, suggesting that concise news summaries play an important role in short-term market reactions.

Cartographic reasoning is the skill of interpreting geographic relationships by aligning legends, map scales, compass directions, map texts, and geometries across one or more map images. Although essential as a concrete cognitive capability and for critical tasks such as disaster response and urban planning, it remains largely unevaluated. Building on progress in chart and infographic understanding, recent large vision language model studies on map visual question-answering often treat maps as a special case of charts. In contrast, map VQA demands comprehension of layered symbology (e.g., symbols, geometries, and text labels) as well as spatial relations tied to orientation and distance that often span multiple maps and are not captured by chart-style evaluations. To address this gap, we introduce FRIEDA, a benchmark for testing complex open-ended cartographic reasoning in LVLMs. FRIEDA sources real map images from documents and reports in various domains and geographical areas. Following classifications in Geographic Information System (GIS) literature, FRIEDA targets all three categories of spatial relations: topological (border, equal, intersect, within), metric (distance), and directional (orientation). All questions require multi-step inference, and many require cross-map grounding and reasoning. We evaluate eleven state-of-the-art LVLMs under two settings: (1) the direct setting, where we provide the maps relevant to the question, and (2) the contextual setting, where the model may have to identify the maps relevant to the question before reasoning. Even the strongest models, Gemini-2.5-Pro and GPT-5-Think, achieve only 38.20% and 37.20% accuracy, respectively, far below human performance of 84.87%. These results reveal a persistent gap in multi-step cartographic reasoning, positioning FRIEDA as a rigorous benchmark to drive progress on spatial intelligence in LVLMs.

The challenges of ongoing war in Sudan highlight the need for rapid monitoring and analysis of such conflicts. Advances in deep learning and readily available satellite remote sensing imagery allow for near real-time monitoring. This paper uses 4-band imagery from Planet Labs with a deep learning model to show that fire damage in armed conflicts can be monitored with minimal delay. We demonstrate the effectiveness of our approach using five case studies in Sudan. We show that, compared to a baseline, the automated method captures the active fires and charred areas more accurately. Our results indicate that using 8-band imagery or time series of such imagery only result in marginal gains. Keywords: 1. Introduction The ongoing armed conflict in Sudan began in April 2023.

Abstract--This paper introduces SENSE (Shared Embedding for N-lingual Speech and tExt), an open-source solution inspired by the SAMU-XLSR framework and conceptually similar to Meta AI's SONAR models. These approaches rely on a teacher-student framework to align a self-supervised speech encoder with the language-agnostic continuous representations of a text encoder at the utterance level. We describe how the original SAMU-XLSR method has been updated by selecting a stronger teacher text model and a better initial speech encoder . The source code for training and using SENSE models has been integrated into the SpeechBrain toolkit, and the first SENSE model we trained has been publicly released. We report experimental results on multilingual and multimodal semantic tasks, where our SENSE model achieves highly competitive performance. Finally, this study offers new insights into how semantics are captured in such semantically aligned speech encoders. Speech foundation models based on self-supervised learning (SSL) have brought significant advances in speech processing. These models, such as wav2vec 2.0 [1], HuBERT [2], and WavLM [3], generate learned speech representations that can be applied to a wide range of downstream speech processing tasks. By training on large amounts of unlabelled speech data, SSL models have demonstrated the ability to capture crucial speech features, such as phonemes and other acoustic units [4]. This capability has led to significant progress in multiple downstream tasks, including speech recognition [1], speech translation [5], speech separation, speaker verification, speaker diarization [3], and emotion detection [6]. Different approaches have been proposed to pretrain model by aligning speech and text, like mSLAM [7], a Massively multilingual joint pre-training for speech and text.

International talks to revolutionise how the European Court of Human Rights handles migration cases will begin on Wednesday. The British government is urging partners to modernise the way states tackle the continent-wide illegal migration crisis. The talks are the most significant sign yet that international human rights law could be reinterpreted to make it easier for states to target people smuggling and set up'returns hubs' to hold people with no right to be in Europe. Writing ahead of the major meeting in Strasbourg, Sir Keir Starmer and Danish Prime Minister Mette Frederiksen said other nations should rethink human rights laws to make protecting borders easier. Critics say the ECHR is getting in the way of removing more illegal migrants, while supporters say claims about the ECHR's role in migration are exaggerated.

Google plans to launch smart glasses powered by artificial intelligence (AI) in 2026, after its previous high-profile attempt to enter the market ended in failure. The tech giant set expectations high in 2013 when it unveiled Google Glass, billed by some as the future of technology despite its odd appearance with a bulky screen positioned above the right eye. Google pulled the product in 2015 less than seven months after its UK release, but is now planning on re-entering the market with smart glasses with a cleaner look. But it comes after Meta has already made waves with its smart specs, which have sold two million pairs as of February. Google's new tech will let users interact with its own AI products, such as its chatbot Gemini.

A video game at the centre of a debate over artificial intelligence (AI) is in the running for the top prize at next year's Bafta Game Awards. Arc Raiders, from Swedish developer Embark Studios, has been a smash-hit since its October launch, selling more than four million copies. But the multiplayer shooter has been criticised for using text-to-speech tools to create additional lines, based on dialogue previously recorded by the game's actors. It is one of 10 titles longlisted for the prestigious best game award, with a shortlist to be announced in the run-up to April's annual ceremony. Other games up for the top prize include blockbusters Ghost of Yōtei and Death Stranding 2, indie games Hollow Knight: Silksong and Hades II, and indie adventure Blue Prince.