Stay updated with the latest research and technology news
arXiv:2602.12150v1 Announce Type: new Abstract: Do Large Language Models (LLMs) possess a Theory of Mind (ToM)? Research into this question has focused on evaluating LLMs...
arXiv:2602.12147v1 Announce Type: new Abstract: Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation. However, we...
arXiv:2602.12146v1 Announce Type: new Abstract: Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such...
arXiv:2602.12144v1 Announce Type: new Abstract: AI coding agents are increasingly contributing to software development, yet their impact on mobile development has received little empirical attention....
arXiv:2602.12143v1 Announce Type: new Abstract: As comprehensive large model evaluation becomes prohibitively expensive, predicting model performance from limited observations has become essential. However, existing statistical...
arXiv:2602.12139v1 Announce Type: new Abstract: Transformers excel at time series modelling through attention mechanisms that capture long-term temporal patterns. However, they assume uniform time intervals...
arXiv:2602.12138v1 Announce Type: new Abstract: Federated Learning has been popularized in recent years for applications involving personal or sensitive data, as it allows the collaborative...
arXiv:2602.12136v1 Announce Type: new Abstract: Blue-collar work is often highly collaborative, embodied, and situated in shared physical environments, yet most research on collaborative AI has...
arXiv:2602.12135v1 Announce Type: new Abstract: With the rapid integration of advanced reasoning capabilities into spoken dialogue models, the field urgently demands benchmarks that transcend simple...
arXiv:2602.12134v1 Announce Type: new Abstract: Existing work on value alignment typically characterizes value relations statically, ignoring how interventions - such as prompting, fine-tuning, or preference...
arXiv:2602.12133v1 Announce Type: new Abstract: This study quantifies gender and skin-tone bias in two widely deployed commercial image generators - Gemini Flash 2.5 Image (NanoBanana)...
arXiv:2602.12132v1 Announce Type: new Abstract: Language models and software tools are essential to support the continuing vitality of lesser-used languages; however, currently popular neural models...
arXiv:2602.12129v1 Announce Type: new Abstract: Personalized book recommendation in Bangla literature has been constrained by the lack of structured, large-scale, and publicly available datasets. This...
arXiv:2602.12128v1 Announce Type: new Abstract: The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens....
arXiv:2602.12127v1 Announce Type: new Abstract: Image-to-poster generation is a high-demand task requiring not only local adjustments but also high-level design understanding. Models must generate text,...
arXiv:2602.12126v1 Announce Type: new Abstract: Temporal graphs represent networks in which connections change over time, with edges available only at specific moments. Motivated by applications...
arXiv:2602.12125v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns the student with the teacher's logit distribution on student-generated trajectories, has demonstrated strong empirical gains...
arXiv:2602.12124v1 Announce Type: new Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk is emerging:...
arXiv:2602.12123v1 Announce Type: new Abstract: Demonstration selection is a practical bottleneck in in-context learning (ICL): under a tight prompt budget, accuracy can change substantially depending...
arXiv:2602.12121v1 Announce Type: new Abstract: We study low T-phase-rank approximation of sectorial third-order tensors $\mathscr{A}\in\mathbb{C}^{n\times n\times p}$ under the tensor T-product. We introduce canonical T-phases...
arXiv:2602.12120v1 Announce Type: new Abstract: Many universities face increasing financial pressure and rely on accurate forecasts of commencing enrolments. However, enrolment forecasting in higher education...
arXiv:2602.12118v1 Announce Type: new Abstract: We study a multi-agent contracting problem where agents exert costly effort to achieve individually observable binary outcomes. While the principal...
arXiv:2602.12117v1 Announce Type: new Abstract: Tropical cyclones (TC) are among the most destructive natural disasters, causing catastrophic damage to coastal regions through extreme winds, heavy...
arXiv:2602.12116v1 Announce Type: new Abstract: Personalized alignment of large language models seeks to adapt responses to individual user preferences, typically via reinforcement learning. A key...