arXiv:2307.13352v3 Announce Type: replace Abstract: Adversarial attacks pose a major challenge to distributed learning systems, prompting the development of numerous robust learning methods. However, most existing approaches suffer from the curse of dimensionality, i.e. the error increases with the number…
arXiv:2511.13880v1 Announce Type: new Abstract: This paper studies the problem of class-incremental learning (CIL), a core setting within continual learning where a model learns a sequence of tasks, each containing a distinct set of classes. Traditional CIL methods, which do…
arXiv:2501.01558v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly relied on in AI systems, predicting when they make mistakes is crucial. While a great deal of work in the field uses internal representations to interpret model behavior,…
arXiv:2511.13888v1 Announce Type: new Abstract: Investment planning in power utilities, such as generation and transmission expansion, requires decade-long forecasts under profound uncertainty. Forecasting of energy mix and energy use decades ahead is nontrivial. Classical approaches focus on generating a finite…
The virtual VideoCAD tool could boost designers’ productivity and help train engineers learning computer-aided design.
arXiv:2407.04055v2 Announce Type: replace-cross Abstract: The prediction modeling of drug-target interactions is crucial to drug discovery and design, which has seen rapid advancements owing to deep learning technologies. Recently developed methods, such as those based on graph neural networks (GNNs)…
arXiv:2511.10094v2 Announce Type: replace Abstract: Although recent generative models are remarkably capable of producing instruction-following and realistic outputs, they remain prone to notable physical plausibility failures. Though critical in applications, these physical plausibility errors often escape detection by existing evaluation…
arXiv:2411.15127v3 Announce Type: replace Abstract: Sensing human motions through Inertial Measurement Units (IMUs) embedded in personal devices has enabled significant applications in health and wellness. Labeled IMU data is scarce, however, unlabeled or weakly labeled IMU data can be used…
arXiv:2505.08915v2 Announce Type: replace Abstract: Recent experiments have shown that training trajectories of multiple deep neural networks with different architectures, optimization algorithms, hyper-parameter settings, and regularization methods evolve on a remarkably low-dimensional “hyper-ribbon-like” manifold in the space of probability distributions.…
arXiv:2511.14295v1 Announce Type: cross Abstract: We present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed…
