Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 11738v1 Announce Type: cross Abstract: Multimodal Large Language Model (MLLM)-based UAV aerial image understanding and reasoning is essential for aerial intelligence yet poses distinct challenges arising from extreme scale variation, arbitrary camera orientations, and high object density.
arXiv:2608. 11891v1 Announce Type: cross Abstract: Governments increasingly fund indigenous foundation models to strengthen national AI capability, digital sovereignty, and multilingual computing.
arXiv:2608. 11884v1 Announce Type: cross Abstract: Quantum generative adversarial networks (QGANs) have attracted increasing attention for image generation using parameterized quantum circuits.
arXiv:2608. 11860v1 Announce Type: cross Abstract: Data-driven inverse design enables efficient generation of nanophotonic structures with prescribed optical responses, but spectrum-to-geometry mapping remains challenging due to non-uniqueness and fine geometric features.
arXiv:2608. 11980v1 Announce Type: cross Abstract: Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence.
arXiv:2608. 12083v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) achieve strong predictive performance on graph-structured data across domains such as chemistry, biology, and network analysis, yet they provide no intrinsic explanation of their predictions.
arXiv:2608. 12196v1 Announce Type: cross Abstract: Purpose: Deep learning-based medical image segmentation has achieved remarkable success, yet purely data-driven approaches often fail to exploit the rich mathematical structure inherent in medical images.
arXiv:2608. 12246v1 Announce Type: cross Abstract: Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VICs) - the commits that first introduce vulnerabilities into codebases.
arXiv:2608. 12299v1 Announce Type: cross Abstract: Class activation mapping (CAM) is one of the most widely used visual explanation families in explainable artificial intelligence.
arXiv:2608. 12290v1 Announce Type: cross Abstract: Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows.
arXiv:2608. 12278v1 Announce Type: cross Abstract: Artificial intelligence tools for education and language support are increasingly framed as scalable responses to access gaps in under-resourced communities.
arXiv:2509. 13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets.
arXiv:2601. 16083v2 Announce Type: replace-cross Abstract: Computing the conditional mode of a distribution, better known as the maximum a posteriori (MAP) assignment, is a fundamental task in probabilistic inference.
arXiv:2506. 17332v2 Announce Type: replace-cross Abstract: By 2050, people aged 65 and over are projected to make up 16% of the global population.
arXiv:2511. 20597v2 Announce Type: replace-cross Abstract: The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models.
arXiv:2608. 11342v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in settings such as personalization, where each author requires separate weight access, optimization, storage, and retraining, its costs become prohibitive.
arXiv:2608. 11423v1 Announce Type: new Abstract: Robust comparisons of federated aggregation methods require joint consideration of predictive performance, threat definitions, metric semantics, and execution provenance.
arXiv:2608. 11567v1 Announce Type: new Abstract: In real-world scenarios, the training data usually contains redundant features, label noise and feature noise, which provide severe challenges for the efficiency of machine learning methods.
arXiv:2608. 11690v1 Announce Type: new Abstract: Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting.
arXiv:2608. 11839v1 Announce Type: new Abstract: Poor air quality in urban areas is driven by a complex chain of processes and presents a significant public health concern.