arXiv:2510.07191v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has advanced visual representation learning, but its value in chest radiography, a high-volume imaging modality with fine-grained findings, remains unclear. Meta’s DINOv3 extends earlier SSL models through Gram-anchored self-distillation. Whether these design choices improve transfer learning for chest radiography has not been systematically tested. We benchmarked DINOv3 […]
Growth, yield and quality response of two industrial potato cultivars to chelated potassium and humic acid during fall season
arXiv:2512.19766v1 Announce Type: new Abstract: The study was carried out to known the response of two industrial potato cultivars (Hermes, and Challenger) Netherlands origin, to chelated potassium fertilizer and humic acid due to growth, yield and quality in the fall season of 2024, planted in an open field of the educational field of Horticulture Department, […]
Evasion-Resilient Detection of DNS-over-HTTPS Data Exfiltration: A Practical Evaluation and Toolkit
arXiv:2512.20423v1 Announce Type: cross Abstract: The purpose of this project is to assess how well defenders can detect DNS-over-HTTPS (DoH) file exfiltration, and which evasion strategies can be used by attackers. While providing a reproducible toolkit to generate, intercept and analyze DoH exfiltration, and comparing Machine Learning vs threshold-based detection under adversarial scenarios. The originality […]
SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization
arXiv:2512.20482v1 Announce Type: cross Abstract: Maintaining large-scale, multilingual codebases hinges on accurately localizing issues, which requires mapping natural-language error descriptions to the relevant functions that need to be modified. However, existing ranking approaches are often Python-centric and perform a single-pass search over the codebase. This work introduces SweRank+, a framework that couples SweRankMulti, a cross-lingual […]
Cube Bench: A Benchmark for Spatial Visual Reasoning in MLLMs
arXiv:2512.20595v1 Announce Type: cross Abstract: We introduce Cube Bench, a Rubik’s-cube benchmark for evaluating spatial and sequential reasoning in multimodal large language models (MLLMs). The benchmark decomposes performance into five skills: (i) reconstructing cube faces from images and text, (ii) choosing the optimal next move, (iii) predicting the outcome of a candidate move without applying […]
Phenotype-structuring of non-local kinetic models of cell migration driven by environmental sensing
arXiv:2412.16258v3 Announce Type: replace Abstract: The capability of cells to form surface extensions to non-locally probe the surrounding environment plays a key role in cell migration. The existing mathematical models for migration of cell populations driven by this non-local form of environmental sensing rely on the simplifying assumption that cells in the population share the […]
Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems
arXiv:2511.18417v2 Announce Type: replace-cross Abstract: We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural networks. Equivariance is formulated as naturality in a topological category with Radon measures. Formulating linear and nonlinear layers in the categorical setup, we prove the equivariant universal approximation theorem in the […]
Trust Semantics Distillation for Collaborator Selection via Memory-Augmented Agentic AI
arXiv:2509.08151v2 Announce Type: replace Abstract: Offloading computational tasks from resource-constrained devices to resource-abundant peers constitutes a critical paradigm for collaborative computing. Within this context, accurate trust evaluation of potential collaborating devices is essential for the effective execution of complex computing tasks. This trust evaluation process involves collecting diverse trust-related information from every potential collaborator and […]
ScoutGPT: Capturing Player Impact from Team Action Sequences Using GPT-Based Framework
arXiv:2512.17266v2 Announce Type: replace Abstract: Transfers play a pivotal role in shaping a football club’s success, yet forecasting whether a transfer will succeed remains difficult due to the strong context-dependence of on-field performance. Existing evaluation practices often rely on static summary statistics or post-hoc value models, which fail to capture how a player’s contribution adapts […]
Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models
arXiv:2505.02824v2 Announce Type: replace-cross Abstract: Text-to-image (T2I) diffusion models enable high-quality image generation conditioned on textual prompts. However, fine-tuning these pre-trained models for personalization raises concerns about unauthorized dataset usage. To address this issue, dataset ownership verification (DOV) has recently been proposed, which embeds watermarks into fine-tuning datasets via backdoor techniques. These watermarks remain dormant […]