arXiv:2507.07947v3 Announce Type: replace Abstract: Recent advances in generative models, such as diffusion models, have raised concerns related to privacy, copyright infringement, and data stewardship. To better understand and control these risks, prior work has introduced techniques and attacks that…
arXiv:2512.01868v3 Announce Type: replace Abstract: We develop a mathematical framework that interprets Transformer attention as an interacting particle system and studies its continuum (mean-field) limits. By idealizing attention on the sphere, we connect Transformer dynamics to Wasserstein gradient flows, synchronization…
arXiv:2601.03332v1 Announce Type: new Abstract: Kolmogorov–Arnold Networks (KAN) replace scalar weights by learnable univariate functions, often implemented with B-splines. This design can be accurate and interpretable, but it makes inference expensive on CPU because each layer requires many spline evaluations.…
arXiv:2410.08925v4 Announce Type: replace Abstract: Prototypical part networks offer interpretable alternatives to black-box deep learning models by learning visual prototypes for classification. This work provides a comprehensive analysis of prototype formulations, comparing point-based and probabilistic approaches in both Euclidean and…
arXiv:2601.03327v1 Announce Type: new Abstract: Wildfires are highly imbalanced natural hazards in both space and severity, making the prediction of extreme events particularly challenging. In this work, we introduce the first ordinal classification framework for forecasting wildfire severity levels directly…
arXiv:2601.03329v1 Announce Type: new Abstract: Attention mechanisms represent a fundamental paradigm shift in neural network architectures, enabling models to selectively focus on relevant portions of input sequences through learned weighting functions. This monograph provides a comprehensive and rigorous mathematical treatment…
arXiv:2601.03322v1 Announce Type: new Abstract: Electroencephalography (EEG)-based brain-computer interfaces facilitate direct communication with a computer, enabling promising applications in human-computer interactions. However, their utility is currently limited because EEG decoding often suffers from poor generalization due to distribution shifts across…
arXiv:2601.03321v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown strong potential for radiology report generation, yet their clinical translation is hindered by architectural heterogeneity and the prevalence of factual hallucinations. Standard supervised fine-tuning often fails to strictly…
arXiv:2601.03320v1 Announce Type: new Abstract: On-policy reinforcement learning (RL), particularly Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), has become the dominant paradigm for fine-tuning large language models (LLMs). While policy ratio clipping stabilizes training, this heuristic hard…
arXiv:2601.03988v1 Announce Type: cross Abstract: Background: Extracting the stages that structure Machine Learning (ML) pipelines from source code is key for gaining a deeper understanding of data science practices. However, the diversity caused by the constant evolution of the ML…
