Digital advertising increasingly relies on visual content, yet marketers lack rigorous methods for understanding how specific visual attributes causally affect consumer engagement. This paper addresse...
Deep neural networks often exploit spurious associations in their training data, a failure known as shortcut learning. Concept-based explainability methods screen for shortcuts by testing whether conc...
We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable con...
In modern applications of linear mixed models, the number of candidate fixed-effects covariates can grow exponentially with the sample size, while dependence induced by random effects and possible dat...
As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely activated Transformers, but...
Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed number of denoising s...
Early-phase oncology evidence is often summarized by asking whether a treatment is promising, but an encouraging signal can support several different next studies. We propose Evidence-to-Decision (E2D...
Underwater tactile force sensing is crucial for achieving nondestructive and stable object manipulation in ocean robotics, especially in deep-sea environments where traditional vision-based methods ar...
Indonesia's marine ecosystem is rich in biodiversity, including sea cucumbers that contain a range of potentially valuable bioactive compounds. Among these, exosomes-nanosized extracellular vesicles (...
The Black Sea offers underutilized marine bioresources with potential for the development of materials intended for wound healing and skin tissue repair. In this study, new composite biomaterials were...
The gut-skin axis represents a bidirectional communication network linking the gut microbiota, microbial metabolism, immune regulation, and skin physiology. Natural bioactives derived from dietary pla...
We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract dispropo...
We study minimum-norm interpolation (MNI) in overparameterized linear regression with isotropic Gaussian covariates, in settings where the MNI has no closed-form formula. Whereas most prior work relie...
Quantifying random spatial variations in composite interface properties is an essential prerequisite for the high-fidelity propagation of material properties variabilities through structural numerical...
Doochi, a traditional Korean dish made from boiled shark skin and intestine, may be a source of mercury exposure. In 2013, total mercury was measured in untreated fragments of boiled shark skin from 3...
Forecasting is usually framed as a problem of model choice. This paper starts earlier, asking how much predictive information is available at each horizon. Under logarithmic loss, the answer is exact:...
We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable con...
Agentic vision-language models increasingly act through extended interactions, but most evaluations still focus on single-image, single-turn correctness. We introduce AMIGO (Agentic Multi-Image Ground...
🌊
