arXiv:2509.13818v1 Announce Type: new Abstract: Quantum Machine Learning (QML) offers a new paradigm for addressing complex financial problems intractable for classical methods. This work specifically tackles the challenge of few-shot credit risk assessment, a critical issue in inclusive finance where…
arXiv:2504.17827v4 Announce Type: replace-cross Abstract: Neural Architecture Search (NAS) has gained widespread attention for its transformative potential in deep learning model design. However, the vast and complex search space of NAS leads to significant computational and time costs. Neural Architecture…
arXiv:2509.13841v1 Announce Type: new Abstract: Accurate prediction of permeability in porous media is essential for modeling subsurface flow. While pure data-driven models offer computational efficiency, they often lack generalization across scales and do not incorporate explicit physical constraints. Pore network…
arXiv:2507.22149v2 Announce Type: replace-cross Abstract: Large language models (LLMs) tend to follow maliciously crafted instructions to generate deceptive responses, posing safety challenges. How deceptive instructions alter the internal representations of LLM compared to truthful ones remains poorly understood beyond output…
arXiv:2509.13855v1 Announce Type: new Abstract: We present a graph-regularized learning of Gaussian Mixture Models (GMMs) in distributed settings with heterogeneous and limited local data. The method exploits a provided similarity graph to guide parameter sharing among nodes, avoiding the transfer…
arXiv:2509.13866v1 Announce Type: new Abstract: We present a systematic theoretical framework that interprets masked diffusion models (MDMs) as solutions to energy minimization problems in discrete optimal transport. Specifically, we prove that three distinct energy formulations–kinetic, conditional kinetic, and geodesic energy–are…
arXiv:2505.18325v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries–a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative safety alignment, causing models…
As part of our ongoing commitment to Africa, Google is announcing new connectivity infrastructure, access to powerful AI tools, and skills.
If a new proposal by MIT physicists bears out, the recent detection of a record-setting neutrino could be the first evidence of elusive Hawking radiation.
arXiv:2509.14040v1 Announce Type: cross Abstract: Learning from demonstration allows robots to acquire complex skills from human demonstrations, but conventional approaches often require large datasets and fail to generalize across coordinate transformations. In this paper, we propose Prompt2Auto, a geometry-invariant one-shot…
