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…
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: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: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:2509.13841v1 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: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:2509.13818v1 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:2411.01544v2 Announce Type: replace-cross Abstract: Error detection and correction are essential for ensuring robust and reliable operation in modern communication systems, particularly in complex transmission environments. However, discussions on these topics have largely been overlooked in semantic communication (SemCom), which…
arXiv:2509.13805v1 Announce Type: new Abstract: Foundation models have revolutionized natural language processing through a “train once, deploy anywhere” paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation Model (PFM) would be…
arXiv:2405.13541v2 Announce Type: replace-cross Abstract: Preference optimization is a standard approach to fine-tuning large language models to align with human preferences. The quantity, diversity, and representativeness of the preference dataset are critical to the effectiveness of preference optimization. However, obtaining…
