arXiv:2509.14386v1 Announce Type: new Abstract: We prove a fundamental impossibility theorem: neural networks cannot simultaneously learn well-calibrated confidence estimates with meaningful diversity when trained using binary correct/incorrect supervision. Through rigorous mathematical analysis and comprehensive empirical evaluation spanning negative reward training,…
arXiv:2509.15085v1 Announce Type: cross Abstract: The task of Mel vocoding, i.e., the inversion of a Mel magnitude spectrogram to an audio waveform, is still a key component in many text-to-speech (TTS) systems today. Based on generative flow matching, our prior…
arXiv:2509.14536v1 Announce Type: new Abstract: Predictive process monitoring techniques support the operational decision making by predicting future states of ongoing cases of a business process. A subset of these techniques predict the remaining sequence of activities of an ongoing case…
arXiv:2509.15167v1 Announce Type: cross Abstract: This paper explores the transfer of knowledge from general vision models pretrained on 2D natural images to improve 3D medical image segmentation. We focus on the semi-supervised setting, where only a few labeled 3D medical…
arXiv:2509.14562v1 Announce Type: new Abstract: Large models recently are widely applied in artificial intelligence, so efficient training of large models has received widespread attention. More recently, a useful Muon optimizer is specifically designed for matrix-structured parameters of large models. Although…
arXiv:2410.19665v3 Announce Type: replace Abstract: Timely updating of Internet of Things data is crucial for achieving immersion in vehicular metaverse services. However, challenges such as latency caused by massive data transmissions, privacy risks associated with user data, and computational burdens…
arXiv:2509.14563v1 Announce Type: new Abstract: The discovery of environmental knowledge depends on labeled task-specific data, but is often constrained by the high cost of data collection. Existing machine learning approaches usually struggle to generalize in data-sparse or atypical conditions. To…
arXiv:2505.20646v3 Announce Type: replace Abstract: Understanding and controlling the informational complexity of neural networks is a central challenge in machine learning, with implications for generalization, optimization, and model capacity. While most approaches rely on entropy-based loss functions and statistical metrics,…
arXiv:2509.14568v1 Announce Type: new Abstract: We present the fundamental theory and implementation guidelines underlying Evidential Physics-Informed Neural Network (E-PINN) — a novel class of uncertainty-aware PINN. It leverages the marginal distribution loss function of evidential deep learning for estimating uncertainty…
arXiv:2509.14577v1 Announce Type: new Abstract: The Large Margin Distribution Machine (LMDM) is a recent advancement in classifier design that optimizes not just the minimum margin (as in SVM) but the entire margin distribution, thereby improving generalization. However, existing LMDM formulations…
