arXiv:2509.15121v2 Announce Type: replace-cross Abstract: We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the $Z_3$-symmetric Next-to-Minimal Supersymmetric Standard Model (NMSSM). This framework gives rise to regions of parameter space…
arXiv:2605.26189v1 Announce Type: new Abstract: Quantization-aware training (QAT) with low-bit floating-point formats enables efficient LLM deployment, yet introduces subtle failure modes invisible to standard training metrics. We present a systematic study of HiF8 W8A8 QAT for OpenPangu-Embedded-1B through the lens…
arXiv:2602.10104v2 Announce Type: replace-cross Abstract: Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control interfaces from unlabeled video, learned latents often fail to transfer across contexts: they entangle scene-specific…
arXiv:2605.26190v1 Announce Type: new Abstract: This paper presents the HRVConformer, a novel deep learning architecture for the classification of hypoxic-ischemic encephalopathy (HIE) using the instantaneous heart rate (HR) signal. Unlike conventional approaches that rely on handcrafted features, HRVConformer directly processes…
arXiv:2605.18468v4 Announce Type: replace-cross Abstract: This paper studies approximation by shallow ReLU$^s$ networks, $sigma_s(t)=max{0,t}^s$, together with their generalization behavior under $ell_1$ path-norm control. For the $L^p$-type integral spaces $widetilde{mathcal{F}}_{p,tau_d,s}$, $1le ple2$, spherical harmonic analysis yields approximation bounds for shallow networks.…
arXiv:2605.26191v1 Announce Type: new Abstract: This research addresses the problem of adaptive modeling in time-series data streams with clear input-output relationships. This problem is challenging because rapid system changes (regime shifts) caused by environmental factors or input delay changes degrade…
arXiv:2605.27355v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing alignment influences…
arXiv:2605.26192v1 Announce Type: new Abstract: Protein structure generative models excel at predicting single protein static structures from sequence, but routinely fail to capture the correct conformational state of protein complexes, critical for protein design and induced proximity modalities such as…
arXiv:2503.21510v3 Announce Type: replace Abstract: Ensuring that predictions of machine learning (ML) classification models are accompanied by uncertainty estimates is one of the main pillars of trustworthy AI. Current research in uncertainty quantification focuses mainly on epistemic uncertainty of the…
arXiv:2605.26193v1 Announce Type: new Abstract: Time series anomaly detection (TSAD) has long been a hot research topic in data mining due to its various applications. Recent studies challenge the effectiveness of popular deep learning methods for TSAD, suggesting their failure…
