Quality follows upgrading
All Articles
arXiv:2603.20406v1 Announce Type: new Abstract: We investigate whether independently trained language models converge to geometrically compatible latent representations, and whether this compatibility can be exploited …
arXiv:2603.20410v1 Announce Type: new Abstract: Scientific machine learning is increasingly used to build surrogate models, yet most models are trained under a restrictive assumption in …
arXiv:2603.20418v1 Announce Type: new Abstract: Unidirectional tapes surface roughness determines the evolution of the degree of intimate contact required for ensuring the thermoplastic molecular diffusion …
arXiv:2603.20442v1 Announce Type: new Abstract: We propose Melaguard, a multimodal ML framework (Transformer-lite, 1.2M parameters, 4-head self-attention) for detecting neurovascular instability (NVI) from wearable-compatible physiological …
arXiv:2603.20452v1 Announce Type: new Abstract: Longitudinal neuroimaging is essential for modeling disease progression in Alzheimer's disease (AD), yet irregular sampling and missing visits pose substantial …
arXiv:2603.20453v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference …
arXiv:2603.20474v1 Announce Type: new Abstract: Conservation laws are fundamental to understanding dynamical systems, but discovering them from data remains challenging due to parameter variation, non-polynomial …
arXiv:2603.20488v1 Announce Type: new Abstract: Electricity theft, or non-technical loss (NTL), presents a persistent threat to global power systems, driving significant financial deficits and compromising …
arXiv:2603.20492v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse applications, yet their deployment remains challenging due to substantial computational …
arXiv:2603.20507v1 Announce Type: new Abstract: We study the effects of center initialization on the performance of a family of distributed gradient-based clustering algorithms introduced in …
arXiv:2603.20521v1 Announce Type: new Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log-probability) under …
arXiv:2603.20526v1 Announce Type: new Abstract: Policy gradient computes a backward pass for every sample, even though the backward pass is expensive and most samples carry …
