Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
Academic
arXiv:2603.15958v1 Announce Type: new Abstract: Hyperparameter transfer has become an important component of modern large-scale training recipes. Existing methods, such as muP, primarily focus on …
arXiv:2603.15987v1 Announce Type: new Abstract: Achieving deterministic computation results in asynchronous neuromorphic systems remains a fundamental challenge due to the inherent temporal stochasticity of continuous-time …
arXiv:2603.15990v1 Announce Type: new Abstract: Each LoRA checkpoint compactly stores task-specific updates in low-rank weight matrices, offering an efficient way to adapt large language models …
arXiv:2603.16015v1 Announce Type: new Abstract: Recent work has highlighted the centrality of smooth calibration [Kakade and Foster, 2008] as a robust measure of calibration error. …
arXiv:2603.16039v1 Announce Type: new Abstract: Recent work has made clear that the residual pathway is not mere optimization plumbing; it is part of the model's …
arXiv:2603.16043v1 Announce Type: new Abstract: Human Activity Recognition using wearable inertial sensors is foundational to healthcare monitoring, fitness analytics, and context-aware computing, yet its deployment …
arXiv:2603.16066v1 Announce Type: new Abstract: This paper introduces a novel variational Bayesian method that integrates Tucker decomposition for efficient high-dimensional inverse problem solving. The method …
arXiv:2603.16077v1 Announce Type: new Abstract: Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens into …
arXiv:2603.16080v1 Announce Type: new Abstract: Bitcoin transaction networks are large scale socio- technical systems in which activities are represented through multi-hop interaction patterns. Graph Neural …
arXiv:2603.16123v1 Announce Type: new Abstract: Neural networks systematically fail at compositional generalization -- producing correct outputs for novel combinations of known parts. We show that …
arXiv:2603.16140v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven recent capability advances of large language models across various domains. Recent studies …