Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
Academic
arXiv:2602.15563v1 Announce Type: new Abstract: Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at …
arXiv:2602.15571v1 Announce Type: new Abstract: Predictive coding (PC) is a biologically inspired algorithm for training neural networks that relies only on local updates, allowing parallel …
arXiv:2602.15572v1 Announce Type: new Abstract: Agent-based modelling (ABM) is a widespread approach to simulate complex systems. Advancements in computational processing and storage have facilitated the …
arXiv:2602.15586v1 Announce Type: new Abstract: This paper provides statistical guarantees on the accuracy of dynamical models learned from dependent data sequences. Specifically, we develop uniform …
arXiv:2602.15593v1 Announce Type: new Abstract: Recurrent and deep neural networks (RNNs/DNNs) are cornerstone architectures in machine learning. Remarkably, RNNs differ from DNNs only by weight …
arXiv:2602.15595v1 Announce Type: new Abstract: In this paper, we formulate the new multi-objective coverage (MOC) problem where our goal is to identify a small set …
arXiv:2602.15602v1 Announce Type: new Abstract: Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case …
Combining mass and energy with information in the inseparable quantum equivalence of E=i mc2 has opened a new informational medicine to help patients maintain truth, …
arXiv:2602.14062v1 Announce Type: new Abstract: Large, openly licensed speech datasets are essential for building automatic speech recognition (ASR) systems, yet many widely spoken languages remain …
arXiv:2602.14069v1 Announce Type: new Abstract: Scalar reward models compress multi-dimensional human preferences into a single opaque score, creating an information bottleneck that often leads to …
arXiv:2602.14073v1 Announce Type: new Abstract: Most vision-language models (VLMs) are trained on English-centric data, limiting their performance in other languages and cultural contexts. This restricts …
arXiv:2602.14077v1 Announce Type: new Abstract: Inference-time scaling (ITS) in latent reasoning models typically introduces stochasticity through heuristic perturbations, such as dropout or fixed Gaussian noise. …