arXiv:2602.17696v1 Announce Type: new Abstract: Large language models (LLMs) are often assumed to contain “safety regions” — parameter subsets whose modification directly influences safety behaviors. We conduct a systematic evaluation of four safety region identification methods spanning different parameter granularities, from individual weights to entire Transformer layers, across four families of backbone LLMs with varying sizes. Using ten safety identification datasets, we find that the identified safety regions exhibit only low to moderate overlap, as measured by IoU. […]

Ver mais

This study examines the challenges of modeling complex and noisy data related to socioeconomic factors over time, with a focus on data from various districts in Odisha, India. Traditional time-series models struggle to capture both trends and variations together in this type of data. To tackle this, a Variational Neural Stochastic Differential Equation (V-NSDE) model is designed that combines the expressive dynamics of Neural SDEs with the generative capabilities of Variational Autoencoders (VAEs). This model uses an encoder […]

Ver mais

By Doug Needham, DataOps.live Technical debt is a challenge for any digital team. Suggestions to avoid it get overridden or ignored, and it’s a rare treat to get to fix the things we know need fixing. If only our PMs and data owners understood what we know—how terrifying technical debt really is—maybe they’d push back less when we fight to build things the right way.  I think I’ve found the way to tell them. Fairy tales, parables, and […]

Ver mais

arXiv:2602.16831v1 Announce Type: new Abstract: This paper presents a low-thrust trajectory optimization strategy to achieve a near-circular lunar orbit for a CubeSat injected into a lunar flyby trajectory. The 12U CubeSat HORYU-VI is equipped with four Hall-effect thrusters and designed as a secondary payload on NASA’s Space Launch System under the Artemis program. Upon release, the spacecraft gains sufficient energy to escape the Earth-Moon system after a lunar flyby. The proposed trajectory is decomposed into three phases: (1) […]

Ver mais

arXiv:2506.13139v2 Announce Type: replace Abstract: Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data and rely on overparameterized models, where classical low-dimensional intuitions break down. In particular, the proportional regime where the data dimension, sample size, and number of model parameters are all large and comparable, gives rise to novel and sometimes counterintuitive behaviors. This paper extends traditional Random Matrix Theory (RMT) beyond eigenvalue-based analysis of linear models to address the challenges posed […]

Ver mais

arXiv:2602.11167v1 Announce Type: new Abstract: Large Language Models (LLMs) often hallucinate, generating nonsensical or false information that can be especially harmful in sensitive fields such as medicine or law. To study this phenomenon systematically, we introduce FalseCite, a curated dataset designed to capture and benchmark hallucinated responses induced by misleading or fabricated citations. Running GPT-4o-mini, Falcon-7B, and Mistral 7-B through FalseCite, we observed a noticeable increase in hallucination activity for false claims with deceptive citations, especially in GPT-4o-mini. […]

Ver mais

Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this challenge by developing a human-in-the-loop framework to learn binary classifiers with rich query types, consisting of item ranking and exemplar selection. We first introduce probabilistic human response models for these rich queries motivated by the relationship experimentally observed between the perceived […]

Ver mais

arXiv:2501.02378v2 Announce Type: replace-cross Abstract: Abrupt learning is a common phenomenon in recurrent neural networks (RNNs) trained on working memory tasks. In such cases, the networks develop transient slow regions in state space that extend the effective timescales of computation. However, the mechanisms driving sudden performance improvements and their causal role remain unclear. To address this gap, we introduce the ghost mechanism, a process by which dynamical systems exhibit transient slowdown near the remnant of a saddle-node bifurcation. […]

Ver mais