arXiv:2510.19163v1 Announce Type: new Abstract: Stochastic Natural Gradient Variational Inference (NGVI) is a widely used method for approximating posterior distribution in probabilistic models. Despite its empirical success and foundational role in variational inference, its theoretical underpinnings remain limited, particularly in…
arXiv:2506.16313v2 Announce Type: replace Abstract: Efficiently identifying the right trajectories for training remains an open problem in GFlowNets. To address this, it is essential to prioritize exploration in regions of the state space where the reward distribution has not been…
arXiv:2510.05874v2 Announce Type: replace Abstract: Accurately simulating physics is crucial across scientific domains, with applications spanning from robotics to materials science. While traditional mesh-based simulations are precise, they are often computationally expensive and require knowledge of physical parameters, such as…
arXiv:2503.01675v2 Announce Type: replace Abstract: Formal languages are an integral part of modeling and simulation. They allow the distillation of knowledge into concise simulation models amenable to automatic execution, interpretation, and analysis. However, the arguably most humanly accessible means of…
arXiv:2505.15754v2 Announce Type: replace Abstract: Continuous time systems are often modeled using discrete time dynamics but this requires a small simulation step to maintain accuracy. In turn, this requires a large planning horizon which leads to computationally demanding planning problems…
arXiv:2510.19811v1 Announce Type: cross Abstract: We present Hubble, a suite of fully open-source large language models (LLMs) for the scientific study of LLM memorization. Hubble models come in standard and perturbed variants: standard models are pretrained on a large English…
arXiv:2410.10811v2 Announce Type: replace Abstract: Weight space learning aims to extract information about a neural network, such as its training dataset or generalization error. Recent approaches learn directly from model weights, but this presents many challenges as weights are high-dimensional…
arXiv:2510.18934v1 Announce Type: new Abstract: A wide variety of generalization measures have been applied to deep neural networks (DNNs). Although obtaining tight bounds remains challenging, such measures are often assumed to reproduce qualitative generalization trends. In this position paper, we…
arXiv:2508.00890v2 Announce Type: replace-cross Abstract: Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world problems are multi-stage complex tasks,…
arXiv:2510.18925v1 Announce Type: new Abstract: Modeling and predicting the dynamics of complex multiscale systems remains a significant challenge due to their inherent nonlinearities and sensitivity to initial conditions, as well as limitations of traditional machine learning methods that fail to…
