arXiv:2509.13349v2 Announce Type: replace-cross Abstract: We study whether 3D self-supervised pretraining with Point–JEPA enables label-efficient grasp joint-angle prediction. Meshes are sampled to point clouds and tokenized; a ShapeNet-pretrained Point–JEPA encoder feeds a $K{=}5$ multi-hypothesis head trained with winner-takes-all and evaluated…
arXiv:2509.20529v1 Announce Type: new Abstract: Model discovery aims to uncover governing differential equations of dynamical systems directly from experimental data. Benchmarking such methods is essential for tracking progress and understanding trade-offs in the field. While prior efforts have focused mostly…
arXiv:2007.04568v2 Announce Type: replace Abstract: First-price auctions have very recently swept the online advertising industry, replacing second-price auctions as the predominant auction mechanism on many platforms. This shift has brought forth important challenges for a bidder: how should one bid…
arXiv:2509.20549v1 Announce Type: new Abstract: Neural Probabilistic Circuits (NPCs), a new class of concept bottleneck models, comprise an attribute recognition model and a probabilistic circuit for reasoning. By integrating the outputs from these two modules, NPCs produce compositional and interpretable…
arXiv:2501.18792v2 Announce Type: replace Abstract: Many real-world black-box optimization problems have multiple conflicting objectives. Rather than attempting to approximate the entire set of Pareto-optimal solutions, interactive preference learning allows to focus the search on the most relevant subset. However, few…
arXiv:2509.20565v1 Announce Type: new Abstract: Background/Purpose: Diabetes affects over 537 million people worldwide and is projected to reach 783 million by 2045. Early risk stratification can benefit from machine learning. We compare two hybrid classifiers and assess their generalizability on…
arXiv:2505.11766v2 Announce Type: replace Abstract: Neural Operators have emerged as powerful tools for learning mappings between function spaces. Among them, the kernel integral operator has been widely validated on universally approximating various operators. Although many advancements following this definition have…
arXiv:2509.20570v1 Announce Type: new Abstract: Diffusion models have demonstrated strong generative capabilities across scientific domains, but often produce outputs that violate physical laws. We propose a new perspective by framing physics-informed generation as a sparse reward optimization problem, where adherence…
arXiv:2506.01052v2 Announce Type: replace Abstract: We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone algorithm in the field of reinforcement learning. We are interested in the so-called “robust” setting, where the convergence…
arXiv:2509.20574v1 Announce Type: new Abstract: In scientific applications, predictive modeling is often of limited use without accurate uncertainty quantification (UQ) to indicate when a model may be extrapolating or when more data needs to be collected. Bayesian Neural Networks (BNNs)…
