LLMs Struggle to Perform Counterfactual Reasoning with Parametric Knowledge
arXiv:2506.15732v1 Announce Type: new Abstract: Large Language Models have been shown to contain extensive world knowledge in their parameters, enabling…
The future of open human feedback
Nature Machine Intelligence, Published online: 20 June 2025; doi:10.1038/s42256-025-01038-2 Don-Yehiya et al. explore creating an open ecosystem for human feedback…
ArchShapeNet:An Interpretable 3D-CNN Framework for Evaluating Architectural Shapes
arXiv:2506.14832v1 Announce Type: cross Abstract: In contemporary architectural design, the growing complexity and diversity of design demands have made generative…
DreamGen: Unlocking Generalization in Robot Learning through Video World Models
arXiv:2505.12705v2 Announce Type: replace-cross Abstract: We introduce DreamGen, a simple yet highly effective 4-stage pipeline for training robot policies that…
AIn’t Nothing But a Survey? Using Large Language Models for Coding German Open-Ended Survey Responses on Survey Motivation
arXiv:2506.14634v2 Announce Type: replace-cross Abstract: The recent development and wider accessibility of LLMs have spurred discussions about how they can…
Over-squashing in Spatiotemporal Graph Neural Networks
arXiv:2506.15507v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have achieved remarkable success across various domains. However, recent theoretical advances…