Unintended Side Effects of Value Training in LLMs
arXiv:2610.29922v1 Announce Type: cross Abstract: As LLMs are increasingly deployed in value-sensitive contexts, aligning them with human values has emerged…
Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs
arXiv:2610.29925v1 Announce Type: cross Abstract: As large language models (LLMs) continue to grow in scope and capability, privacy concerns are…
S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents
arXiv:2610.27746v3 Announce Type: replace-cross Abstract: Simulating economic responses at society scale requires agents whose decisions reflect household circumstances and the…
A Generalisation Signal Need Not Be a Model-Selection Signal
arXiv:2609.39099v2 Announce Type: replace-cross Abstract: Model selection in computational biology often relies on validation data drawn from the training regime,…
Offline Apprenticeship Learning for Human-Centric Environments
arXiv:2610.28716v1 Announce Type: cross Abstract: Effective decision-making in human-centric environments such as Intelligent Tutoring Systems (ITSs) and clinical healthcare requires…
Efficient equivariant framework for universal charge density prediction
Nature Machine Intelligence, Published online: 23 October 2026; doi:10.1038/s42256-026-01326-5 Li et al. introduce EdenGNN-Uni, a universal charge density model for…
Retargeting Motions to Diverse Skeletons via Learnable Flattening
arXiv:2609.38578v3 Announce Type: replace-cross Abstract: Cross-structural motion retargeting aims to transfer motion between different skeletal topologies. Despite recent progress, existing…