Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration? Paper • 2602.07055 • Published 21 days ago • 22
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security Paper • 2601.18491 • Published 30 days ago • 125
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning Paper • 2510.12693 • Published Oct 14, 2025 • 28
Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models Paper • 2506.18945 • Published Jun 23, 2025 • 40