LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation Paper • 2608.30935 • Published 6 days ago • 30
Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction Paper • 2608.27529 • Published 10 days ago • 33
EgoSuite-Open100K Collection The largest fully-annotated open egocentric human dataset. 100,000 hours across 15,000+ tasks and scenes. • 3 items • Updated 18 days ago • 51
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration Paper • 2605.03042 • Published May 4 • 150
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End? Paper • 2608.15265 • Published 22 days ago • 60
Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence Paper • 2608.16590 • Published 20 days ago • 150
MatrAIx: Simulating the World with 8.3 Billion Persona Agents Paper • 2608.04205 • Published Aug 4 • 53
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 20 days ago • 340
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Paper • 2605.31264 • Published May 29 • 132
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning Paper • 2608.09888 • Published 27 days ago • 771
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published Jul 21 • 313
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report Paper • 2607.18367 • Published Jul 20 • 61
GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation Paper • 2607.02642 • Published Jul 2 • 40