view article Article Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action nvidia • 8 days ago • 73
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments Paper • 2605.30280 • Published 13 days ago • 140
V2-SAM Collection The model, training, and evaluation data of V2-SAM. • 6 items • Updated 10 days ago
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published 13 days ago • 142
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration Paper • 2605.03042 • Published May 4 • 130
view article Article NEO-unify: Building Native Multimodal Unified Models End to End sensenova • Mar 5 • 164