Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching Paper • 2609.01404 • Published Sep 1 • 31
Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand Paper • 2609.17172 • Published Sep 15 • 3
DistScene: Object-to-Scene Distillation for 3D Scene Generation Paper • 2610.06960 • Published Oct 3 • 12
OmniTaskonomy: When Does Visual Generation Improve Visual Understanding? Paper • 2609.38079 • Published Sep 29 • 41
WorldAttention: An Efficient Attention Architecture for Interactive Video World Models Paper • 2609.34606 • Published Sep 28 • 21
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Paper • 2608.30821 • Published Aug 31 • 64
Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization Paper • 2608.26103 • Published Aug 26 • 24
ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video Paper • 2607.17790 • Published Jul 20 • 5
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions Paper • 2606.02859 • Published Jun 1 • 12
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 50
When Do Diffusion Models learn to Generate Multiple Objects? Paper • 2605.00273 • Published Apr 30 • 9
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation Paper • 2604.19741 • Published Apr 21 • 18