Unlocking precise 3D object localization without 3D data, VLM-Grounder revolutionizes visual grounding by leveraging advanced 2D image analysis—achieving breakthrough accuracy and redefining zero-shot ...

*Important notice: arXiv publishes preliminary scientific reports that are not peer-reviewed and, therefore, should not be regarded as definitive, used to guide development decisions, or treated as ...

Researchers from Anthropic explore AI's potential to secretly influence and manipulate decisions, highlighting the urgency for new evaluation strategies as AI capabilities advance. In a recent ...

Researchers introduce iDP3, a 3D visuomotor policy that enables humanoid robots to perform complex tasks autonomously in diverse real-world environments using lab-collected data.

A groundbreaking framework uses influence functions to trace how training data impacts AI-generated outputs, ensuring greater transparency and trust in diffusion models applied across industries.

Geospatial clustering coefficients and pairwise distances between seismic events were calculated to enhance the model’s ability to detect patterns of earthquake occurrence. In an article recently ...

*Important notice: arXiv publishes preliminary scientific reports that are not peer-reviewed and, therefore, should not be regarded as definitive, used to guide development decisions, or treated as ...