Search papers, labs, and topics across Lattice.
Xi鈥檃n Jiaotong University
3
0
5
Current vision-language models can *see* point cloud defects, but can't reliably *diagnose* them, highlighting a critical gap in grounded quality understanding.
GUI agents struggle in dynamic environments because they only see static screenshots, but DynamicUI's video-based approach with frame selection and action-conditioned refinement leaps ahead.
Forget GPT-4o, the secret to better robot manipulation might be an agentic framework that generates diverse, physically plausible tasks, leading to superior VLA pre-training.
