Search papers, labs, and topics across Lattice.
Zhejiang University
3
0
5
1
Image-generation models can outperform text-output VLMs in spatial tasks when evaluated through visual answers, revealing a critical shift in how we assess spatial intelligence in AI.
Token-level attribution transforms memory learning, enabling agents to identify and leverage crucial information for better performance in complex tasks.
VLA-Corrector allows VLA models to adaptively replan actions in real-time, drastically reducing compounding errors in dynamic environments.
