Search papers, labs, and topics across Lattice.
Beihang University, Peking University
3
0
5
19
TVIR-Agent reveals that integrating visual elements into report generation can dramatically improve the quality and reliability of analytical outputs.
VLMs exhibit distinct failure modes under physical visual stress, revealing that traditional accuracy metrics can mask critical vulnerabilities in embodied AI systems.
Monocular dynamic scene reconstruction gets a unified spatiotemporal decomposition framework, achieving up to 9% improvement in reconstruction quality.
