Search papers, labs, and topics across Lattice.
Nanjing University
3
0
3
MLLMs can recover global shapes but often fail to capture precise parametric geometry, revealing critical gaps in their 3D modeling capabilities.
Current video editing models falter under the weight of complex user instructions, often omitting critical edits and introducing artifacts.
Open-weight Omni models struggle with binding accuracy, achieving only 41.55% on a new counterfactual benchmark, highlighting a critical gap in long-video comprehension.
