Search papers, labs, and topics across Lattice.
Fudan University
3
0
6
Proprietary MLLMs excel in chart annotation, but open-source models are rapidly catching up, especially with clearer instructions.
SenseWalk reveals how LLMs can transform the simulation of human movement by seamlessly integrating semantic understanding with physical modeling.
Integrating visual frames with textual reasoning steps, VTI-CoT achieves state-of-the-art video reasoning performance while boosting training efficiency.
