Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
3
0
6
A 4B-parameter model, InternVL-U, punches above its weight, outperforming 14B-parameter models in multimodal generation and editing by using a novel data synthesis pipeline and architecture.
VLMs still struggle to grasp spatial relationships in dynamic sports scenes, as evidenced by a new benchmark revealing a significant human-AI performance gap.
Forget hand-annotated 3D datasets: a new automated pipeline generates massive, high-quality 3D spatial intelligence from raw video, unlocking better VLM reasoning.
