arxiv:2504.13122
Shengqiong Wu
ChocoWu
AI & ML interests
Large Language Model, Multimodal learning, Scene graph Generation
Recent Activity
authored
a paper
3 days ago
VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference
Optimization for Large Video Models
updated
a dataset
4 days ago
General-Level/General-Bench-Closeset
Organizations
datasets
None public yet