arxiv:2506.07971
Xiangtai Li
LXT
AI & ML interests
Computer Vision, Multi-Modal Understanding, Generative AI
Recent Activity
authored
a paper
10 days ago
OmniAudio: Generating Spatial Audio from 360-Degree Video
authored
a paper
10 days ago
Towards Semantic Equivalence of Tokenization in Multimodal LLM
authored
a paper
10 days ago
So-Fake: Benchmarking and Explaining Social Media Image Forgery
Detection
Organizations
