arxiv:2609.19143
Evangelos Kazakos
ekazakos
AI & ML interests
Computer Vision, Vision-Language, Video-Language, Multi-modal Learning, Robotics, VLA Models
Recent Activity
liked a dataset 1 day ago
XGQ12345/GiT_hdf5 upvoted a paper 23 days ago
Large-scale Pre-training for Grounded Video Caption Generation authored a paper about 1 month ago
PANORAMA: Panoptic Grounded Captioning via Mask Proposal SelectionOrganizations
