Evangelos Kazakos

ekazakos

·

AI & ML interests

Computer Vision, Vision-Language, Video-Language, Multi-modal Learning, Robotics, VLA Models

Recent Activity

upvoted a paper 5 days ago

Large-scale Pre-training for Grounded Video Caption Generation

authored a paper 19 days ago

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

upvoted a paper 19 days ago

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

View all activity

Organizations

upvoted a paper 5 days ago

Large-scale Pre-training for Grounded Video Caption Generation

Paper • 2503.10781 • Published Mar 13, 2025 • 17

upvoted a paper 19 days ago

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

Paper • 2609.19143 • Published 20 days ago • 19

upvoted a paper 9 months ago

REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation

Paper • 2512.19562 • Published Dec 22, 2025 • 5

upvoted an article 11 months ago

Article

Open-sourced ICCV 2025 works

yoshitomo-matsubara

•

Oct 16, 2025

• 1