LAPA (Look Around and Pay Attention): multi-camera point tracking. Contains pretrained models for TAPVid-3D-MC and PointOdyssey-MC and LAPA-Joint
Bishoy Moussa Galoaa PRO
bishoygaloaa
AI & ML interests
Teaching Machines
Recent Activity
authored a paper 5 days ago
Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation authored a paper 5 days ago
ViMoLa: Discrete Motion Tokens for Language-Guided Video Generation authored a paper 5 days ago
PanoWorld: Geometry-Consistent Panoramic Video World ModelingOrganizations
spaces 5
pinned
Sleeping
Agents
2
Gaslight Turing Test — JKP Leaderboard
🧠
VLM robustness leaderboard on STAR video QA
Running
DNA Motion Lab
🧬
Edit DNA, or watch a cassette fail
Sleeping
Synovial Sarcoma Survival Calculator
🩺
Calculate 2‑ and 5‑year survival odds for synovial sarcoma
Sleeping
Agents
Qween Space
📚
No application file
Agents
Mote
📈
More than meets the eye
models 12
bishoygaloaa/tcam
Video-Text-to-Text • 0.3B • Updated • 99 • 1
bishoygaloaa/ViMoLa
Image-to-Video • Updated • 1
bishoygaloaa/tokengazer
Robotics • Updated • 1
bishoygaloaa/cardano
Video-Text-to-Text • Updated
bishoygaloaa/LAPA-Joint
Updated
bishoygaloaa/LAPA-PointOdyssey-MC
Updated
bishoygaloaa/LAPA-TAPVid-3D-MC
Updated
bishoygaloaa/LAPA
Updated • 1
bishoygaloaa/motion-o
Video-Text-to-Text • Updated • 1 • 2
bishoygaloaa/Qween
Video-Text-to-Text • Updated