SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation
Paper
•
2501.18564
•
Published
•
1
Duan
Jiafei1224
·
AI & ML interests
embodied AI
Recent Activity
authored
a paper
10 days ago
Selective Visual Representations Improve Convergence and Generalization
for Embodied AI
authored
a paper
10 days ago
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for
Robotics
authored
a paper
10 days ago
SAT: Spatial Aptitude Training for Multimodal Language Models
Organizations
