Do Pre-trained Vision-Language Models Encode Object States?
Paper • 2409.10488 • Published • 2
Kaleb Slater Newman
KalebCanCode
AI & ML interests
Computer Vision, Reinforcement Learning, HCI, General Intelligence
Recent Activity
authored a paper 2 days ago
Do Pre-trained Vision-Language Models Encode Object States? authored a paper 2 days ago
GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation authored a paper 2 days ago
Video Models Reason Early: Exploiting Plan Commitment for Maze SolvingOrganizations
None yet