Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition
Paper • 2603.13904 • Published • 1
seokminlee
SeokminLee-Chris
AI & ML interests
Robotics & Self Supervised Learning
Recent Activity
submitted a paper about 12 hours ago
Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition authored a paper about 15 hours ago
Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where CompositionOrganizations
None yet
submitted a
paper to Daily Papers about 12 hours ago
authored a
paper about 15 hours ago