Where to Attend: A Principled Vision-Centric Position Encoding with Parabolas
Paper
•
2602.01418
•
Published
Christoffer Koo Øhrstrøm
chriskoo
AI & ML interests
None yet
Recent Activity
submitted
a paper
about 3 hours ago
Where to Attend: A Principled Vision-Centric Position Encoding with Parabolas
authored
a paper
2 months ago
Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras
new activity
over 3 years ago
microsoft/layoutlmv3-large:Add TF weights
Organizations
submitted
a
paper
to Daily Papers
about 3 hours ago
authored
a
paper
2 months ago