Studying Image Tokenizers as Visual Languages in Unified Multimodal Models
Paper • 2609.09143 • Published • 17
AI & ML interests
Robotics, deep learning, navigation, perception
Recent Activity
View all activity
Papers
Studying Image Tokenizers as Visual Languages in Unified Multimodal Models
Autoregressive Image Generation with Masked Bit Modeling
lst627
submitted a
paper to Daily Papers about 14 hours ago
Fix QK norm to apply before RoPE, retrain released checkpoints
#2 opened 2 months ago
by 
tommiekerssies
Fix QK norm to apply before RoPE, retrain released checkpoints
#2 opened 2 months ago
by tommiekerssies
tommiekerssies
updated 6
models 5 months ago
Amazon-FAR/rgb-head-imagenet
Image-to-Image • Updated • 1
Amazon-FAR/depth-head-kitti
Depth Estimation • Updated • 1
Amazon-FAR/seg-head-cityscapes
Image Segmentation • Updated • 2
Amazon-FAR/seg-head-vspw
Image Segmentation • Updated • 1
Amazon-FAR/deltaworld-kinetics
Image-to-Video • Updated • 1
Amazon-FAR/deltatok-kinetics
Image Feature Extraction • Updated • 1
tommiekerssies
authored a
paper 5 months ago
tommiekerssies
updated a
collection 5 months ago
Add pipeline tag and external links
#1 opened 5 months ago
by 
nielsr
Add pipeline tag and links to paper/code
#1 opened 5 months ago
by nielsr
Add pipeline tag and links to paper/project/code
#1 opened 5 months ago
by nielsr
Add pipeline tag and links to paper/code
#1 opened 5 months ago
by nielsr
Improve model card: add pipeline tag, project links and usage snippet
#1 opened 5 months ago
by nielsr
Improve model card: add pipeline tag, links to paper, code, and project page
#1 opened 5 months ago
by nielsr
tommiekerssies
published 3
models 5 months ago