Grounding Everything in Tokens for Multimodal Large Language Models
Open paper
Benchmark
Model
Rank
Results
referring-expression-segmentation-on-refcoco-plus-testa
GETok-SFT
–
Overall IoU: 72.3
referring-expression-segmentation-on-refcoco-plus-testa
GETok-SFT-grid
–
Overall IoU: 71.9
Rank counts only results with a code link.