LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
Open paper
Benchmark
Model
Rank
Results
image-editing-on-imgedit-data
LaViDa-R1
–
Overall: 3.90
Add: 4.25
Adjust: 3.90
Extract: 2.32
Replace: 4.52
…
Rank counts only results with a code link.