RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination
Open paper
Benchmark
Model
Rank
Results
monocular-depth-estimation-on-da-2k
RxBrain
#4
Accuracy: 83.4
text-to-image-generation-on-geneval
RxBrain
#85
Overall: 0.824
Rank counts only results with a code link.