Update README.md

README.md

@@ -43,7 +43,6 @@ pipeline_tag: image-text-to-text
 - **Dense Spatial Rewards**: Multi-objective reward function enforcing format, count, accuracy, and spatial grounding
 - **9 Spatial Reasoning Categories**: Relations, reach, size, orientation, instance location, depth, distance, count, and existence
 - **MoE Efficiency**: 30B total parameters with only ~3B active per token — comparable quality to dense 30B models at a fraction of the compute
-- **Strong Zero-Shot Generalization**: Matches or beats SpatialThinker-7B on 11 of 13 evals.py benchmarks (+5pp average excluding outliers)
 
 ## Inference Template