Skip to main content
Search

# Visual Board

1 related articles

Subscribe to updates
  1. arXiv

    Visual Board splits what is seen from what is inferred in multimodal agents, and an 8B system beats a standalone 32B on all three benchmarks

    In multi-step visual question answering, an early misreading persists as a premise in the dialogue history, and later reasoning stays coherent around it. Visual Board writes image observations, unresolved details and derived conclusions into separate fields of a capacity-bounded workspace that is replaced by snapshot, while the original image stays available for reinspection. Without task-specific training, it improves 4B, 8B, Qwen3-VL-Flash and 32B configurations on Euclid30K, SolidGeo and ChartQA bar charts by 6.10 to 24.82 percentage points, and the homogeneous All-8B system outperforms standalone Qwen3-VL-32B on all three benchmarks.

You’re all caught up