Skip to main content
Search

Hongxu Chen

1 related articles

Subscribe to updates
  1. arXiv

    Unified multimodal models can't weave text and images on their own: UniWeaver adds planning and visual checks, lifting BAGEL's overall score from 27.7 to 58.9

    Unified multimodal models can understand and generate images but generally lack native support for coordinating interleaved text-image output, and turning a coarse request into coherent multimodal content requires explicit planning. UniWeaver is a model-agnostic structured harness that decomposes a request into content units, assigns what text and images each convey, then generates images and verifies them against observable checklists, regenerating only failed units. On the 120-task UniWeaver-Bench, the BAGEL, OmniGen2 and TokenFlow backbones rise from overall scores of 27.7, 27.9 and 39.2 to 58.9, 52.7 and 60.5 without updating model parameters.

You’re all caught up