OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning
Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited generalizability. (2) Reflection is often deferred until task completion. (3) Knowledge is often acquired...
Xun Xu, Jin-Xiu Liu, Zhang-Bo Qiao et al.
· 1 citation