With the rapid advancement of image editing models and their widespread application across various domains, there is an increasingly urgent need to deploy these model capabilities directly into real-world scenarios. However, existing benchmarks remain confined to simple single-image tasks, suffering from limited covera...
Qinye Zhou, Jun Zheng, Yongchao Du et al.· 2 citations
A tailored Bootstrapped Pareto Policy Optimization (BPPO) is proposed, which synergizes Bootstrapping Reward Rectification and Conflict-Aware Pareto Advantage Fusion (CPAF) and exposes critical reasoning deficits, highlighting imperative for knowledge-intensive benchmarks towards next-generation visual generation.
Yuan Wang, Yongchao Du, Mengting Chen et al.· arXiv.org· 1 citation
Swift-Image achieves leading aggregate performance among evaluated open-source models with only 6B parameters and 243K GPU training hours; the compressed 3B model incurs nearly no loss, while few-step distillation further improves aggregate editing performance with substantially fewer sampling steps.