LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis
LongBanana is introduced, to the authors' knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age of agent-driven image generation, and experiments show that minimal agent harnesses improve over direct generation, while a ReAct-Plan-Exec-Reflect (RPR...
Hao-Xiang Cao, Yuxuan Zhang, Peng-Hui Du et al.
· 0 citations