一作ACL 2026Findings· Findings of ACL
ANCHOR : LLM -driven Subject Conditioning for Text-to-Image Synthesis
Aashish Anantha Ramakrishnan · Sharon X Huang · Dongwon Lee
摘要
Text-to-image (T2I) models have achieved remarkable progress in high-quality image synthesis, yet most benchmarks rely on simple, self-contained prompts, failing to capture the complexity of real-world captions. Human-written captions often involve multiple interacting subjects, rich contextual r...