Reproduce “TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Leigang Qu, Haochuan Li, Tan Wang, Wenjie Wang, Yongqi Li, Liqiang Nie, Tat-Seng Chua
TIGeR-ONE combines image generation and gallery retrieval in one training-free multimodal model, then selects between their outputs using model-estimated prompt–image similarity. It searches gallery images through discrete visual codes and reranks a shortlist. On TIGeR-Bench, LaVIT scores 28.45 CLIP-T and 61.37 CLIP-I, exceeding the listed unified agent; these aggregate results do not establish success in every category.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.