Recent multimodal image generation models can take multiple images and textual instructions as input, enabling reference-based generation guided not only by text but also by visual instructions such as layouts, arrows, and pose cues. However, existing benchmarks do not evaluate the joint setting in which multiple refer...
Yuta Oshima, Masakazu Yoshimura, Masahiro Suzuki et al.· 0 citations
This work proposes AutoRef, which optimizes the harness automatically while keeping both models frozen: a coding agent iteratively rewrites the harness code, and discovers AutoRef-Harness, which improves the open-weight FLUX.
Yuta Oshima, Ku Onoda, Yusuke Iwasawa et al.· 0 citations
A symbolic-attribute oracle shows that CoT can improve counting once ground-truth attributes are supplied as text, while a single-object probe-vs-decode check shows that hard attributes can be linearly recoverable from hidden states yet difficult for the model itself to output.
Readout Feedback (RoFB), a test-time intervention that converts intermediate predictions into token-wise pairwise coupling forces injected into the latent dynamics, is introduced, suggesting that closed-loop steering of latent dynamics can serve as a complementary inference-time control mechanism for recurrent reasonin...
Shunsuke Kamiya, Masanori Koyama, Seongcheol Jeong et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
