EUVIMEDEUVIMED entdecken
Crossref

SIFThinker: Spatially-Aware Image Focus for Visual Reasoning

Zhangquan Chen, Ruihui Zhao, Chuwei Luo, Mingze Sun, Xinlei Yu, Yangyang Kang, Ruqi Huang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 20436-20444

DOI: 10.1609/aaai.v40i25.39178 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhangquan Chen und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current multimodal large language models (MLLMs) still face significant challenges in complex visual tasks (e.g., spatial understanding, fine-grained perception). Prior methods have tried to incorporate visual reasoning, however, they fail to leverage attention correction with spatial cues to iteratively refine their focus on prompt-relevant regions. In this paper, we introduce SIFThinker, a spatially-aware “think-with-images” framework that mimics human visual perception. Specifically, SIFThinker enables attention correcting and image region focusing by interleaving depth-enhanced bounding boxes and natural language. Our contributions are twofold: First, we introduce a reverse-expansion-forward-inference strategy that facilitates the generation of interleaved image-text chains of thought for process-level supervision, which in turn leads to the construction of the SIF-50K dataset. Besides, we propose GRPO-SIF, a reinforced training paradigm that integrates depth-informed visual grounding into a unified reasoning pipeline, teaching the model to dynamically correct and focus on prompt-relevant regions. Extensive experiments demonstrate that SIFThinker outperforms state-of-the-art methods in spatial understanding and fine-grained visual perception, while maintaining strong general capabilities, highlighting the effectiveness of our method.

Zitieren

APA

Chen, Z., Zhao, R., Luo, C., Sun, M., Yu, X., Kang, Y., & Huang, R. (2026). SIFThinker: Spatially-Aware Image Focus for Visual Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 20436-20444. https://doi.org/10.1609/aaai.v40i25.39178

Vancouver

Chen Z, Zhao R, Luo C, Sun M, Yu X, Kang Y, et al. SIFThinker: Spatially-Aware Image Focus for Visual Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):20436-20444. doi:10.1609/aaai.v40i25.39178

BibTeX
@article{Chen2026,
  author = {Chen, Zhangquan and Zhao, Ruihui and Luo, Chuwei and Sun, Mingze and Yu, Xinlei and Kang, Yangyang and Huang, Ruqi},
  title = {SIFThinker: Spatially-Aware Image Focus for Visual Reasoning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {25},
  pages = {20436--20444},
  doi = {10.1609/aaai.v40i25.39178}
}
Kostenlos starten →