AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2698-2706
DOI: 10.1609/aaai.v40i4.37258 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Boyu Chang und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Visual abductive reasoning (VAR) is a challenging task that requires AI systems to infer the most likely explanation for incomplete visual observations. While recent MLLMs develop strong general-purpose multimodal reasoning capabilities, they remain fall short in abductive inference, as compared to human beings. To bridge this gap, we draw inspiration from the interplay between verbal and pictorial abduction in human cognition, and propose to strengthen abduction of MLLMs by mimicking such dual-mode behavior. Concretely, we introduce AbductiveMLLM comprising of two synergistic components: REASONER and IMAGINER. The REASONER operates in the verbal domain. It first explores a broad space of possible explanations using a blind LLM and then prunes visually incongruent hypotheses based on cross-modal causal alignment. The remaining hypotheses are introduced into the MLLM as targeted priors, steering its reasoning toward causally coherent explanations. The IMAGINER, on the other hand, further guides MLLMs by emulating human-like pictorial thinking. It conditions a text-to-image diffusion model on both the input video and the REASONER’s output embeddings to “imagine” plausible visual scenes that correspond to verbal explanation, thereby enriching MLLMs' contextual grounding. The two components are trained jointly in an end-to-end manner. Experiments on standard VAR benchmarks show that AbductiveMLLM achieves state-of-the-art performance, consistently outperforming traditional solutions and advanced MLLMs.
Zitieren
APA
Chang, B., Wang, Q., Guo, X., Nan, Z., Yao, Y., & Zhou, T. (2026). AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2698-2706. https://doi.org/10.1609/aaai.v40i4.37258
Vancouver
Chang B, Wang Q, Guo X, Nan Z, Yao Y, Zhou T. AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2698-2706. doi:10.1609/aaai.v40i4.37258
BibTeX
@article{Chang2026,
author = {Chang, Boyu and Wang, Qi and Guo, Xi and Nan, Zhixiong and Yao, Yazhou and Zhou, Tianfei},
title = {AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {2698--2706},
doi = {10.1609/aaai.v40i4.37258}
}
EUVIMED