Video question answering (VideoQA) requires sophisticated interpretation of spatio-temporal dynamics. While grounded VideoQA has emerged to provide verifiable evidence, existing benchmarks are predominantly confined to Coarse-grained Spatio-Temporal (CST) evidence, such as event or object-level localization. Consequent...
Xiao-Jun Ye, Chun Wang, Jun-Liang Chen et al.· Proceedings of the 34th ACM...· 0 citations
Graph-Language Models (GLMs) aim to endow LLMs with structure-grounded reasoning ability, yet existing solutions often struggle with modality interference : structural information can disrupt pretrained linguistic reasoning, while language cues can overwhelm structural signals. Mainstream modular GLMs with an external...
Zhiyao Zhou, Yugang Ji, Zi-Wen Xu et al.· Proceedings of the 32nd ACM...· 0 citations
This work demonstrates that structure-aware discrete tokenization is a feasible way toward general-purpose graph–language models capable of structural reasoning, and preserves full structural fidelity while enabling LLMs to natively reason over compositional graphlets through graph-level next-token prediction.
Zhonghao Wang, Yugang Ji, Zhuonan Zheng et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.