ACM International Conference on Multimedia

LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning

ACM International Conference on Multimedia

Shibo, Sun and Xue, Li and Donglin, Di and Mingjie, Wei and Lanshun, Nie and Weinan, Zhang and Dechen, Zhan and Yang, Song and Lei Fan

LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning

ACM International Conference on Multimedia

Shibo, Sun and Xue, Li and Donglin, Di and Mingjie, Wei and Lanshun, Nie and Weinan, Zhang and Dechen, Zhan and Yang, Song and Lei Fan

PRISM: A Benchmark for Unveiling Cross-model Knowledge Inconsistency in Large Vision-Language Models

ACM International Conference on Multimedia

Mingjie, Wei and Weinan, Zhang and Chen, Zhang and Yifeng, Ding and Donglin, Di and Lei, Ren and Chen, Wei and Ting Liu

PRISM: A Benchmark for Unveiling Cross-model Knowledge Inconsistency in Large Vision-Language Models

ACM International Conference on Multimedia

Mingjie, Wei and Weinan, Zhang and Chen, Zhang and Yifeng, Ding and Donglin, Di and Lei, Ren and Chen, Wei and Ting Liu