Papers by Yaser Yacoob
MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning (2024.naacl-long)
Copied to clipboard
Fuxiao Liu, Xiaoyang Wang, Wenlin Yao, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Yaser Yacoob, Dong Yu
| Challenge: | Existing large language models have limited ability to perform tasks effectively. |
| Approach: | They propose a large-scale multimodal chart instruction dataset with 600k instances supporting diverse tasks and chart types. |
| Outcome: | The proposed LMM achieves state-of-the-art performance on existing chart QA benchmarks. |
COVID-VTS: Fact Extraction and Verification on Short Video Platforms (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for fact checking multimodal information are limited due to the lack of public data. |
| Approach: | They propose a benchmark for fact-checking multi-modal information involving short-duration videos with COVID19- focused information from both the real world and machine generation. |
| Outcome: | The proposed model detects token-level malicious tampering in different modalities and generates explanations. |