Papers by Gaurav Harit
TabComp: A Dataset for Visual Table Reading Comprehension (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing OCR-free models struggle with complex table layouts and formatting. |
| Approach: | They propose a dataset to evaluate OCR-free models in table reading comprehension using table images, questions, and generative answers. |
| Outcome: | The proposed model outperforms existing models in the visual table reading comprehension dataset and encourages the research community to work on improving them. |
INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents (2026.findings-acl)
Copied to clipboard
| Challenge: | INDOTABVQA provides a benchmark for evaluating cross-lingual Table Visual Question Answering (VQA) on real-world document images in Bahasa Indonesia. |
| Approach: | They propose a benchmark for evaluating cross-lingual Table Visual Question Answering on real-world document images in Bahasa Indonesia. |
| Outcome: | The proposed model improves on a 3B model and a LoRA- finetuned 7B model on Bahasa Indonesian document images by 11.6% and 17.8% respectively. |