🧑‍🔬 Shubhashis Roy Dipta

🏛️ Affiliations

🎓University of Maryland, Baltimore CountyBaltimore · United States2021–2026 · 33 papersEducation since 2021 · Doctor of Philosophy, Computer ScienceEducation 2021–2023 · Master of Science, Computer ScienceEmployment since 2021 · Research Assistant, Computer Sciencecurrent🎓United International UniversityDhaka · Bangladesh2020 · 3 papers🎓Military Institute of Science and TechnologyDhaka · Bangladesh2013–2017 · 2 papersEducation 2013–2016 · Bachelor of Science, Computer Science and Engineering

🏛️Sapien.NetworkNew York · Bangladesh2019–2021Employment 2019–2021 · Full-Stack Software Engineer

🏛️BackpackDhaka · Bangladesh2018–2019Employment 2018–2019 · Software Engineer

🏛️SELISEDhaka · Bangladesh2018Employment 2018 · Software Engineer

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. BanglaLlama: LLaMA for Bangla Language (2026 · 2 citations)
   Bangla has roughly 240 million native speakers, yet open LLMs handle it poorly because it makes up only a tiny share of their training data. The authors build BanglaLlama, an open family of five Bangla-adapted LLaMA models (from LLaMA 2-7B, 3-8B, 3.1-8B, 3.2-1B and 3.2-3B), each released in base and instruct form.
2. Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks (2026)
   Multimodal foundation models such as VLMs, DMs, LLMs, and AFMs can absorb private, copyrighted, biased, or harmful associations from web-scale training data.

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. BanglaLlama: LLaMA for Bangla LanguageWorkshop on Language Models for Low-Resource LanguagesAbdullah Khan Zehady, Shubhashis Roy Dipta, Naymul Islam, et al.2026 · 2 citations
2. If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition ↗Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025) · no summary yetShubhashis Roy Dipta, Francis Ferraro2025 · 1 citation
3. Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and BenchmarksFindings of the Association for Computational LinguisticsNobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, et al.2026
4. Last Translation Benchmark ↗arXiv:2609.04173 · no summary yetVilem Zouhar et al.2026

🤝 Co-authors here

2 co-authors with a page, the most papers together first.

• Abdullah Khan Zehady
• Zheyuan Liu

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Workshop on Language Models for Low-Resource Languages: Workshop on Language Models for Low-Resource Languages 2026
• Proceedings of the 14th Joint Conference on Lexical and Computational Semantics (*SEM 2025)

🔗 Cited by

Papers of our library cite their works 3 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/shubhashis-roy-dipta/