--- title: "Fahad Shahbaz Khan — author profile and papers" description: "Fahad Shahbaz Khan, Linköping University: 2 papers on Elamur Research (2023–2025), h-index 92 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/fahad-shahbaz-khan/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/fahad-shahbaz-khan/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Fahad Shahbaz Khan # Fahad Shahbaz Khan Fahad Shahbaz Khan works on models that connect visual input with language. The papers here sit in [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/), language models and pretraining, and [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/). They ask how large language models can move beyond plain text, toward reasoning about video and toward serving languages other than English, Arabic in particular. The usual approach is to extend an existing open model with a light adaptation step, then train it on carefully assembled instruction data. The most cited paper here is [Video-ChatGPT](https://md.research.elamur.ai/free/en/papers/maaz-2023-video-chatgpt-towards-detailed-video/) (2023). It sets out to let a model hold an open-ended conversation about a video clip, where earlier systems were limited to fixed tasks such as recognition or retrieval. The model builds on LLaVA. It encodes each frame on its own, then pools those features both spatially and temporally. A single trainable linear layer projects the combined result into the language model's input space. Training uses video question–answer pairs derived from ActivityNet-200. The more recent [AIN: The Arabic INclusive Large Multimodal Model](https://md.research.elamur.ai/free/en/papers/heakl-2025-ain-arabic-inclusive-large-multimodal/) (2025) turns to bilingual English–Arabic multimodal understanding, fine-tuning Qwen2-VL-7B on a blend of native Arabic and translated samples. Much of that paper concerns data quality. Sentence-similarity scorers were tested on known good and bad translations before being used as filters, and images were screened for harmful content. Khan's current affiliations are [Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/), [Linköping University](https://md.research.elamur.ai/free/en/universities/linkoping-university/) and [University of California, Merced](https://md.research.elamur.ai/free/en/universities/university-of-california-merced/). Earlier papers list the [Inception Institute of Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/inception-institute-of-artificial-intelligence/) in Abu Dhabi. Co-authors on the work here include [Salman Khan](https://md.research.elamur.ai/free/en/authors/salman-khan/), [Hisham Cholakkal](https://md.research.elamur.ai/free/en/authors/hisham-cholakkal/), Rao Muhammad Anwer and Sara Ghaboura. Fahad Shahbaz Khan has 2 papers in our library, in 2023–2025, most of them on [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/); often with [Salman Khan](https://md.research.elamur.ai/free/en/authors/salman-khan/), [Hisham Cholakkal](https://md.research.elamur.ai/free/en/authors/hisham-cholakkal/), [Rao Muhammad Anwer](https://md.research.elamur.ai/free/en/authors/rao-muhammad-anwer/). 2 papers in our library · 2023–2025 current affiliation [Linköping University](https://md.research.elamur.ai/free/en/universities/linkoping-university/), Linköping, Sweden; [University of California, Merced](https://md.research.elamur.ai/free/en/universities/university-of-california-merced/), Merced, United States; [Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/), Abu Dhabi, United Arab Emirates [OpenAlex](https://openalex.org/A5100760570) · [ORCID](https://orcid.org/0000-0002-4263-3143) · [**h-index 92**](https://openalex.org/authors/A5100760570) · [407 works](https://openalex.org/works?filter=author.id:A5100760570) · [48 401 citations](https://openalex.org/works?filter=author.id:A5100760570&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/fahad-shahbaz-khan/#papers) · [259 citations in our library](https://md.research.elamur.ai/free/en/authors/fahad-shahbaz-khan/cited-by/) · 5 more works in our library · [⭐ Paper Star rank #2610](https://md.research.elamur.ai/free/en/paper-stars/page/27/#star-2610) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Fahad+Shahbaz+Khan) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Fahad+Shahbaz+Khan) · [dblp](https://dblp.org/search?q=Fahad+Shahbaz+Khan) · [ACL Anthology](https://aclanthology.org/search/?q=Fahad+Shahbaz+Khan) ## Affiliations - [Mohamed bin Zayed University of Artificial Intelligence](https://md.research.elamur.ai/free/en/universities/mohamed-bin-zayed-university-of-artificial-intelligence/) · Abu Dhabi, United Arab Emirates —current · 2020–2026 on 222 papers - [Linköping University](https://md.research.elamur.ai/free/en/universities/linkoping-university/) · Linköping, Sweden —current · 2012–2026 on 157 papers - [University of California, Merced](https://md.research.elamur.ai/free/en/universities/university-of-california-merced/) · Merced, United States —current · 2023–2026 on 2 papers - [Inception Institute of Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/inception-institute-of-artificial-intelligence/) · Abu Dhabi, United Arab Emirates —2018–2025 on 44 papers - [Abu Dhabi University](https://ror.org/01r3kjq03) · Abu Dhabi, United Arab Emirates —2023–2025 on 2 papers - [Zayed University](https://md.research.elamur.ai/free/en/universities/zayed-university/) · Abu Dhabi, United Arab Emirates —2024–2025 on 2 papers - [Aalto University](https://md.research.elamur.ai/free/en/universities/aalto-university/) · Espoo, Finland —2023–2024 on 2 papers - [Australian National University](https://md.research.elamur.ai/free/en/universities/australian-national-university/) · Canberra, Australia —2022–2024 on 2 papers - [ETH Zurich](https://md.research.elamur.ai/free/en/universities/eth-zurich/) · Zurich, Switzerland —2019–2022 on 2 papers - [Monash University](https://md.research.elamur.ai/free/en/universities/monash-university/) · Melbourne, Australia —2021 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 10 more institutions on single bylines are not listed. ## Topics [Vision & language 2](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) · [Semitic languages 1](https://md.research.elamur.ai/free/en/topics/semitic-languages/) ## Works by year ### 2020s [**2025** 1 paper](https://md.research.elamur.ai/free/en/papers/heakl-2025-ain-arabic-inclusive-large-multimodal/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/maaz-2023-video-chatgpt-towards-detailed-video/) ## Papers The most cited first (OpenAlex and our library). 1. **[Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://md.research.elamur.ai/free/en/papers/maaz-2023-video-chatgpt-towards-detailed-video/)** *(2023 · 634 citations)* Current video models handle fixed tasks such as recognition or retrieval, but they cannot hold a free-form dialogue about what happens in a clip. 2. **[AIN: The Arabic INclusive Large Multimodal Model](https://md.research.elamur.ai/free/en/papers/heakl-2025-ain-arabic-inclusive-large-multimodal/)** *(2025 · 11 citations)* Arabic text-only LLMs have improved, but Arabic multimodal models still cover only narrow slices of vision-language understanding. ## Also in our library 5 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Salman Khan](https://md.research.elamur.ai/free/en/authors/salman-khan/) ×2 - [Hisham Cholakkal](https://md.research.elamur.ai/free/en/authors/hisham-cholakkal/) - [Rao Muhammad Anwer](https://md.research.elamur.ai/free/en/authors/rao-muhammad-anwer/) - [Sara Ghaboura](https://md.research.elamur.ai/free/en/authors/sara-ghaboura/) ## Cited by Papers of our library cite their works 259 times (of the 140 884 papers whose bibliographies we read); [25 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/fahad-shahbaz-khan/cited-by/).