Research Interests
I mostly work on Large Language Models, Vision Language Models, Responsible AI, Privacy & Bias, their efficiency, and building downstream industrial applications using RAG methods and LLM deployment.I have also curated high-quality datasets and benchmarks for Multilingual LMMs, Bias Mitigation, and Industrial Applications for the MENA region.
|
News
[Jun 2025] - Co-organized CVPR 2025 Workshop for VidLLMs.
[May 2025] - Started internship at Pinterest as an MLE Intern.
[Mar 2025] - MobiLlama is accepted at ICLR-SLLM Workshop 2025 (Spotlight).
[Feb 2025] - ALM-Bench is accepted at CVPR 2025 (Highlight).
[Oct 2024] - One Paper Accepted at NeurIPS Vision Language Models Workshop, 2024.
[Aug 2024] - Joined the UCF (CRCV) as a Master's in Computer Vision Student.
[Jan 2024] - Promoted to a Research Engineer at MBZUAI.
[Dec 2023] - Merit Award - Tertiary Student Project APICTA Awards held in Hong Kong 2023.
[Dec 2023] - People's Choice Award at APICTA Awards held in Hong Kong 2023.
[Nov 2023] - Released the Jais Climate as a Lead Engineer.
[Aug 2023] - Joined the MBZUAI as a Research Assistant.
|
Publications
selected publications, full here
* denotes joint first authors
|
|
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
Ashmal Vayani,
Dinura Dissanayake,
Hasindri Watawana,
Omkar Thawakar,
Michael Felsberg,
Thamar Solorio,
Monojit Choudhury,
Ivan Laptev,
Mubarak Shah,
Salman Khan,
Fahad Shahbaz Khan
Under Review
Paper
/
Code
|
|
SB-Bench: Sstereotype Bias Benchmark for Large Multimodal Models
Vishal Narnaware*,
Ashmal Vayani*,
Rohit Gupta,
Swetha Sirnam,
Mubarak Shah
Under Review
Paper
/
Code
|
|
GAEA: World-Wide Geo-localization Assistant
Ron Compas,
Ashmal Vayani,
Parth Kulkarni,
Aritra Dutta,
Mubarak Shah
Under Review
Paper
/
Code
|
|
VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding
Ashmal Vayani*,
Ahmad Mahmood*,
Muzammal Naseer,
Salman Khan,
Fahad Shahbaz Khan
NeurIPS Vision Language Models Workshop 2024.
Paper
|
|
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
Omkar Thawakar*,
Ashmal Vayani*,
Salman Khan,
Hisham Cholakkal,
Rao Muhammad Anwer,
Michael Felsberg,
Timothy Baldwin,
Eric P. Xing,
Fahad Shahbaz Khan
Under review
Paper
/
Code
|
|