Ashmal Vayani

I am an MSc. student in the College of Engineering and Computer Science department at the University of Central Florida. I am a member of the Center for Research in Computer Vision (CRCV) Lab advised by Prof. Mubarak Shah.

Previously, I was a Research Engineer in the Computer Vision Department, affiliated with the IVAL-Lab at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI). I was advised by Prof. Fahad Khan, and Dr. Salman Khan (Aug 2023 - Jul 2024). During my undergrad, I worked as a Research Intern at Retrocausal with Dr. Zeeshan Zia. I completed my Bachelors from National University of Computer and Emerging Sciences majoring in Computer Science (Aug 2019 - June 2023).

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo

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

  • [Aug 2025] - Our work GAEA is accepted at WACV 2026.
  • [Aug 2025] - Our work VIMUL is accepted at EMNLP 2025.
  • [Aug 2025] - Our work GRAMVIS is accepted at EMNLP Findings 2025 .
  • [Jun 2025] - Co-organized CVPR 2025 Workshop for VidLLMs.
  • [May 2025] - Started internship at Pinterest as an MLE Intern in the Visual Search Team.
  • [Mar 2025] - Our work MobiLlama is accepted at ICLR-SLLM Workshop 2025 (Spotlight).
  • [Feb 2025] - Our work ALM-Bench is accepted at CVPR 2025 (Highlight).
  • [Oct 2024] - Our work VURF/span> is accepted at NeurIPS VLM 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
    VURF-diag 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
    CVPR 2025 (Highlight)
    Paper / Project / Code / Data
    GAEA-Figure GAEA: A Geolocation Aware Conversational Assistant
    Ron Campos*, Ashmal Vayani*, Parth Parag Kulkarni*, Rohit Gupta Aizan Zafar, Aritra Dutta, Mubarak Shah,
    WACV 2026
    Paper / Project / Code / Data

    ViMUL-Figure A Culturally-diverse Multilingual Multimodal Video Benchmark & Model
    Bhuiyan Sanjid Shafique, Ashmal Vayani, Muhammad Maaz, Hanoona Abdul Rasheed, Dinura Dissanayake Michael Felsberg, Mubarak Shah, Salman Khan Fahad Shahbaz Khan
    EMNLP 2025 (Main)
    Paper / Project / Code / Data

    GRAMVIS-Visual Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models
    Muhammed Saeed, Shaina Raza, Ashmal Vayani, Muhammad Abdul-Mageed, Ali Emami, Shady Shehata
    EMNLP 2025 (Findings)
    Paper

    VURF-diag 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 / Code

    Mobillama-diag 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
    ICLR SLLM Workshop 2025 (Spotight)
    Paper / Code / Models

    SB-Bench-Figure SB-Bench: Sstereotype Bias Benchmark for Large Multimodal Models
    Vishal Narnaware*, Ashmal Vayani*, Rohit Gupta, Swetha Sirnam, Mubarak Shah
    Under Review
    Paper / Project / Code / Data