Publications

System and Method for Video Instance Segmentation via Multi-Scale Spatio-Temporal Transformers

Omkar Thawakar, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Muhammad Haris, Salman Khan, Fahad Khan

US Patent App. 17/983,841 GRANTED

System and method for video instance segmentation via recurrent encoder-based transformers

Omkar Thawakar, Alexandre Rivkind, Ehud Ahissar, Fahad Khan

US Patent App. 18/435,537 GRANTED

Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models

Shravan Venkatraman, Ritesh Thawkar, Omkar Thawakar, Rao Muhammad Anwer, Hisham Cholakkal, Salman Khan, Fahad Shahbaz Khan

ECCV 2026 arXiv GitHub

EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards

Omkar Thawakar, Shravan Venkatraman, Ritesh Thawkar, Abdelrahman M. Shaker, Hisham Cholakkal, Rao Muhammad Anwer, Salman H. Khan, Fahad Shahbaz Khan

CVPR 2026 (findings) arXiv GitHub

20+ Citations 2.5k+ Model Downloads

CoVR-R: Reason-Aware Composed Video Retrieval

Omkar Thawakar, Dmitry Demidov, Vaishnav Potlapalli, Bogireddy Sai Prasanna Teja, Viswanatha Reddy Gajjala, Alaa Mostafa Lasheen, Rao Muhammad Anwer, Fahad Shahbaz Khan

CVPR 2026 (findings) arXiv GitHub

6+ Citations 3.1K+ Dataset Downloads

LLM Post-Training: A Deep Dive into Reasoning Large Language Models

Komal Kumar, Tajamul Ashraf, Omkar Thawakar, Rao Muhammad Anwer, Hisham Cholakkal, Mubarak Shah, Ming-Hsuan Yang, Phillip H. S. Torr, Salman H. Khan, Fahad Shahbaz Khan

TPAMI arXiv GitHub

2.2K+ GitHub Stars 100+ Citations

Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs

Dmitry Demidov, Zaigham Zaheer, Zongyan Han, Omkar Thawakar, Rao Muhammad Anwer

CVPR 2026 (Main) arXiv GitHub

DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding

Shubham Patle, Sara Ghaboura, Hania Tariq, Mohammad Usman Khan, Omkar Thawakar, Rao Muhammad Anwer, Salman H. Khan

EACL 2026 (Main) arXiv GitHub

500+ Dataset Downloads

Beyond Simple Edits: Composed Video Retrieval with Dense Modifications

Omkar Thawakar, Dmitry Demidov, Ritesh Thawkar, Rao Muhammad Anwer, Mubarak Shah, Fahad Shahbaz Khan, Salman Khan

ICCV 2025 arXiv GitHub

7.1K+ Dataset Downloads 522 Model Downloads 2 Citations

LlamaV-o1: Rethinking Step-by-Step Visual Reasoning in LLMs

Omkar Thawakar, Dinura Dissanayake, Ketan Pravin More, Ritesh Thawkar, Ahmed Heakl, Noor Ahsan, Yuhao Li, Mohammed Zumri, Jean Lahoud, Rao Muhammad Anwer, Hisham Cholakkal, Ivan Laptev, Mubarak Shah, Fahad Shahbaz Khan, Salman H. Khan

ACL 2025 arXiv GitHub

300+ GitHub Stars 130+ Citations 7.3K+ Dataset Downloads 31K+ Model Downloads

TimeTravel: A Benchmark for Historical & Cultural Artifact Understanding

Sara Ghaboura, Ketan Pravin More, Ritesh Thawkar, Wafa Al Ghallabi, Omkar Thawakar, Fahad Shahbaz Khan, Hisham Cholakkal, Salman H. Khan, Rao Muhammad Anwer

ACL 2025 arXiv GitHub

10+ Citations 3.1K+ Dataset Downloads

MobiLLaMA: Towards Accurate & Lightweight Fully Transparent GPT

Omkar Thawakar, Ashmal Vayani, Salman H. Khan, Hisham Cholakkal, Rao Muhammad Anwer, Michael Felsberg, Tim Baldwin, Eric P. Xing, Fahad Shahbaz Khan

ICLR 2025 (Spotlight, Top-2%) arXiv GitHub

600+ GitHub Stars 50+ Citations 320K+ Model Downloads

All Languages Matter: Evaluating LMMs on 100 Culturally Diverse Languages

A Vayani, D Dissanayake, H Watawana, N Ahsan, N Sasikumar, Omkar Thawakar ...

CVPR 2025 (Highlight) arXiv GitHub

40+ Citations 9.8K+ Dataset Downloads

Composed Video Retrieval via Enriched Context and Discriminative Embeddings

Omkar Thawakar, Muzammal Naseer, Rao Muhammad Anwer, Salman H. Khan, Michael Felsberg, Mubarak Shah, Fahad Shahbaz Khan

CVPR 2024 arXiv GitHub

25+ Citations

CAMEL-Bench: A Comprehensive Arabic LMM Benchmark

Sara Ghaboura, Ahmed Heakl, Omkar Thawakar, Ali Husain Salem Abdulla Alharthi, Ines Riahi, Abduljalil Radman, Jorma Laaksonen, Fahad Shahbaz Khan, Salman Khan, Rao Muhammad Anwer

NAACL 2025 arXiv GitHub

15+ Citations 7.7K+ Dataset Downloads

Fann or Flop: A Benchmark for Arabic Poetry Understanding

Wafa Al Ghallabi, Ritesh Thawkar, Sara Ghaboura, Ketan Pravin More, Omkar Thawakar, Hisham Cholakkal, Salman Khan, Rao Muhammad Anwer

EMNLP 2025 (Main Track) arXiv GitHub

8+ Citations 3.2K+ Dataset Downloads

XrayGPT: Chest Radiograph Summarization using Medical VLMs

Omkar Thawakar, Abdelrahman M. Shaker, Sahal Shaji Mullappilly, Hisham Cholakkal, Rao Muhammad Anwer, Salman H. Khan, Jorma Laaksonen, Fahad Shahbaz Khan

ACL-Workshop 2024 arXiv GitHub

500+ GitHub Stars 300+ Citations 352K+ Model Downloads

3D Mitochondria Instance Segmentation with Spatio-Temporal Transformers

Omkar Thawakar, Rao Muhammad Anwer, Jorma Laaksonen, Orly Reiner, Mubarak Shah, Fahad Shahbaz Khan

MICCAI 2023 arXiv GitHub

Fast Video Instance Segmentation via Recurrent Encoder Transformers

Omkar Thawakar, Alexandre Rivkind, Ehud Ahissar, Fahad Shahbaz Khan

CAIP 2023 arXiv GitHub

Video Instance Segmentation via Multi-Scale Spatio-Temporal Attention

Omkar Thawakar, Sanath Narayan, Jiale Cao, Hisham Cholakkal, Rao Muhammad Anwer, Muhammad Haris Khan, Salman Khan, Michael Felsberg, Fahad Shahbaz Khan

ECCV 2022 arXiv GitHub

20+ Citations

Video Instance Segmentation in an Open-World

Omkar Thawakar, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Salman H. Khan, Jorma Laaksonen, Mubarak Shah, Fahad Shahbaz Khan

International Journal of Computer Vision (IJCV), 2024 arXiv GitHub

8 Citations

Image and video super resolution using recurrent generative adversarial network

Omkar Thawakar, Prashant W. Patil, Akshay Dudhane, Subrahmanyam Murala, Uday Kulkarni

IEEE international conference on advanced video and signal based surveillance (AVSS), 2019 arXiv GitHub

25+ Citations

Motion saliency based generative adversarial network for underwater moving object segmentation

Prashant W. Patil, Omkar Thawakar, Akshay Dudhane, Subrahmanyam Murala

IEEE international conference on image processing (ICIP), 2019 arXiv GitHub

35+ Citations

Mobile-O: Unified Multimodal Understanding & Generation on Mobile

Abdelrahman M. Shaker, Ahmed Heakl, Jaseel Muhammad Kaithakkodan, Ritesh Thawkar, Omkar Thawakar, Senmao Li, Hisham Cholakkal, Ian Reid, Eric P. Xing, Salman H. Khan, Fahad Shahbaz Khan

Preprint arXiv GitHub

Ain: The arabic inclusive large multimodal model

Ahmed Heakl, Sara Ghaboura, Omkar Thawakar, Fahad Shahbaz Khan, Hisham Cholakkal, Rao Muhammad Anwer, Salman H. Khan

Preprint 2025 arXiv GitHub

50+ GitHub Stars 8+ Citations 192K+ Model Downloads

Dynamic pre-training: Towards efficient and scalable all-in-one image restoration

Akshay Dudhane, Omkar Thawakar, Syed Waqas Zamir, Salman H. Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang

Preprint 2024 arXiv GitHub

70+ GitHub Stars 22+ Citations

Full record

Patents

Conferences & Journals

Under Review / Preprints