Omkar Thawakar
12 papers · 2022–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (30) π₯ Mega-Team Β· Legion π€ Dynamic Duo (11)
ποΈ
Keyword Collector
(54)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(5)
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(9)
Deep Learning
(6)
Machine Learning
(6)
Computer Vision
(4)
Natural Language Processing
(4)
Models
(4)
Resources & Methods
(4)
Application Areas
(3)
Domain-Specific
(2)
Generation
(2)
Learning Types Β· Machine Learning
(2)
Learning Types Β· Deep Learning
(2)
Healthcare & Medicine
(1)
Interdisciplinary
(1)
Keywords
multimodal learning
(5)
large language model
(4)
benchmark evaluation
(3)
large multimodal model
(3)
video retrieval
(2)
visual reasoning
(2)
cultural heritage
(2)
zero-shot learning
(2)
multilingual nlp
(2)
arabic language
(2)
medical imaging
(1)
video understanding
(1)
image reconstruction
(1)
embedding learning
(1)
language model evaluation
(1)
diffusion model
(1)
curriculum learning
(1)
low-resource language
(1)
fine-grained recognition
(1)
instruction tuning
(1)
Papers
A Multi-Agent Diffusion Approach for MRI Anomaly Segmentation via Modality-Specific LoRA Specialization
WACV 2026
DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding
EACL 2026
Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs
CVPR 2026
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
CVPR 2025
Beyond Simple Edits: Composed Video Retrieval with Dense Modifications
ICCV 2025
CAMEL-Bench: A Comprehensive Arabic LMM Benchmark
NAACL 2025
Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs
EMNLP 2025
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
ACL 2025
Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts
ACL 2025
Composed Video Retrieval via Enriched Context and Discriminative Embeddings
CVPR 2024
Arabic Mini-ClimateGPT : A Climate Change and Sustainability Tailored Arabic LLM
EMNLP 2023
Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer
ECCV 2022