Skip to content
View Hasnat79's full-sized avatar
9 followers · 16 following

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Highlights

  • Pro

Block or report Hasnat79

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Hasnat79/README.md

Howdy! I'm Hasnat Md Abdullah

Profile Views

GitHub Streak

🔬 Research Focus

  • Multimodal AI & Video Understanding: Developing systems for unusual activity detection and temporal localization
  • Computer Vision: Working on road damage assessment using drone imagery and AI-generated image detection
  • Natural Language Processing: Expertise in language models and multimodal interactions
  • AI Safety: Research on toxic content detection and mitigation in AI-generated content

📚 Publications

  1. "DETONATE: A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization" - Submitted to AAAI 2026

  2. "CliME: Evaluating Multimodal Climate Discourse on Social Media and the Climate Alignment Quotient" - ACL2025-NLP4PI Workshop

  3. "InstaLearn: Continual Knowledge Updates for Domain Adaptation" - KDD'25 International Workshop on Resource-Efficient Learning for Knowledge Discovery (RelKD)

  4. "Snap&Spot: Localizing Unusual Activities in Videos with Large Vision Language Models" - To be submitted at ARR Cycle 2025

  5. "UALBench: The First Comprehensive Unusual Activity Localization Benchmark" - WACV'25

  6. "Non-Uniform Spatial Alignment Errors in sUAS Imagery From Wide-Area Disasters" - IEEE RO-MAN 2025

  7. "Alignment Quality Index (AQI)" - Submitted to EMNLP 2025

  8. "Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs" - Submitted to EMNLP 2025

  9. "Ask Me Again Differently: GRAS for Measuring Bias in VLMs on Gender, Race, Age, and Skin Tone" - Submitted at ARR Cycle 2025

  10. "Visual Counter Turing Test (VCT²)" - Submitted at ARR Cycle 2025

  11. "SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models for Chest X-Ray Classification" - IEEE IICAIET 2022

  12. "A Comparative Analysis of Lumpy Skin Disease Prediction through ML approaches" - IEEE IICAIET 2022

  13. "Affective Social Anthropomorphic Intelligent System" - Multimedia Tools and Applications Journal, Springer Nature, 2023

💻 Technical Stack

{
    'Languages': ['Python', 'C++'],
    'ML/DL': ['PyTorch', 'TensorFlow', 'Keras'],
    'Computer Vision': ['OpenCV', 'YOLO', 'UNet', 'ViT'],
    'NLP': ['Transformers', 'NLTK', 'spaCy'],
    'Data Analysis': ['Pandas', 'NumPy', 'SciPy', 'SPSS'],
    'Tools': ['Git', 'Linux', 'AWS']
}

📫 Connect With Me

Pinned Loading

  1. h2i_hatespeech_to_image h2i_hatespeech_to_image Public

    In this project, we generate images using generative ai models from popular hatespeech text datasets: UCBHateSpeech & SupersetHateSpeechatespeech &

    Python 1

  2. uag uag Public

    Adapting Pretrained Foundation Models for Unusual Activity Localization or gounding

    Python

  3. AnomalyWatchdog AnomalyWatchdog Public

    Python

  4. Snap_n_Spot Snap_n_Spot Public

    Python

  5. LlamaGen_local LlamaGen_local Public

    Forked from FoundationVision/LlamaGen

    Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

    Python

  6. Transformer_Arch_Scratch Transformer_Arch_Scratch Public

    Jupyter Notebook