🧑 Career Summary

I am Azmine Toushik Wasi, a 4th year undergrad in Industrial and Production Engineering at Shahjalal University of Science and Technology, Bangladesh.

My core research focuses on exploring Biomedical AI and Graph Neural Networks (GNNs), with an emphasis on structural biology, neuro, therapeutic, and molecular ML domains. In addition to that, my other research interests include interdisciplinary research in Human-Centered AI (HCI, HAI) with NLP (Bias and Fairness) and AI in Industrial Engineering. I am looking forward to pursue a PhD in Fall 2025 to continue my research.

I working with Prof. Dong-Kyu Chae (HYU) as a visiting researcher on GNNs, MedAI, and NLP-HCI. I'm also collaborating with Riashat Islam (PhD, McGill and Mila) at Mila Quebec on molecular ML (Drugs and Proteins) and generative AI. In parallel, I collaborate with Prof. Min Xu (CMU) on biomolecules. I'm an active contributor in Cohere for AI Community. I founded CIOL to mentor young researchers, collaborating with Prof. Ahsan (OU) and Prof. Bappy (LSU) on using GNNs and digital twins for industrial and medical applications.

My research has been published in prestigious venues such as ICLR, COLING, ACCV, CSCW, and workshops of NeurIPS, AAAI, ACL, EMNLP, ICML and CHI, with ongoing reviews in ICLR, TCBB, COLING, IJPR among others. I regularly serve as reviewer for top ML conferences (ICLR, ACL, EMNP, CSCW, CHI) and as program chair/committee for workshops in top conferences (NeurIPS, ICML, ACL, MICCAI). I am also a Kaggle Grandmaster (3rd GM in Bangladesh). Additionally, I have 3 years of experience in AI-integrated product/content automation, and product and project management.

I am a quick learner and highly adaptable, capable of leading projects and teams. I enjoy exploring new topics, sharing knowledge, refining existing skills, experimenting with new techniques, and challenging my capabilities.

View my Curriculum Vitae →
Feel free to email me (azminetoushik dot wasi at gmail dot com) if you're interested in collaboration or discussing research. I'm open to new ideas and collaborations.

🔍 Research Interests

---

• 🧬 Exploring Computational Biology and Biomedical AI Applications
  • Working on Computational Molecular Biology, Bioinformatics, and Computational Drug Discovery (CADGL).
  • Exploring problems like molecular properties prediction, protein discovery, binder design and affinity, molecular interactions, structural biology, digital twins design and development, and healthcare optimization (ICLR'24).
  • Worked with de novo protein generation models and experienced with RL-inspired/energy-guided geometric/sequential structural biology modeling tools with GNNs, Flow Matching, GFLowNets and Diffusion models.
  • Working with Prof. Chae (HYU), Dr. Islam (Mila Quebec), Prof. Xu (CMU) and Prof. Ahsan (OU) on this area.
• 💠 Understanding and Applying Graph Neural Networks (GNN)
  • Engaged in Geometric Machine Learning, focusing on GNN theories and applications, with an emphasis on biomedical AI applications as described above.
  • Additionally, applying GNNs to industrial engineering, specifically in supply chain optimization (GNNs in SCM) and manufacturing.
  • Interested in application of knowledge graphs (extending GNNs) across diverse systems and domains ( COLING'24, ACL'24W, EMNLP'24W).
  • Working with Prof. Chae (HYU), Dr. Islam (Mila Quebec), and Prof. Xu (CMU), Prof. Bappy (LSU), and CIOL researchers on this area.
• 🧑‍💻 Interdisciplinary Research on Humans, AI, and Language
  • Despite extensive coursework in ergonomics, human factors, behavior, and psychology within our IPE curriculum, there's a notable gap in inter-disciplinary research between IPE and AI in Bangladesh, which drives my current initiatives in HCI.
  • Focusing on fairness and reliability (AI for Good), I've worked on evaluating and improving human factors and ergonomics (ICML'24W and EMNLP'24W), religious/cultural values ( CSCW'24, CHI'24W, COLING'25 - 1, 2), into AI systems, mainly Generative AI and Large Language Models (ICLR'25).
  • Working with Cohere for AI Community, Prof. Chae (HYU), and CIOL researchers on this area.

📰 News and Updates

---

🧑‍🔬 Research Experiences

---

• Student Research Assistant, Mila Quebec AI Institute | May, 2024 - Present

• Research Intern, Xu Lab, Carnegie Mellon University | July, 2024 - Present

• Contributor (Aya Projects), Cohere for AI | Aug, 2024 - Present

• Researcher, Computational Intelligence and Operations Laboratory, Shahjalal University of Science and Technology | 2021 - Present

• Visiting Researcher, Data Intelligence Lab, Hanyang University | Nov, 2023 - July, 2024

• Computational Neuroscience Summer School (Research Student), Neuromatch Academy | July, 2024

• CCAI Summer School (Research Student), Climate Change AI | Jun - Aug, 2024

📄 Selected Publications

---

• GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution
  Azmine Toushik Wasi*, Taki Hasan Rafi*, Raima Islam, Karlo Šerbetar, Dong-Kyu Chae (*Equal Contribution)
  ACCV'24 ▪ CV

• BanglaAutoKG: Automatic Bangla Knowledge Graph Construction with Semantic Neural Graph Filtering
  Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Dong-Kyu Chae
  COLING'24 ▪ [ACL Anthology] ▪ [arXiv] ▪ [GitHub] ▪ NLP ▪ GNN

• Neural Control System for Continuous Glucose Monitoring and Maintenance
  Azmine Toushik Wasi
  ICLR'24 Tiny Papers ▪ [OpenReview] ▪ [arXiv] ▪ [GitHub] ▪ Optimization ▪ Medical AI

• When SMILES have Language: Drug Classification using Text Classification Methods on Drug SMILES Strings
  Azmine Toushik Wasi, Karlo Serbetar, Raima Islam, Taki Hasan Rafi, Dong-Kyu Chae
  ICLR'24 Tiny Papers ▪ [OpenReview] ▪ [arXiv] ▪ [GitHub] ▪ Medical AI

• DiaFrame: A Framework for Understanding Bengali Dialects in Human-AI Collaborative Creative Writing Spaces
  Azmine Toushik Wasi, Taki Hasan Rafi, Dong-Kyu Chae
  CSCW'24 Posters ▪ NLP ▪ HCI ▪ HAI ▪ [PDF]

• CADGL: Context-Aware Deep Graph Learning for Predicting Drug-Drug Interactions
  Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Serbetar Karlo, Dong-Kyu Chae
  TCBB In Review ▪ [arXiv] ▪ Medical AI ▪ GNN

• Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and Benchmarks
  Azmine Toushik Wasi, MD Shafikul Islam Sohan, Adipto Raihan Akib, Mahathik Muhammad Bappy
  IJPR In Review ▪ [PDF] ▪ [GitHub] ▪ Dataset and Benchmarks ▪ Supply Chains ▪ GNN

• INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
  Angelika Romanou, ... , Azmine Toushik Wasi, ... , Sara Hooker, Antoine Bosselut
  ICLR In Review ▪ [OpenReview] ▪ Dataset and Benchmarks ▪ NLP ▪ LLM

View All Publications and Ongoing Works →

📜 Selected Projects

---

• AyaFestPe: A multi-lingual and multi-cultural festival exploration guide
  The pipeline starts by collecting festival data from HF and translating it with AyaExpanse for multilingual access. We then gather user queries, use M-RAG to embed data and queries, rerank results, and combine relevant context with the query to generate output.
  [GitHub] ▪ [Colab] (using Cohere API) ▪ [Kaggle] (Using released model weights, with quantization)
• 🏫 Online ML University: Free AI resource collection for everyone! Currently ~150⭐ in GitHub!
• 📑 Paper Organization and Collection
  
  • ICML 2024 Graph Paper Collection : List of all graph and/or GNN papers accepted at ICML'24. Currently ~160⭐ in GitHub!
  • ICLR 2024 Graph Paper Collection : List of all graph papers accepted at ICLR'24. Currently ~70⭐ in GitHub!
  • ICLR 2024 LLM Paper Collection : List of all LLM papers accepted at ICLR'24. Currently ~35⭐ in GitHub!

👩‍💻 Technical Skills

---

• Programming Languages: Python (Advanced), R, SQL, C
• DS & ML Tools (Python): NumPy, Pandas, Matplotlib, Seaborn, Scikitlearn, Keras, Tensorflow, Pycaret, PyTorch.
• ML Techniques: Normal ML Methods, Deep Learning, NLP, Computer Vision, Graph Neural Networks, Explainable AI, Robust Modeling, etc.
• DS Techniques: EDA, Hypothesis Testing, Sampling, Statistical Testing, Corelation Analysis and Inference.
• Data Analysis: MS Excel, SAS, Tableau, Power BI
• IT Automation: Automation in MS Word, Powerpoint, Excel, Google Sheets, Adobe Photoshop, Illustrator, Python based Photo Manipulations
• Computational Biology and Bio-molecules: Molecular Networks, Classification, Molecular Interaction Detection and Classification, Generative Modeling with Flow Matching and Graph Diffusion
• Human-Computer Interaction: LLM Customization, Survey Design, UI/Framework Design and Development, Data Collection and Analysis
• Others: Product Development, Project Management, Business Development and Strategic Planning and Analysis.

💼 Academic Services

---

• Conference or Journal Reviewer
  • AI/ML: ICLR'25, ICLR'24 Tiny Papers.
  • NLP: ACL ARR Feb (ACL), Apr, Jun (EMNLP), Aug 2024 [View in official reviewer list]; COLING'25.
  • HCI/HAI: CHI'25, CSCW'24,'25, UbiComp/ISWC'24, TEI'25, ICMI'24, IDC'24.
  • Journals: Complex & Intelligent Systems (Springer Nature).
  • Total conference or journal paper reviewed: 42
• Workshop Program Committee and Reviewer
  • NeurIPS'24: Behavioral ML, AI4MaterialsDiscovery, EvalEval, Military AI, MusIML
  • EMNLP'24: NLP for Positive Impact, Multulingual Represent Learning
  • ICML'24: AI4Science, LLMs & Cognition
  • ACL'24: TextGraphs-17, ClimateNLP, SMM4H, Language + Molecules, GenderBiasNLP, WASSA.
  • MICCAI'24: Fairness in Medical Imaging, GRaphs in biomedicAl Image anaLysis.
  • Total top conference workshop paper reviewed: 43
• Organizer
  • NeurIPS'24 Muslims in ML Affinity Workshop