Efficient LLMs and Applications (ELLMA 2026)
Aim and Scope
As large language models continue to grow in capability and complexity, the demand for efficiency in both training and deployment is more critical. This special session invites original research contributions addressing the challenges of building and applying efficient large language models across diverse real-world settings. We encourage both theoretical contributions and applied systems work that pushes the frontier of accessible, scalable, and sustainable LLM applications and NLP research.
Topics of interest
- Model Compression Techniques (pruning, quantization, and knowledge distillation).
- Parameter-Efficient Fine-tuning Methods, Efficient Inference and Serving Strategies
- Transfer Learning
- Data Resource Construction and Analysis,
- Multilingual and Cross-Lingual Modeling
- Multimodal Data Analysis and Learning
- Few-shot and Zero-shot Learning
- Synthetic Data Generation
- Efficient LLM Applications in Security, Healthcare, Education, and Code Generation
- Agentic RAG, Multi-Agent
Submission Guideline
https://kse2026.kse-conferences.org/call-for-papers/
Session Organizers
Assoc Prof. Ngan Luu-Thuy Nguyen
University of Information Technology (VNUHCM-UIT)
Assoc. Prof. Dien Dinh
The University of Science (VNUHCM-US)
Dr. Kiet Van Nguyen
University of Information Technology (VNUHCM-UIT)
Dr. Huy Tien Nguyen
The University of Science (VNUHCM-US)
Dr. Tung Thanh Le
The University of Science (VNUHCM-US)
Dr. Luu Thanh Son
University of Information Technology (VNUHCM-UIT), sonlt@uit.edu.vn