SCOPE of MLNLP 2026

Contributed papers are solicited describing original works in Machine Learning and Natural Language Processing. Topics and technical areas of interest include but are not limited to the following:

 

Track 1: Machine Learning (ML)
Foundations: Supervised, unsupervised, and semi-supervised learning.
Deep Learning: Neural network architectures, attention mechanisms, and graph neural networks.
Learning Paradigms: Reinforcement learning, transfer learning, and multi-task learning.
Trustworthy AI: Explainable AI (XAI), robustness, fairness, and privacy-preserving machine learning.
Optimization: Large-scale optimization algorithms and evolutionary computing.
Edge & Distributed ML: Federated learning and on-device machine learning.

Track 2: Natural Language Processing (NLP)
Large Language Models (LLMs): Pre-training, fine-tuning, prompting, and alignment (RLHF).
Linguistic Analysis: Syntactic parsing, semantic analysis, and pragmatic reasoning.
Core NLP Tasks: Named entity recognition, sentiment analysis, and summarization.
Dialogue & Interactive Systems: Chatbots, multi-turn dialogue management, and human-computer interaction.
Machine Translation: Neural machine translation and multilingual processing.
Information Retrieval: Question answering, document ranking, and knowledge graph construction.

Track 3: ML & NLP Convergence (Emerging Trends)
Multimodal Learning: Integration of vision, audio, and text (Vision-Language Models).
Cognitive Computing: Language understanding inspired by human cognition.
AI for Science: Applications of MLNLP in healthcare, finance, and social sciences.
Efficiency & Sustainability: Green AI, model compression, and efficient inference.
Creative AI: Controllable text generation and AI-aided content creation.
Ethics & Society: Detection of AI-generated content (Deepfake text) and bias mitigation.