7th International Conference on Machine Learning & Trends (MLT 2026)
June 20 ~ 21, 2026, Sydney, Australia
Scope & Topics 7th International Conference on Machine Learning & Trends (MLT 2026) serves as a premier global forum for presenting and exchanging the latest advancements in Machine Learning theory, methodologies, and real world applications. As machine learning continues to shape the future of intelligent systems, scientific discovery, and industry innovation, MLT 2026 aims to bring together leading researchers, practitioners, and industry experts to explore emerging trends and transformative breakthroughs in the field.
The conference provides a dynamic platform for fostering collaboration between academia and industry, encouraging the cross pollination of ideas that drive the next generation of machine learning technologies. Participants will have the opportunity to engage with cutting edge research, discuss open challenges, and identify new directions that will influence the evolution of ML in the years ahead.
Authors are invited to contribute high quality submissions that showcase original research results, innovative projects, comprehensive surveys, and industrial case studies demonstrating significant progress in machine learning and its rapidly expanding ecosystem. Contributions may address, but are not limited to, the broad range of topics outlined below.
Topics of interest include, but are not limited to, the following Machine Learning Foundations
- Supervised, Unsupervised and Semi Supervised Learning
- Reinforcement Learning and Sequential Decision Making
- Probabilistic Modeling and Bayesian Machine Learning
- Optimization Methods for Machine Learning
- Learning Theory, Generalization and Sample Efficiency
- Representation Learning and Feature Learning
Deep Learning and Neural Architectures
- Deep Neural Networks and Training Dynamics
- Transformers and Attention Based Models
- Graph Neural Networks (GNNs) and Graph Transformers
- Self Supervised and Contrastive Learning
- Neural Architecture Search (NAS)
- Foundation Models and Large Scale Pretraining
Generative Models and Synthetic Data
- Diffusion Models and Score Based Generative Models
- Generative Adversarial Networks (GANs)
- Synthetic Data Generation and Data Centric AI
- Generative Modeling for Images, Text, Audio, Video and Multimodal Data
Advanced Learning Paradigms
- Meta Learning and Few Shot Learning
- Continual, Lifelong and Online Learning
- Multi Task and Transfer Learning
- Active Learning and Curriculum Learning
- Federated, Distributed and Collaborative Learning
Causal and Explainable Machine Learning
- Causal Inference and Causal Discovery
- Causal Representation Learning
- Counterfactual Reasoning
- Explainable and Interpretable Machine Learning
Time Series, Forecasting and Sequential Modeling
- Deep Learning for Time Series Forecasting
- Streaming Data and Online Prediction
- Event Based and Temporal Modeling
- Sequential and Structured Data Analysis
Scientific Machine Learning (SciML)
- Neural Differential Equations
- ML for Physics, Chemistry, Biology and Engineering
- ML for Scientific Discovery, Simulation and Surrogate Modeling
- Physics Informed Machine Learning
ML Security, Safety and Robustness
- Adversarial Attacks and Defenses
- Model Extraction, Poisoning and Evasion Attacks
- Secure and Trustworthy ML Pipelines
- Safety, Reliability and Risk Aware ML
- ML for Safety Critical Systems (healthcare, aviation, autonomous driving)
Scalable, Efficient and Systems Level ML
- Efficient Training: Compression, Pruning, Quantization
- Large Scale ML Systems and Distributed Training
- Hardware Aware ML (GPUs, TPUs, Edge Devices)
- Energy Efficient and Sustainable ML
- Real Time ML, Edge ML andTinyML
Robotics, Embodied AI and Control
- Robot Learning and Policy Optimization
- Embodied Agents and Perception Action Loops
- Sim to Real Transfer
- Learning for Autonomous Systems
ML for Code, Software Engineering and Program Synthesis
- Code Generation and Repair
- Program Synthesis and Verification
- ML Assisted Software Development
- Multimodal Code Understanding
Multimodal Learning, Vision and Perception
- Computer Vision and Visual Recognition
- Vision Language Models and Multimodal Fusion
- 3D Vision, Scene Understanding and Embodied Perception
- Audio, Speech and Sensor Based Learning
Differentiable Programming and Implicit Models
- Differentiable Optimization Layers
- Implicit Neural Representations and Equilibrium Models
- Differentiable Physics and Simulation
- End to End Differentiable Pipelines
Agentic AI and Autonomous ML Systems
- Autonomous ML Agents and Tool Using Systems
- Multi Agent Learning, Cooperation and Negotiation
- Planning + Reasoning + Acting Loops
- Agentic Evaluation and Safety Frameworks
Quantum Machine Learning
- Quantum Inspired ML Algorithms
- Hybrid Quantum Classical Models
- Quantum Optimization and Simulation
ML for Biology, Medicine and Synthetic Bio Design
- Protein and Molecule Design with ML
- DNA/RNA Sequence Modeling
- ML for Gene Editing and Synthetic Biology
- Biological Foundation Models
ML for Economics, Markets and Mechanism Design
- Market Simulation and Prediction
- Mechanism Design and Auctions
- Game Theoretic Machine Learning
- ML for Economic Forecasting
ML for Infrastructure, Networking and Systems Optimization
- ML for Cloud and Distributed Systems
- ML for Networking, Routing and Traffic Optimization
- ML for Resource Allocation and Scheduling
Geospatial, Earth Observation and Climate ML
- Satellite Imagery and Remote Sensing ML
- Geospatial Forecasting and Mapping
- Climate Modeling and Environmental ML
Data Mining, Knowledge Discovery and Predictive Analytics
- Pattern Mining and Anomaly Detection
- Predictive Modeling and Forecasting
- Large Scale Data Mining and Big Data Analytics
- Knowledge Discovery in Databases (KDD)
Applied Machine Learning Across Domains
- Healthcare, Bioinformatics and Drug Discovery
- Finance, Economics and Risk Modeling
- Cybersecurity and Threat Detection
- Social Media, BehaviorModeling and Misinformation
- Education, Personalization and Learning Analytics
- Industrial Systems, IoT and Smart Manufacturing
Evaluation, Benchmarking and Reproducibility
- ML Evaluation Metrics and Benchmark Design
- Reproducibility, Transparency and Open Science
- Dataset Governance, Quality and Bias Detection
- Model Auditing and Performance Diagnostics
AI Governance, Ethics and Societal Impact
- Fairness, Bias and Ethical AI
- AI Governance, Regulation and Policy Frameworks
- Societal Impact and Responsible Deployment
- Human Centered and Human AI Collaborative Systems
Paper Submission Authors are invited to submit papers through the conference Submission System by May 02, 2026. Submissions must be original and should not have been published previously or be under consideration for publication while being evaluated for this conference. The proceedings of the conference will be published by Computer Science Conference Proceedings in Computer Science & Information Technology (CS & IT) series (Confirmed). Selected papers from MLT 2026, after further revisions, will be published in the special issue of the following journals. Important Dates | Submission Deadline | : | May 02, 2026 | | Authors Notification | : | May 23, 2026 | | Final Manuscript Due | : | May 30, 2026 |
Co - Located Event ***** The invited talk proposals can be submitted to mlt@sai2026.org |
