7th International Conference on Advanced Machine Learning (AMLA 2026)
July 25 ~ 26, 2026, Toronto, Canada
Scope
The 7th International Conference on Advanced Machine Learning (AMLA 2026) serves as a premier international forum for presenting cutting edge research, exchanging ideas, and exploring the latest breakthroughs in Machine Learning and its rapidly expanding ecosystem. As ML continues to transform science, engineering, industry, and society, AMLA 2026 aims to highlight both foundational advances and emerging innovations that define the next generation of intelligent systems.
Topics of interest include, but are not limited to, the following
Machine Learning Foundations
- Machine Learning Algorithms and Theory
- Supervised, Unsupervised and Semi Supervised Learning
- Learning in Knowledge Intensive Systems
- Optimization, Generalization and Learning Dynamics
- Probabilistic Modeling, Bayesian Learning and Uncertainty Quantification
- Classical ML Tasks: Classification, Regression, Clustering, Ranking
Deep Learning and Representation Learning
- Deep Neural Networks and Advanced Architectures
- Self Supervised, Contrastive and Representation Learning
- Foundation Models and Large Scale Pretraining
- Parameter Efficient Fine Tuning (PEFT, LoRA, Adapters)
- Multimodal Deep Learning (Vision, Text, Audio, Graphs)
- Efficient Deep Learning: Distillation, Quantization, Pruning and Sparse Models
- Scaling Laws and Training Dynamics of Large Models
Generative AI and Creative ML
- Diffusion Models and Score Based Generative Models
- Generative Transformers and Autoregressive Models
- GANs and Hybrid Generative Architectures
- Text to X, Image to X and Multimodal Generation
- Synthetic Data Generation, Evaluation and Bias Control
- Generative Agents and Simulation Driven Generation
Reinforcement Learning and Decision Making
- Reinforcement Learning (RL) and Deep RL
- RLHF (Reinforcement Learning from Human Feedback)
- Model Based RL, World Models and Planning
- Multi Agent RL and Game Theoretic Learning
- RL for Robotics, Control, Games and Autonomous Systems
- Causal RL and Safe RL
Agentic ML and Autonomous Learning Systems
- Autonomous ML Agents and Tool Using Agents
- Multi Agent Collaboration, Communication and Coordination
- Planning Augmented ML Models
- Agent Memory, Long Horizon Reasoning and Task Decomposition
- Evaluation of Agentic Systems
Graph Machine Learning and Structured Models
- Graph Neural Networks (GNNs)
- Graph Transformers and Relational Learning
- Knowledge Graph Embeddings and Reasoning
- Structured Prediction and Probabilistic Graphical Models
- Spatio Temporal Graph Learning
Causal ML, Reasoning and Explainability
- Causal Inference and Causal Representation Learning
- Counterfactual Reasoning and Causal Discovery
- Causal Generative Modeling
- Explainable ML (XAI) and Interpretable Models
- Trustworthy ML: Robustness, Fairness and Bias Mitigation
Multimodal ML and Cross Domain Learning
- Vision Language, Audio Language and Multimodal Transformers
- Cross Modal Alignment, Fusion and Retrieval
- Multimodal Representation Learning
- Vision Language Action Models and Embodied ML
Time Series ML, Forecasting and Sequential Models
- Temporal Transformers and Sequence Modeling
- Forecasting, Predictive Modeling and Anomaly Detection
- Sequential Decision Making and Temporal Representation Learning
- ML for Sensor Data, IoT and Real Time Systems Optimization, ML Systems and Infrastructure
- Optimization Algorithms for ML
- Distributed Training, Parallel ML and Large Scale Systems
- ML Compilers, Accelerators and Hardware Aware ML
- Efficient Inference, Model Compression and Deployment
- MLOps, ML Pipelines and Lifecycle Management
- Memory Augmented ML and Long Context Models
Federated, Distributed and Privacy Preserving ML
- Federated Learning and Collaborative ML
- Differential Privacy and Secure ML
- Edge ML, TinyML and On Device Intelligence
- Privacy Preserving Training and Inference
Adversarial ML and ML Security
- Adversarial Attacks and Defenses
- Robust ML and Certified Robustness
- Secure ML Pipelines and Model Integrity
- Red Teaming ML Systems and Safety Critical ML
Meta Learning, Active Learning and Learning to Learn
- Meta Learning and Few Shot Learning
- Active Learning and Curriculum Learning
- AutoML, Neural Architecture Search (NAS)
- Continual Learning, Lifelong Learning and Catastrophic Forgetting Mitigation
Applied Machine Learning and Real World Systems
- ML for Healthcare, Bioinformatics and Genomics
- ML for Finance, Economics and Risk Modeling
- ML for Engineering, Manufacturing and Industry 4.0
- ML for Climate Science, Energy and Sustainability
- ML for Social Computing, Recommendation and Personalization
- ML for Scientific Discovery, Simulation and Physical Modeling
- ML for Software Engineering, Code Generation and Program Synthesis
Paper Submission
Authors are invited to submit papers through the conference Submission System by May 16, 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 AMLA 2026, after further revisions, will be published in the special issue of the following journal.
- Machine Learning and Applications: An International Journal (MLAIJ)
- International Journal of Artificial Intelligence & Applications (IJAIA)
Important Dates
· Submission Deadline: May 16, 2026
· Authors Notification: June 20, 2026
· Registration & camera - Ready Paper Due: June 27, 2026
Contact Us
Here's where you can reach us: amla@ais2026.org (or) amlaconff@gmail.com
Paper Submission Link: https://csit2026.org/submission/index.php
