Welcome to MLNN 2026 | Chengdu, China | April 10-12, 2026
2026 3rd International Conference on Machine Learning and Neural Networks
Countdown to the meeting:
About MLNN 2026
The 3rd International Conference on Machine Learning and Neural Networks ( MLNN 2026 ) will be held in Chengdu, China, from April 10 to 12, 2026. This conference focuses on machine learning theory innovation, neural network architecture design, deep learning optimization and cross-domain applications ( such as computer vision, natural language processing, industrial intelligent systems, etc. ), aiming to build a high-level communication platform for global academic and industrial experts. The conference will cover cutting-edge topics such as reinforcement learning, generative models, edge intelligence, and interpretable AI, and promote the integration of basic theoretical breakthroughs and industrial practices through keynote reports, symposiums, paper presentations, and industry-university-research dialogues. Relying on Chengdu innovation ecology and industrial resources, MLNN 2026 will further promote international cooperation and help the sustainable development of artificial intelligence technology on a global scale.
Important Dates
Full Paper Submission Date
February 6, 2026
Notification Date
March 6, 2026
Final Paper Submission Date
March 20, 2026
Conference Dates
April 10-12, 2026
Supported by
☛ CFP
☛ Submission
☛ Publication
Call For Papers
The topics of interest for submission include, but are not limited to:
Neural Networks
Deep Neural Networks, Convolutional Neural Networks, Generative Adversarial Networks, Recurrent Neural Networks, Neural Network Structures, Neural Symbolic Hybrid Models, Interpretability and Visualization Methods of Neural Networks, Analysis and Research of Neural Networks in Multiple Fields
Machine Learning
Broad Learning Systems, Machine Learning,Deep Learning, Reinforcement Learning, Learning Transfer, Knowledge Graph, Path Planning, Transfer Learning, Generative Adversarial Networks, Adversarial Learning,Dual Learning, Distributed Learning, Meta-Learning
Deep learning algorithms and applications
Applications of Convolutional Neural Networks in Image Processing, Recurrent Neural Networks and Their Applications in Sequence Data, Autoencoders and Generative Models, Natural Language Processing Applications, Applications of Neural Networks in Medical Image Analysis,Applications of Neural Networks in Bioinformatics, Applications of Neural Networks in Intelligent Transportation Systems, Applications of Neural Networks in Robot Control, Applications of Neural Networks in Recommendation Systems, Applications of Neural Networks in Anomaly Detection and Early Warning, Federated Learning and Distributed Neural Networks, Hardware Acceleration of Neural Networks, Applications of Neural Networks in the Internet of Things (IoT), Applications of Neural Networks in Edge Computing
Submission
1. The submitted papers must not be under consideration elsewhere.
2. Please send the full paper(word+pdf) to Submission System.
3. Please submit the full paper, if presentation and publication are both needed.
4. Please submit the abstract only, if you just want to make presentations.
5. Templates Download.
6. Should you have any questions, or you need any materials in English, please contact us.
Publication
All papers, both invited and contributed, will be reviewed by two or three expert reviewers from the conference committees. After a careful reviewing process, all accepted papers of MLNN 2026 will be published inACM International Conference Proceedings Series (ISBN：979-8-4007-2267-7), which will be archived in the ACM Digital Library, and indexed by EI Compendex, Scopus.
Note: All submitted articles should report original research results, experimental or theoretical, not previously published or under consideration for publication elsewhere. Articles submitted to the conference should meet these criteria. We firmly believe that ethical conduct is the most essential virtue of any academics. Hence, any act of plagiarism or other misconduct is totally unacceptable and cannot be tolerated.