8th Annual Learning for Dynamics & Control Conference
University of Southern California
June 17-19, 2026
8th Annual Learning for Dynamics & Control Conference
University of Southern California
June 17-19, 2026
The explosion of real-time data arising from devices that sense and control the physical world requires improving synergy in research areas such as machine learning, control theory, and optimization. While control theory has been firmly rooted in the tradition of model-based design, the availability and scale of data (both temporal and spatial) will require rethinking the foundations of the discipline. From a machine learning perspective, one of the main challenges going forward is to go beyond pattern recognition and address problems in data-driven control and optimization of dynamical processes. Our conference has been building a new community of people who think rigorously across the disciplines, ask new questions, and develop the foundations of this new scientific area.
This year, L4DC will be co-located with International Conference on Neuro-symbolic Systems (NeuS).
Submission deadline: November 8, 2025*
Paper decision: January 22, 2026
Registration opens: March 2026
Camera-ready deadline: April 15, 2026
Tutorials day: June 17, 2026
Main conference: June 18-19, 2026
* Submission deadline will not be extended as these dates aim to accommodate timely notification of the decision before the end of January.
A "call for papers flyer" (PDF) is available here.
Please submit your paper using the provided L4DC LaTeX template. The submission link will be provided shortly.
We invite submissions of short papers addressing topics including:
Foundations of learning of dynamics models
System identification
Optimization for machine learning
Data-driven optimization for dynamical systems
Distributed learning over distributed systems
Reinforcement learning for physical systems
Safe reinforcement learning and safe adaptive control
Statistical learning for dynamical and control systems
Bridging model-based and learning-based dynamical and control systems
Machine learning for reduced-order modeling and physics-constrained systems
Physical learning in dynamical and control systems applications in robotics, autonomy, biology, energy systems, transportation systems, cognitive systems, neuroscience, etc.
The conference is open to any topic on the interface between machine learning, control, and optimization; its primary goal is to address scientific and application challenges in real-time processes modeled by dynamical or control systems.
2025 7th L4DC at University of Michigan, Ann Arbor, USA
2024 6th L4DC at University of Oxford, UK
2023 5th L4DC at University of Pennsylvania, USA
2022 4th L4DC at Stanford University, USA
2021 3rd L4DC at ETH Zurich, Switzerland (virtual)
At the L4DC conference, we aim to create a safe, welcoming, and positive environment that facilitates exchanging ideas and forming professional connections. We expect all participants to be respectful towards each other. The conference will not tolerate harassment, discrimination, or personal attacks. Participants must stop any problematic behavior immediately. If you have concerns about problematic behavior, please notify the L4DC organizers. If you would like to notify the organizers anonymously, a form will be made available on this website before the conference.
It is important to note that problematic communication can occur even without an explicit intent to offend or harass. Hence, we ask that all participants be mindful of how their comments can be interpreted, and err on the side of caution during formal and informal interactions.
L4DC is interdisciplinary, bringing together researchers from control, robotics, machine learning, and optimization. One of the goals of L4DC is to build strong ties between these disciplines and enable active collaboration. Please consider taking on the constructive role of contributing to the community, instead of taking on a critical role to pinpoint flaws and weaknesses in the works of others during the conference. Focusing on weak points could cause others to retreat back to places where they feel comfortable, and instead of interdisciplinary interaction, we could end up with separate sub-clusters of people only interacting within their own fields. So please help us create a positive tone so that it is easy for the participants to leave their comfort zones, gain new perspectives, and form new collaborations.