The field of control and estimation is moving towards the development of more sophisticated and robust methods for handling complex systems. Researchers are exploring the use of machine learning and data-driven approaches to improve the accuracy and efficiency of control and estimation algorithms. One notable trend is the integration of physical models with data-driven representations to leverage the strengths of both approaches. This has led to the development of innovative methods such as physics-informed neural networks and data-fused model predictive control. Another area of focus is the development of safety-critical control systems that can operate effectively in uncertain and dynamic environments. Noteworthy papers in this area include: Optimal Control of an SIR Model with Noncompliance as a Social Contagion, which proposes a compartmental model for epidemiology with human behavioral effects. Learning-Based Data-Assisted Port-Hamiltonian Control for Free-Floating Space Manipulators, which introduces a generic data-assisted control architecture within the port-Hamiltonian framework. Data-fused Model Predictive Control with Guarantees: Application to Flying Humanoid Robots, which combines physics-based models with data-driven representations of unknown dynamics. A Physics-Informed Neural Networks-Based Model Predictive Control Framework for SIR Epidemics, which addresses the joint real-time estimation of states and parameters within the MPC framework using only noisy infected states. Hybrid State Estimation of Uncertain Nonlinear Dynamics Using Neural Processes, which discusses a novel hybrid, data-driven state estimation approach based on the physics-informed attentive neural process. Safety filtering of robotic manipulation under environment uncertainty: a computational approach, which proposes a physics-based safety filtering scheme that leverages high-fidelity simulation to assess control policies under uncertainty in world parameters. MAPS: A Mode-Aware Probabilistic Scheduling Framework for LPV-Based Adaptive Control, which integrates an Interacting Multiple Model estimator with a Linear Parameter-Varying based control strategy. Ellipsoidal partitions for improved multi-stage robust model predictive control, which aims to integrate the strengths of both ellipsoidal tube-based MPC and scenario-based approaches. Model Predictive Control with Reference Learning for Soft Robotic Intracranial Pressure Waveform Modulation, which introduces a learning-based control framework for a soft robotic actuator system designed to modulate intracranial pressure waveforms. Perception-Integrated Safety Critical Control via Analytic Collision Cone Barrier Functions on 3D Gaussian Splatting, which presents a perception-driven safety filter that converts each 3D Gaussian Splat into a closed-form forward collision cone.