Classically, the Singular Value Decomposition (SVD) (see, e.g., [vides w-rankapproximation.

Continuous deep learning architectures enable learning of flexible probabilistic modelsforpredictivemodeling asneuralordinary differential equations (ODEs), and for generative modeling as continuous normalizing flows.

Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper,we propose anovelmethod for training non-Bayesian NNs to estimate a continuous target as well as its associated evidence in order tolearn both aleatoric andepistemic uncertainty.

End-to-end learning directly maps sensory inputs to actions, creating highly integrated and efficient policies for complex robotics tasks. However, such models are tricky to efficiently train and often struggle to generalize beyond their training scenarios, limiting adaptability to new environments, tasks, and concepts. In this work, we investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies under unseen text instructions and visual distribution shifts. To this end, we design datasets with various levels of data representation richness, refine feature extraction protocols by leveraging multi-modal foundation model encoders, and assess the suitability of different policy network heads. Our findings are synthesized in Flex (Fly-lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors, generating spatially aware embeddings that integrate semantic and visual information. These rich features form the basis for training highly robust downstream policies capable of generalizing across platforms, environments, and text-specified tasks. We demonstrate the effectiveness of this approach on quadrotor fly-to-target tasks, where agents trained via behavior cloning on a small simulated dataset successfully generalize to real-world scenes, handling diverse novel goals and command formulations.

Magnetic navigation (MagNav) is a rising alternative to the Global Positioning System (GPS) and has proven useful for aircraft navigation. Traditional aircraft navigation systems, while effective, face limitations in precision and reliability in certain environments and against attacks. Airborne MagNav leverages the Earth's magnetic field to provide accurate positional information. However, external magnetic fields induced by aircraft electronics and Earth's large-scale magnetic fields disrupt the weaker signal of interest. We introduce a physics-informed approach using Tolles-Lawson coefficients for compensation and Liquid Time-Constant Networks (LTCs) to remove complex, noisy signals derived from the aircraft's magnetic sources. Using real flight data with magnetometer measurements and aircraft measurements, we observe up to a 64% reduction in aeromagnetic compensation error (RMSE nT), outperforming conventional models. This significant improvement underscores the potential of a physics-informed, machine learning approach for extracting clean, reliable, and accurate magnetic signals for MagNav positional estimation.

The modern pervasiveness of large-scale deep neural networks (NNs) is driven by their extraordinary performance on complex problems but is also plagued by their sudden, unexpected, and often catastrophic failures, particularly on challenging scenarios. Existing algorithms that provide risk-awareness to NNs are complex and ad-hoc. Specifically, these methods require significant engineering changes, are often developed only for particular settings, and are not easily composable. Here we present capsa, a framework for extending models with risk-awareness. Capsa provides a methodology for quantifying multiple forms of risk and composing different algorithms together to quantify different risk metrics in parallel. We validate capsa by implementing state-of-the-art uncertainty estimation algorithms within the capsa framework and benchmarking them on complex perception datasets. We demonstrate capsa's ability to easily compose aleatoric uncertainty, epistemic uncertainty, and bias estimation together in a single procedure, and show how this approach provides a comprehensive awareness of NN risk.

Makram Chahine, a PhD student in electrical engineering and computer science and an MIT CSAIL affiliate, leads a drone used to test liquid neural networks. In the vast, expansive skies where birds once ruled supreme, a new crop of aviators is taking flight. These pioneers of the air are not living creatures, but rather a product of deliberate innovation: drones. Rather, they're avian-inspired marvels that soar through the sky, guided by liquid neural networks to navigate ever-changing and unseen environments with precision and ease. Inspired by the adaptable nature of organic brains, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have introduced a method for robust flight navigation agents to master vision-based fly-to-target tasks in intricate, unfamiliar environments.

MIT researchers unveil the first open-source simulation engine capable of constructing realistic environments for deployable training and testing of autonomous vehicles. Since they've proven to be productive test beds for safely trying out dangerous driving scenarios, hyper-realistic virtual worlds have been heralded as the best driving schools for autonomous vehicles (AVs). Tesla, Waymo, and other self-driving companies all rely heavily on data to enable expensive and proprietary photorealistic simulators, because testing and gathering nuanced I-almost-crashed data usually isn't the easiest or most desirable to recreate. VISTA 2.0 is an open-source simulation engine that can make realistic environments for training and testing self-driving cars. With this in mind, scientists from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) created "VISTA 2.0," a data-driven simulation engine where vehicles can learn to drive in the real world and recover from near-crash scenarios.