Autonomous racing serves as a critical platform for evaluating automated driving systems and enhancing vehicle mobility intelligence. This work investigates offline reinforcement learning methods to train agents within the dynamic F1tenth racing environment. The study begins by exploring the challenges of online training in the Austria race track environment, where agents consistently fail to complete the laps. Consequently, this research pivots towards an offline strategy, leveraging `expert' demonstration dataset to facilitate agent training. A waypoint-based suboptimal controller is developed to gather data with successful lap episodes. This data is then employed to train offline learning-based algorithms, with a subsequent analysis of the agents' cross-track performance, evaluating their zero-shot transferability from seen to unseen scenarios and their capacity to adapt to changes in environment dynamics. Beyond mere algorithm benchmarking in autonomous racing scenarios, this study also introduces and describes the machinery of our return-conditioned decision tree-based policy, comparing its performance with methods that employ fully connected neural networks, Transformers, and Diffusion Policies and highlighting some insights into method selection for training autonomous agents in driving interactions.

Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different probability distributions. In this work, we give an information-theoretic analysis of the generalization error and excess risk of transfer learning algorithms. Our results suggest, perhaps as expected, that the Kullback-Leibler (KL) divergence $D(\mu\|\mu')$ plays an important role in the characterizations where $\mu$ and $\mu'$ denote the distribution of the training data and the testing data, respectively. Specifically, we provide generalization error and excess risk upper bounds for learning algorithms where data from both distributions are available in the training phase. Recognizing that the bounds could be sub-optimal in general, we provide improved excess risk upper bounds for a certain class of algorithms, including the empirical risk minimization (ERM) algorithm, by making stronger assumptions through the \textit{central condition}. To demonstrate the usefulness of the bounds, we further extend the analysis to the Gibbs algorithm and the noisy stochastic gradient descent method. We then generalize the mutual information bound with other divergences such as $\phi$-divergence and Wasserstein distance, which may lead to tighter bounds and can handle the case when $\mu$ is not absolutely continuous with respect to $\mu'$. Several numerical results are provided to demonstrate our theoretical findings. Lastly, to address the problem that the bounds are often not directly applicable in practice due to the absence of the distributional knowledge of the data, we develop an algorithm (called InfoBoost) that dynamically adjusts the importance weights for both source and target data based on certain information measures. The empirical results show the effectiveness of the proposed algorithm.

Provably sample-efficient Reinforcement Learning (RL) with rich observations and function approximation has witnessed tremendous recent progress, particularly when the underlying function approximators are linear. In this linear regime, computationally and statistically efficient methods exist where the potentially infinite state and action spaces can be captured through a known feature embedding, with the sample complexity scaling with the (intrinsic) dimension of these features. When the action space is finite, significantly more sophisticated results allow non-linear function approximation under appropriate structural constraints on the underlying RL problem, permitting for instance, the learning of good features instead of assuming access to them. In this work, we present the first result for non-linear function approximation which holds for general action spaces under a linear embeddability condition, which generalizes all linear and finite action settings. We design a novel optimistic posterior sampling strategy, TS^3 for such problems, and show worst case sample complexity guarantees that scale with a rank parameter of the RL problem, the linear embedding dimension introduced in this work and standard measures of the function class complexity.

LLMs are statistical models of language learning through stochastic gradient descent with a next token prediction objective. Prompting a popular view among AI modelers: LLMs are just next token predictors. While LLMs are engineered using next token prediction, and trained based on their success at this task, our view is that a reduction to just next token predictor sells LLMs short. Moreover, there are important explanations of LLM behavior and capabilities that are lost when we engage in this kind of reduction. In order to draw this out, we will make an analogy with a once prominent research program in biology explaining evolution and development from the genes eye view. LLMs are statistical models of language learning through stochastic gradient descent with a next token prediction objective. So, LLMs are'just next token predictors', a popular view among AI modelers, explicitly laid out by Shanahan (2024): "A great many tasks that demand intelligence in humans can be reduced to next-token prediction with a sufficiently performant model" (2024, 68), and "surely what they are doing is more than'just' next-token prediction? Well, it is an engineering fact that this is what an LLM does. The noteworthy thing is that next-token prediction is sufficient for solving previously unseen reasoning problems" (2024, 77).

Federated learning is a promising distributed machine learning paradigm that can effectively exploit large-scale data without exposing users' privacy. However, it may incur significant communication overhead, thereby potentially impairing the training efficiency. To address this challenge, numerous studies suggest binarizing the model updates. Nonetheless, traditional methods usually binarize model updates in a post-training manner, resulting in significant approximation errors and consequent degradation in model accuracy. To this end, we propose Federated Binarization-Aware Training (FedBAT), a novel framework that directly learns binary model updates during the local training process, thus inherently reducing the approximation errors. FedBAT incorporates an innovative binarization operator, along with meticulously designed derivatives to facilitate efficient learning. In addition, we establish theoretical guarantees regarding the convergence of FedBAT. Extensive experiments are conducted on four popular datasets. The results show that FedBAT significantly accelerates the convergence and exceeds the accuracy of baselines by up to 9\%, even surpassing that of FedAvg in some cases.

Surgery requires comprehensive medical knowledge, visual assessment skills, and procedural expertise. While recent surgical AI models have focused on solving task-specific problems, there is a need for general-purpose systems that can understand surgical scenes and interact through natural language. This paper introduces GP-VLS, a general-purpose vision language model for surgery that integrates medical and surgical knowledge with visual scene understanding. For comprehensively evaluating general-purpose surgical models, we propose SurgiQual, which evaluates across medical and surgical knowledge benchmarks as well as surgical vision-language questions. To train GP-VLS, we develop six new datasets spanning medical knowledge, surgical textbooks, and vision-language pairs for tasks like phase recognition and tool identification. We show that GP-VLS significantly outperforms existing open- and closed-source models on surgical vision-language tasks, with 8-21% improvements in accuracy across SurgiQual benchmarks. GP-VLS also demonstrates strong performance on medical and surgical knowledge tests compared to open-source alternatives. Overall, GP-VLS provides an open-source foundation for developing AI assistants to support surgeons across a wide range of tasks and scenarios. The code and data for this work is publicly available at gpvls-surgery-vlm.github.io.

Miniaturized cyber-physical systems (CPSes) powered by tiny machine learning (TinyML), such as nano-drones, are becoming an increasingly attractive technology. Their small form factor (i.e., ~10cm diameter) ensures vast applicability, ranging from the exploration of narrow disaster scenarios to safe human-robot interaction. Simple electronics make these CPSes inexpensive, but strongly limit the computational, memory, and sensing resources available on board. In real-world applications, these limitations are further exacerbated by domain shift. This fundamental machine learning problem implies that model perception performance drops when moving from the training domain to a different deployment one. To cope with and mitigate this general problem, we present a novel on-device fine-tuning approach that relies only on the limited ultra-low power resources available aboard nano-drones. Then, to overcome the lack of ground-truth training labels aboard our CPS, we also employ a self-supervised method based on ego-motion consistency. Albeit our work builds on top of a specific real-world vision-based human pose estimation task, it is widely applicable for many embedded TinyML use cases. Our 512-image on-device training procedure is fully deployed aboard an ultra-low power GWT GAP9 System-on-Chip and requires only 1MB of memory while consuming as low as 19mW or running in just 510ms (at 38mW). Finally, we demonstrate the benefits of our on-device learning approach by field-testing our closed-loop CPS, showing a reduction in horizontal position error of up to 26% vs. a non-fine-tuned state-of-the-art baseline. In the most challenging never-seen-before environment, our on-device learning procedure makes the difference between succeeding or failing the mission.

To deploy machine learning models on-device, practitioners use compression algorithms to shrink and speed up models while maintaining their high-quality output. A critical aspect of compression in practice is model comparison, including tracking many compression experiments, identifying subtle changes in model behavior, and negotiating complex accuracy-efficiency trade-offs. However, existing compression tools poorly support comparison, leading to tedious and, sometimes, incomplete analyses spread across disjoint tools. To support real-world comparative workflows, we develop an interactive visual system called Compress and Compare. Within a single interface, Compress and Compare surfaces promising compression strategies by visualizing provenance relationships between compressed models and reveals compression-induced behavior changes by comparing models' predictions, weights, and activations. We demonstrate how Compress and Compare supports common compression analysis tasks through two case studies, debugging failed compression on generative language models and identifying compression artifacts in image classification models. We further evaluate Compress and Compare in a user study with eight compression experts, illustrating its potential to provide structure to compression workflows, help practitioners build intuition about compression, and encourage thorough analysis of compression's effect on model behavior. Through these evaluations, we identify compression-specific challenges that future visual analytics tools should consider and Compress and Compare visualizations that may generalize to broader model comparison tasks.

This study explores the integration of real-world machine learning (ML) projects using human-computer interfaces (HCI) datasets in college-level courses to enhance both teaching and learning experiences. Employing a comprehensive literature review, course websites analysis, and a detailed case study, the research identifies best practices for incorporating HCI datasets into project-based ML education. Key findings demonstrate increased student engagement, motivation, and skill development through hands-on projects, while instructors benefit from effective tools for teaching complex concepts. The study also addresses challenges such as data complexity and resource allocation, offering recommendations for future improvements. These insights provide a valuable framework for educators aiming to bridge the gap between theoretical knowledge and practical application in ML education.

Humans often learn new skills by imitating the experts and gradually developing their proficiency. In this work, we introduce Stochastic Trajectory Optimization for Demonstration Imitation (STODI), a trajectory optimization framework for robots to imitate the shape of demonstration trajectories with improved dynamic performance. Consistent with the human learning process, demonstration imitation serves as an initial step, while trajectory optimization aims to enhance robot motion performance. By generating random noise and constructing proper cost functions, the STODI effectively explores and exploits generated noisy trajectories while preserving the demonstration shape characteristics. We employ three metrics to measure the similarity of trajectories in both the time and frequency domains to help with demonstration imitation. Theoretical analysis reveals relationships among these metrics, emphasizing the benefits of frequency-domain analysis for specific tasks. Experiments on a 7-DOF robotic arm in the PyBullet simulator validate the efficacy of the STODI framework, showcasing the improved optimization performance and stability compared to previous methods.