Related papers: Problem Space Transformations for Out-of-Distribut…

In the field of computer vision, fine-tuning pre-trained models has become a prevalent strategy for out-of-distribution (OOD) generalization tasks. Different from most prior work that has focused on advancing learning algorithms, we…

Algorithms for learning programmatic representations for sequential decision-making problems are often evaluated on out-of-distribution (OOD) problems, with the common conclusion that programmatic policies generalize better than neural…

Out-of-distribution (OOD) generalisation is considered a hallmark of human and animal intelligence. To achieve OOD through composition, a system must discover the environment-invariant properties of experienced input-output mappings and…

Traditional machine learning paradigms are based on the assumption that both training and test data follow the same statistical pattern, which is mathematically referred to as Independent and Identically Distributed ($i.i.d.$). However, in…

Systematic, compositional generalization beyond the training distribution remains a core challenge in machine learning -- and a critical bottleneck for the emergent reasoning abilities of modern language models. This work investigates…

Out-of-distribution generalization (OODG) is a longstanding challenge for neural networks. This challenge is quite apparent in tasks with well-defined variables and rules, where explicit use of the rules could solve problems independently…

Although recent advances in machine learning have shown its success to learn from independent and identically distributed (IID) data, it is vulnerable to out-of-distribution (OOD) data in an open world. Domain generalization (DG) deals with…

Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically when encountering out-of-distribution (OoD) data, i.e., when…

With the availability of large pre-trained models, a modern workflow for building real-world machine learning solutions is to fine-tune such models on a downstream task with a relatively small domain-specific dataset. In such applications,…

Our goal is to perform out-of-distribution (OOD) detection, i.e., to detect when a robot is operating in environments drawn from a different distribution than the ones used to train the robot. We leverage Probably Approximately Correct…

There has been a massive increase in research interest towards applying data driven methods to problems in mechanics. While traditional machine learning (ML) methods have enabled many breakthroughs, they rely on the assumption that the…

Machine learning models often fail to generalize well under distributional shifts. Understanding and overcoming these failures have led to a research field of Out-of-Distribution (OOD) generalization. Despite being extensively studied for…

Machine learning models, while progressively advanced, rely heavily on the IID assumption, which is often unfulfilled in practice due to inevitable distribution shifts. This renders them susceptible and untrustworthy for deployment in…

Despite multiple efforts made towards robust machine learning (ML) models, their vulnerability to adversarial examples remains a challenging problem that calls for rethinking the defense strategy. In this paper, we take a step back and…

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d.~assumption on source/target data, which is…

Clinical machine learning models show a significant performance drop when tested in settings not seen during training. Domain generalisation models promise to alleviate this problem, however, there is still scepticism about whether they…

Generalizing beyond the training domain in image-based behavior cloning remains challenging. Existing methods address individual axes of generalization, workspace shifts, viewpoint changes, and cross-embodiment transfer, yet they are…

Machine learning (ML) systems in natural language processing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differs from the training data distribution. This poses important…

Generalization to out-of-distribution (OOD) data is one of the central problems in modern machine learning. Recently, there is a surge of attempts to propose algorithms that mainly build upon the idea of extracting invariant features.…

Learning from previously collected datasets of expert data offers the promise of acquiring robotic policies without unsafe and costly online explorations. However, a major challenge is a distributional shift between the states in the…