Related papers: Learning Domain-Specific Edit Operations from Mode…
Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…
Autonomous driving technologies have received notable attention in the past decades. In autonomous driving systems, identifying a precise dynamical model for motion control is nontrivial due to the strong nonlinearity and uncertainty in…
Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes.…
Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single…
Many engineered as well as naturally occurring dynamical systems do not have an accurate mathematical model to describe their dynamic behavior. However, in many applications, it is possible to probe the system with external inputs and…
Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document…
Off-the-shelf models are widely used by computational social science researchers to measure properties of text, such as sentiment. However, without access to source data it is difficult to account for domain shift, which represents a threat…
Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…
Model transformations are the cornerstone of Model-Driven Engineering, and provide the essential mechanisms for manipulating and transforming models. Checking whether the output of a model transformation is correct is a manual and…
The study of mechanistic interpretability aims to reverse-engineer a model to explain its behaviors. While recent studies have focused on the static mechanism of a certain behavior, the learning dynamics inside a model remain to be…
Foundation models (FM) have demonstrated remarkable performance across a wide range of tasks (especially in the fields of natural language processing and computer vision), primarily attributed to their ability to comprehend instructions and…
Deployed real-world machine learning applications are often subject to uncontrolled and even potentially malicious inputs. Those out-of-domain inputs can lead to unpredictable outputs and sometimes catastrophic safety issues. Prior studies…
Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…
Modeling structure and behavior of software systems plays a crucial role, in various areas of software engineering. As with other software engineering artifacts, software models are subject to evolution. Supporting modelers in evolving…
Neural networks often require large amounts of expert annotated data to train. When changes are made in the process of medical imaging, trained networks may not perform as well, and obtaining large amounts of expert annotations for each…
Model editing aims to enhance the accuracy and reliability of large language models (LLMs) by efficiently adjusting their internal parameters. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited…
The automation of condition monitoring and workpiece inspection plays an essential role in maintaining high quality as well as high throughput of the manufacturing process. To this end, the recent rise of developments in machine learning…
While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift…
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…