Related papers: On-the-Fly Adaptation of Source Code Models using …

Continued pre-training of small language models offers a promising path for domain adaptation with limited computational resources. I've investigated this approach within educational domains, evaluating it as a resource-efficient…

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…

Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…

Few-shot learning, a challenging task in machine learning, aims to learn a classifier adaptable to recognize new, unseen classes with limited labeled examples. Meta-learning has emerged as a prominent framework for few-shot learning. Its…

Syntax highlighting is a critical feature in modern software development environments, enhancing code readability and developer productivity. However, delivering accurate highlighting in real time remains challenging for online and…

Learning-based model predictive control has been widely applied in autonomous racing to improve the closed-loop behaviour of vehicles in a data-driven manner. When environmental conditions change, e.g., due to rain, often only the…

Source-Free Domain Adaptation (SFDA) seeks to adapt a source model, which is pre-trained on a supervised source domain, for a target domain, with only access to unlabeled target training data. Relying on pseudo labeling and/or auxiliary…

Most unsupervised domain adaptation (UDA) methods assume that labeled source images are available during model adaptation. However, this assumption is often infeasible owing to confidentiality issues or memory constraints on mobile devices.…

We propose ADAPT, a meta-learning algorithm that \emph{learns} task sampling proportions under an explicit token budget for multi-task instruction tuning. Instead of fixing task weights by hand, \adapt{} maintains a continuous distribution…

Despite the progress seen in classification methods, current approaches for handling videos with distribution shifts in source and target domains remain source-dependent as they require access to the source data during the adaptation stage.…

In this paper, we propose a learning algorithm that enables a model to quickly exploit commonalities among related tasks from an unseen task distribution, before quickly adapting to specific tasks from that same distribution. We investigate…

Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…

Faults are endemic to all systems. Adaptive fault-tolerant control maintains degraded performance when faults occur as opposed to unsafe conditions or catastrophic events. In systems with abrupt faults and strict time constraints, it is…

Text-based person retrieval aims to identify specific individuals within an image database using textual descriptions. Due to the high cost of annotation and privacy protection, researchers resort to synthesized data for the paradigm of…

AI modeling for source code understanding tasks has been making significant progress, and is being adopted in production development pipelines. However, reliability concerns, especially whether the models are actually learning task-related…

Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain…

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework. Such framework naturally gives the information about…

Despite the known limitations, most machine translation systems today still operate on the sentence-level. One reason for this is, that most parallel training data is only sentence-level aligned, without document-level meta information…

As code generation becomes increasingly central to improving software development efficiency, modern code models are largely trained and evaluated on code with natural-language descriptions. In real projects, developers often implement…

The costly human effort required to prepare the training data of machine learning (ML) models hinders their practical development and usage in software engineering (ML4Code), especially for those with limited budgets. Therefore, efficiently…