Related papers: Pre-trained Model-based Actionable Warning Identif…

Malware analysis and detection techniques have been evolving during the last decade as a reflection to development of different malware techniques to evade network-based and host-based security protections. The fast growth in variety and…

Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and alignment choices. While pretraining encourages models to exploit all available…

Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also growing concerns regarding the potential security issues in the…

Online model predictive control (MPC) for piecewise affine (PWA) systems requires the online solution to an optimization problem that implicitly optimizes over the switching sequence of PWA regions, for which the computational burden can be…

Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such as speech. To better align language models with the speech…

Multi-task learning, in which several tasks are jointly learned by a single model, allows NLP models to share information from multiple annotations and may facilitate better predictions when the tasks are inter-related. This technique,…

For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield…

Recent applications of machine learning (ML) reveal a noticeable shift from its use for predictive modeling in the sense of a data-driven construction of models mainly used for the purpose of prediction (of ground-truth facts) to its use…

While initial applications of artificial intelligence (AI) in wireless communications over the past decade have demonstrated considerable potential using specialized models for targeted communication tasks, the revolutionary demands of…

Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult. Provable guarantees for unlearning are often limited to…

Structured prediction is often approached by training a locally normalized model with maximum likelihood and decoding approximately with beam search. This approach leads to mismatches as, during training, the model is not exposed to its…

In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts…

We study semisupervised mean estimation with a small labeled sample, a large unlabeled sample, and a black-box prediction model whose output may be miscalibrated. A standard approach in this setting is augmented inverse-probability…

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and…

Machine learning-based classifiers have been used for text classification, such as sentiment analysis, news classification, and toxic comment classification. However, supervised machine learning models often require large amounts of labeled…

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However,…

Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…

Foundation models (FMs) are recognized as a transformative breakthrough that has started to reshape the future of artificial intelligence (AI) across both academia and industry. The integration of FMs into wireless networks is expected to…