Related papers: TAPAS: Datasets for Learning the Learning with Err…

Rapid progress in generative AI has given rise to Compound AI systems - pipelines comprised of multiple large language models (LLM), software tools and database systems. Compound AI systems are constructed on a layered traditional software…

Self-supervised pre-training has drawn increasing attention in recent years due to its superior performance on numerous downstream tasks after fine-tuning. However, it is well-known that deep learning models lack the robustness to…

As a powerful tool of asynchronous event sequence analysis, point processes have been studied for a long time and achieved numerous successes in different fields. Among various point process models, Hawkes process and its variants attract…

Semi-supervised learning that leverages synthetic data for training has been widely adopted for developing automatic post-editing (APE) models due to the lack of training data. With this aim, we focus on data-synthesis methods to create…

Recent advances have demonstrated that integrating reinforcement learning with rule-based rewards can significantly enhance the reasoning capabilities of large language models, even without supervised fine-tuning. However, prevalent…

Deep learning and deep architectures are emerging as the best machine learning methods so far in many practical applications such as reducing the dimensionality of data, image classification, speech recognition or object segmentation. In…

Deep learning has a wide range of applications in industrial scenario, but reducing false alarm (FA) remains a major difficulty. Optimizing network architecture or network parameters is used to tackle this challenge in academic circles,…

This paper explores post-disaster analytics using multimodal deep learning models trained with curriculum learning method. Studying post-disaster analytics is important as it plays a crucial role in mitigating the impact of disasters by…

Automated data preparation is crucial for democratizing machine learning, yet existing reinforcement learning (RL) based approaches suffer from inefficient exploration in the vast space of possible preprocessing pipelines. We present…

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

PAWS is a tool to analyse the behaviour of weighted automata and conditional transition systems. At its core PAWS is based on a generic implementation of algorithms for checking language equivalence in weighted automata and bisimulation in…

Cyber-attack attribution is an important process that allows experts to put in place attacker-oriented countermeasures and legal actions. The analysts mainly perform attribution manually, given the complex nature of this task. AI and, more…

Adequate labeled data and expensive compute resources are the prerequisites for the success of neural architecture search(NAS). It is challenging to apply NAS in meta-learning scenarios with limited compute resources and data. In this…

Adversarial training (AT) is a robust learning algorithm that can defend against adversarial attacks in the inference phase and mitigate the side effects of corrupted data in the training phase. As such, it has become an indispensable…

Evaluating the security of multi-agent systems (MASs) powered by large language models (LLMs) is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack…

With the increasing prevalence of Web-based platforms handling vast amounts of user data, machine unlearning has emerged as a crucial mechanism to uphold users' right to be forgotten, enabling individuals to request the removal of their…

Outsourced databases powered by fully homomorphic encryption (FHE) offer the promise of secure data processing on untrusted cloud servers. A crucial aspect of database functionality, and one that has remained challenging to integrate…

Quality Estimation (QE) aims to assess the quality of machine translation (MT) outputs without relying on reference translations, making it essential for real-world, large-scale MT evaluation. Large Language Models (LLMs) have shown…

This tutorial addresses the challenge of incorporating large language models (LLMs), such as ChatGPT, in a data analytics class. It details several new in-class and out-of-class teaching techniques enabled by AI. For example, instructors…