Related papers: Preliminary Experiments using Subjective Logic for…

Learning neural subset selection tasks, such as compound selection in AI-aided drug discovery, have become increasingly pivotal across diverse applications. The existing methodologies in the field primarily concentrate on constructing…

Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…

Mutual information maximization provides an appealing formalism for learning representations of data. In the context of reinforcement learning (RL), such representations can accelerate learning by discarding irrelevant and redundant…

Multimodal self-supervised representation learning has consistently proven to be a highly effective method in medical image analysis, offering strong task performance and producing biologically informed insights. However, these methods…

Cross-lingual text representations have gained popularity lately and act as the backbone of many tasks such as unsupervised machine translation and cross-lingual information retrieval, to name a few. However, evaluation of such…

Analytical information needs, such as trend analysis and causal impact assessment, are prevalent across various domains including law, finance, science, and much more. However, existing information retrieval paradigms, whether based on…

Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two…

A recommendation system assists users in finding items that are relevant to them. Existing recommendation models are primarily based on predicting relationships between users and items and use complex matching models or incorporate…

This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates…

Plausibility models are Kripke models that agents use to reason about knowledge and belief, both of themselves and of each other. Such models are used to interpret the notions of conditional belief, degrees of belief, and safe belief. The…

Learning a compact representation of history is critical for planning and generalization in partially observable environments. While meta-reinforcement learning (RL) agents can attain near Bayes-optimal policies, they often fail to learn…

Existing studies of innovation emphasize the power of social structures to shape innovation capacity. Emerging machine learning approaches, however, enable us to model innovators' personal perspectives and interpersonal innovation…

In large language model-based agents, memory serves as a critical capability for achieving personalization by storing and utilizing users' information. Although some previous studies have adopted memory to implement user personalization,…

Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…

Proof assistants play a dual role as programming languages and logical systems. As programming languages, proof assistants offer standard modularity mechanisms such as first-class functions, type polymorphism and modules. As logical…

Query-expansion via pseudo-relevance feedback is a popular method of overcoming the problem of vocabulary mismatch and of increasing average retrieval effectiveness. In this paper, we develop a new method that estimates a query topic model…

The crucial role of the evaluation in the development of the information retrieval tools is useful evidence to improve the performance of these tools and the quality of results that they return. However, the classic evaluation approaches…

In real-world scenarios, typical visual recognition systems could fail under two major causes, i.e., the misclassification between known classes and the excusable misbehavior on unknown-class images. To tackle these deficiencies, flexible…

Simulation-based inference enables learning the parameters of a model even when its likelihood cannot be computed in practice. One class of methods uses data simulated with different parameters to infer models of the likelihood-to-evidence…

Language models often struggle with handling factual knowledge, exhibiting factual hallucination issue. This makes it vital to evaluate the models' ability to recall its parametric knowledge about facts. In this study, we introduce a…