Related papers: GenZ: Foundational models as latent variable gener…

Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in semantic parsing, we…

Conventional centralised deep learning paradigms are not feasible when data from different sources cannot be shared due to data privacy or transmission limitation. To resolve this problem, federated learning has been introduced to transfer…

Conventional mechanical design follows an iterative process in which initial concepts are refined through cycles of expert assessment and resource-intensive Finite Element Method (FEM) analysis to meet performance goals. While machine…

Semantic segmentation in a supervised learning manner has achieved significant progress in recent years. However, its performance usually drops dramatically due to the data-distribution discrepancy between seen and unseen domains when we…

Consider a movie studio aiming to produce a set of new movies for summer release: What types of movies it should produce? Who would the movies appeal to? How many movies should it make? Similar issues are encountered by a variety of…

Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like data sparsity and cold start, recent researchs have leveraged data from multiple…

The present study explores the interpretability of latent spaces produced by time series foundation models, focusing on their potential for visual analysis tasks. Specifically, we evaluate the MOMENT family of models, a set of…

Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic…

Deep Generative Models (DGMs) are versatile tools for learning data representations while adequately incorporating domain knowledge such as the specification of conditional probability distributions. Recently proposed DGMs tackle the…

Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user through inner product computation between the user and all item…

Large Language Models (LLMs) are being increasingly used within data systems to process large datasets with text fields. A broad class of such tasks involves a semantic join-joining two tables based on a natural language predicate per pair…

Modern software often accepts inputs with highly complex grammars. Recent advances in large language models (LLMs) have shown that they can be used to synthesize high-quality natural language text and code that conforms to the grammar of a…

Latent variable collaborative filtering methods have been a standard approach to modelling user-click interactions due to their simplicity and effectiveness. However, there is limited work on analyzing the mathematical properties of these…

Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models. We propose a…

Humans often communicate by using imprecise language, suggesting that fuzzy concepts with unclear boundaries are prevalent in language use. In this paper, we test the extent to which models trained to capture the distributional statistics…

Generative modelling is a demanding test of foundation models, because it requires robust, holistic representation learning for a given data modality, rather than optimisation for a supervised prediction target alone. While recent work on…

The rapid evolution of generative adversarial networks (GANs) and diffusion models has made synthetic media increasingly realistic, raising societal concerns around misinformation, identity fraud, and digital trust. Existing deepfake…

Modern recommender systems struggle to effectively utilize the rich, yet high-dimensional and noisy, multi-modal features generated by Large Language Models (LLMs). Treating these features as static inputs decouples them from the core…

Regularized regression models are well studied and, under appropriate conditions, offer fast and statistically interpretable results. However, large data in many applications are heterogeneous in the sense of harboring distributional…

Humans can learn to solve new tasks by inducing high-level strategies from example solutions to similar problems and then adapting these strategies to solve unseen problems. Can we use large language models to induce such high-level…