Related papers: SAGE: Sparse Adaptive Guidance for Dependency-Awar…
Improved prediction of personalized health outcomes -- such as sleep quality and stress -- from multimodal lifelog data could have meaningful clinical and practical implications. However, state-of-the-art models, primarily deep neural…
While most generative models show achievements in image data generation, few are developed for tabular data generation. Recently, due to success of large language models (LLM) in diverse tasks, they have also been used for tabular data…
The increasing reliance on Large Language Models (LLMs) across diverse sectors highlights the need for robust domain-specific and language-specific evaluation datasets; however, the collection of such datasets is challenging due to privacy…
Large Language Models (LLMs) offer a flexible means to generate synthetic tabular data, yet existing approaches often fail to preserve key causal parameters such as the average treatment effect (ATE). In this technical exploration, we first…
The common sense reasoning abilities and vast general knowledge of Large Language Models (LLMs) make them a natural fit for interpreting user requests in a Smart Home assistant context. LLMs, however, lack specific knowledge about the user…
Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and…
Unsupervised Graph Domain Adaptation (UGDA) leverages labeled source domain graphs to achieve effective performance in unlabeled target domains despite distribution shifts. However, existing methods often yield suboptimal results due to the…
Surface electromyography (sEMG)-based gesture recognition plays a critical role in human-machine interaction (HMI), particularly for rehabilitation and prosthetic control. However, sEMG-based systems often suffer from the scarcity of…
Generative models for tabular data have evolved rapidly beyond Generative Adversarial Networks (GANs). While GANs pioneered synthetic tabular data generation, recent advances in diffusion models and large language models (LLMs) have opened…
Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have proven effective for explaining the…
Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying…
Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as…
High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…
The generation of data is a common approach to improve the performance of machine learning tasks, among which is the training of models for classification. In this paper, we present TAGAL, a collection of methods able to generate synthetic…
Large language models (LLMs) have shown promise in synthetic tabular data generation, yet existing methods struggle to preserve complex feature dependencies, particularly among categorical variables. This work introduces a…
Pre-trained language models advance patent classification and retrieval via encoding claims as flat token sequences, yet overlooking the dependency hierarchy among claims. Incorporating the hierarchy into self-attention poses two…
The rapid advancement of large language models (LLMs) has sparked interest in data synthesis techniques, aiming to generate diverse and high-quality synthetic datasets. However, these synthetic datasets often suffer from a lack of diversity…
Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks. However, the lack of domain-specific knowledge makes it challenging to bridge the topological gap between tabular data and text, especially…
Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation techniques range from simple photometric and geometrical…
Handling imbalanced target distributions in regression poses a persistent challenge, as the underrepresentation of relevant target values can significantly hinder model performance. Existing data-level solutions often adapt…