Related papers: SMUTF: Schema Matching Using Generative Tags and H…
Synthesizing high-quality tabular data is an important topic in many data science tasks, ranging from dataset augmentation to privacy protection. However, developing expressive generative models for tabular data is challenging due to its…
We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a)…
Multi-Agent Pickup and Delivery (MAPD) is a fundamental problem in robotics, particularly in applications such as warehouse automation and logistics. Existing solutions often face challenges in scalability, adaptability, and efficiency,…
This study tackles the challenge of image matching in difficult scenarios, such as scenes with significant variations or limited texture, with a strong emphasis on computational efficiency. Previous studies have attempted to address this…
Reproducibility of computational results remains a challenge in materials science, as simulation workflows and parameters are often reported only in unstructured text and tables. While literature data are valuable for validation and reuse,…
Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data. Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the…
The increasingly collaborative, globalized nature of scientific research combined with the need to share data and the explosion in data volumes present an urgent need for a scientific data management system (SDMS). An SDMS presents a…
Graph Neural Networks (GNNs) have demonstrated their superiority in collaborative filtering, where the user-item (U-I) interaction bipartite graph serves as the fundamental data format. However, when graph-structured side information (e.g.,…
Text-based collaborative filtering (TCF) has emerged as the prominent technique for text and news recommendation, employing language models (LMs) as text encoders to represent items. However, the current landscape of TCF models mainly…
Multimodal sentiment analysis (MSA) aims to infer emotional states by effectively integrating textual, acoustic, and visual modalities. Despite notable progress, existing multimodal fusion methods often neglect modality-specific structural…
Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have…
Although pre-trained visual models with text have demonstrated strong capabilities in visual feature extraction, sticker emotion understanding remains challenging due to its reliance on multi-view information, such as background knowledge…
Symmetric nonnegative matrix factorization (SNMF) has demonstrated to be a powerful method for data clustering. However, SNMF is mathematically formulated as a non-convex optimization problem, making it sensitive to the initialization of…
Traditional joint source-channel coding employs static learned semantic representations that cannot dynamically adapt to evolving source distributions. Shared semantic memories between transmitter and receiver can potentially enable…
Feature transformation enhances data representation by deriving new features from the original data. Generative AI offers potential for this task, but faces challenges in stable generation (consistent outputs) and valid generation…
In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…
Knowledge graphs (KGs) and multimodal item information, which respectively capture relational and attribute features, play a crucial role in improving recommender system accuracy. Recent studies have attempted to integrate them via…
Joint analysis of data from multiple information repositories facilitates uncovering the underlying structure in heterogeneous datasets. Single and coupled matrix-tensor factorization (CMTF) has been widely used in this context for…
Graph collaborative filtering (GCF) is a dominant paradigm in recommender systems, where contrastive learning (CL) objectives such as the Sampled Softmax (SSM) loss are widely used for optimization. However, it remains unclear how CL…
Policy optimization in high-dimensional continuous control for robotics remains a challenging problem. Predominant methods are inherently local and often require extensive tuning and carefully chosen initial guesses for good performance,…