Related papers: Entity-enhanced Adaptive Reconstruction Network fo…

Retrieval-Augmented Generation (RAG) improves reliability of large language models by incorporating external knowledge, but the retrieval process can introduce bias that propagates to generated outputs. This issue is particularly…

Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions…

Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to overthink on simple problems, producing unnecessarily lengthy…

Referring image segmentation aims to produce a pixel-level mask for the image region described by a natural-language expression. Although pretrained vision-language models have improved semantic grounding, many existing methods still rely…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…

State-of-the-art entity matching (EM) methods are hard to interpret, and there is significant value in bringing explainable AI to EM. Unfortunately, most popular explainability methods do not work well out of the box for EM and need…

Retrieval augmentation, which enhances downstream models by a knowledge retriever and an external corpus instead of by merely increasing the number of model parameters, has been successfully applied to many natural language processing (NLP)…

Generative approaches powered by large language models (LLMs) have demonstrated emergent abilities in tasks that require complex reasoning abilities. Yet the generative nature still makes the generated content suffer from hallucinations,…

The relational model is a ubiquitous representation of big-data, in part due to its extensive use in databases. In this paper, we propose the Equivariant Entity-Relationship Network (EERN), which is a Multilayer Perceptron equivariant to…

The manifold assumption for high-dimensional data assumes that the data is generated by varying a set of parameters obtained from a low-dimensional latent space. Deep generative models (DGMs) are widely used to learn data representations in…

Foundation models (FMs) offer powerful representations for geospatial analysis, but adapting them effectively remains challenging. Standard adaptation methods, whether full fine-tuning or efficient frozen-backbone approaches, typically…

Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate these capabilities holistically. To bridge this gap, we…

Entity linking (EL) is the computational process of connecting textual mentions to corresponding entities. Like many areas of natural language processing, the EL field has greatly benefited from deep learning, leading to significant…

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

In recent years, great success has been achieved in many tasks of natural language processing (NLP), e.g., named entity recognition (NER), especially in the high-resource language, i.e., English, thanks in part to the considerable amount of…

Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the…

Randomized neural network (RaNN) methods have been proposed for solving various partial differential equations (PDEs), demonstrating high accuracy and efficiency. However, initializing the fixed parameters remains challenging. Additionally,…

Referring Expression Comprehension (REC) requires models to localize objects in images based on natural language descriptions. Research on the area remains predominantly English-centric, despite increasing global deployment demands. This…

Entity Alignment (EA) aims to match equivalent entities in different Knowledge Graphs (KGs), which is essential for knowledge fusion and integration. Recently, embedding-based EA has attracted significant attention and many approaches have…

We present a novel graph neural network (GNN) architecture for retrieval-augmented generation (RAG) that leverages query-aware attention mechanisms and learned scoring heads to improve retrieval accuracy on complex, multi-hop questions.…