Related papers: Bridging the Gap between Different Vocabularies fo…

Entity alignment, which is a prerequisite for creating a more comprehensive Knowledge Graph (KG), involves pinpointing equivalent entities across disparate KGs. Contemporary methods for entity alignment have predominantly utilized knowledge…

Visual analytics supports data analysis tasks within complex domain problems. However, due to the richness of data types, visual designs, and interaction designs, users need to recall and process a significant amount of information when…

Large language models (LLMs) are at the forefront of transforming numerous domains globally. However, their inclusivity and effectiveness remain limited for non-Latin scripts and low-resource languages. This paper tackles the imperative…

The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves…

Finetuned LLMs often exhibit poor uncertainty quantification, manifesting as overconfidence, poor calibration, and unreliable prediction results on test data or out-of-distribution samples. One approach commonly used in vision for…

Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level…

We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can…

Combining multiple knowledge graphs (KGs) across linguistic boundaries is a persistent challenge due to semantic heterogeneity and the complexity of graph environments. We propose a framework for cross-lingual graph fusion, leveraging the…

Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work…

Large Language Models (LLMs) have achieved remarkable success across diverse applications, yet their deployment remains challenging due to substantial computational costs, memory requirements, and energy consumption. Recent empirical…

The training and fine-tuning of large language models (LLMs) often involve diverse textual data from multiple sources, which poses challenges due to conflicting gradient directions, hindering optimization and specialization. These…

Designing optimization approaches, whether heuristic or meta-heuristic, usually demands extensive manual intervention and has difficulty generalizing across diverse problem domains. The combination of Large Language Models (LLMs) and…

Recently, there has been a surging interest in using large language models (LLMs) for Verilog code generation. However, the existing approaches are limited in terms of the quality of the generated Verilog code. To address such limitations,…

Large language models (LLMs) exhibit complementary strengths in various tasks, motivating the research of LLM ensembling. However, existing work focuses on training an extra reward model or fusion model to select or combine all candidate…

Large Language Models (LLMs) excel in various natural language processing tasks, but leveraging them for dense passage embedding remains challenging. This is due to their causal attention mechanism and the misalignment between their…

This paper addresses the challenge of integrating 3D meshes as a native modality within Multimodal Large Language Models (MLLMs). Diffusion-based large reconstruction models decouple semantic understanding from geometric reasoning,…

Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box…

Large decoder-only language models (LLMs) have achieved remarkable success in generation and reasoning tasks, where they generate text responses given instructions. However, many applications, e.g., retrieval augmented generation (RAG),…

Although Large Language Models (LLMs) perform well in general fields, they exhibit a confidence distortion problem on multi-choice question-answering (MCQA), particularly as the number of answer choices increases. Specifically, on MCQA with…

Current large vision-language models (VLMs) often encounter challenges such as insufficient capabilities of a single visual component and excessively long visual tokens. These issues can limit the model's effectiveness in accurately…