Related papers: Retrieval of Temporal Event Sequences from Textual…

Large language models (LLMs) have emerged as promising tools for assisting in medical tasks, yet processing Electronic Health Records (EHRs) presents unique challenges due to their longitudinal nature. While LLMs' capabilities to perform…

Representing continuous time is a critical and under-explored challenge in modeling temporal event sequences with large language models (LLMs). Various strategies like byte-level representations or calendar tokens have been proposed.…

Automatic speech recognition in reverberant conditions is a challenging task as the long-term envelopes of the reverberant speech are temporally smeared. In this paper, we propose a neural model for enhancement of sub-band temporal…

Universal multimodal embedding models have achieved great success in capturing semantic relevance between queries and candidates. However, current methods either condense queries and candidates into a single vector, potentially limiting the…

Retrieval-Augmented Generation (RAG) systems in chemistry heavily depend on accurate and relevant retrieval of chemical literature. However, general-purpose text embedding models frequently fail to adequately represent complex chemical…

This paper introduces a novel spatiotemporal feature representation model designed to address the limitations of traditional methods in multidimensional time series (MTS) analysis. The proposed approach converts MTS into one-dimensional…

Unsupervised human motion segmentation (HMS) can be effectively achieved using subspace clustering techniques. However, traditional methods overlook the role of temporal semantic exploration in HMS. This paper explores the use of temporal…

Automatically describing video content with natural language is a fundamental challenge of multimedia. Recurrent Neural Networks (RNN), which models sequence dynamics, has attracted increasing attention on visual interpretation. However,…

Autonomous agents operating in dynamic and safety-critical environments require decision-making frameworks that are both computationally efficient and physically grounded. However, many existing approaches rely on end-to-end learning, which…

Continuous embeddings of tokens in computer programs have been used to support a variety of software development tools, including readability, code search, and program repair. Contextual embeddings are common in natural language processing…

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…

Network embedding techniques are powerful to capture structural regularities in networks and to identify similarities between their local fabrics. However, conventional network embedding models are developed for static structures, commonly…

Current multimodal information retrieval studies mainly focus on single-image inputs, which limits real-world applications involving multiple images and text-image interleaved content. In this work, we introduce the text-image interleaved…

More than 80% of today's data is unstructured in nature, and these unstructured datasets evolve over time. A large part of these datasets are text documents generated by media outlets, scholarly articles in digital libraries, findings from…

Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks. However, they struggle with temporal reasoning, which requires processing time-related…

Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack…

Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length contextualized…

Vision-language models (VLMs) have shown remarkable progress in offline tasks such as image captioning and video question answering. However, real-time interactive environments impose new demands on VLMs, requiring them to generate…

Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on implicitly modeling audio and visual features through weak…

Reconstructing precise clinical timelines is essential for modeling patient trajectories and forecasting risk in complex, heterogeneous conditions like sepsis. While unstructured clinical narratives offer semantically rich and contextually…