21 accepted papers
Document-level knowledge graph (KG) construction faces a fundamental scaling challenge: existing methods either rely on expensive large language models (LLMs), making them economically unviable for large-scale corpora, or employ smaller models that produce incomplete and inconsistent graphs. We iden…
In this letter, we introduce HPGS-SLAM, a real-time RGB-D SLAM system guided by hybrid point features (combining traditional and learned point features), enabling high-precision tracking and online dense mapping with photorealistic reconstruction. HPGS-SLAM consists of two main components: (1) a lig
Time normalization is the task of converting natural language temporal expressions into machine-readable representations. It underpins many downstream applications in information retrieval, question answering, and clinical decision-making. Traditional systems based on the ISO-TimeML schema limit exp…
The paper focuses on the interpretability of Grammatical Error Correction (GEC) evaluation metrics, which received little attention in previous studies. To bridge the gap, we introduce **CLEME2.0**, a reference-based metric describing four fundamental aspects of GEC systems: hit-correction, wrong-co…
Visual Inertial Odometry (VIO) estimates predicted trajectories through self motion. With the popularization of artificial intelligence, deep learning-based VIO methods have shown better performance than traditional geometry-based VIO methods. However, in deep learning methods, how to better achieve
Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve promising performance, these methods fail to account for the intrin…
The advent of deep learning (DL) has transformed signal interpretation, enabling more efficient solutions to complex signal processing problems. DL workloads in signal processing typically share the computational resources of GPU clusters. However, the unpredictable nature of the duration of the DL…
Retrieving CAD models for real-world object scans enhances object-level mapping, providing a nuanced spatial understanding crucial for precise interactions in robotics or mixed reality. Commonly, CAD model retrieval is performed by matching features learned in Euclidean space. However, learning disc…
Chinese grammatical error correction (CGEC) aims to detect and correct errors in the input Chinese sentences. Recently, Pre-trained Language Models (PLMS) have been employed to improve the performance. However, current approaches ignore that correction difficulty varies across different instances an…
Multimodal retrieval-augmented generation (RAG) plays a crucial role in domains such as knowledge-based visual question answering (KB-VQA), where models should effectively integrate additional knowledge to generate a response. However, existing vision and language models (VLMs) are not inherently de…
Temporal information extraction (IE) aims to extract structured temporal information from unstructured text, thereby uncovering the implicit timelines within. This technique is applied across domains such as healthcare, newswire, and intelligence analysis, aiding models in these areas to perform tem
Given its wide application in robotics, point cloud registration is a widely researched topic. Conventional methods aim to find a rotation and translation that align two point clouds in 6 degrees of freedom (DoF). However, certain tasks in robotics, such as category-level pose estimation, involve no…
Visual SLAM is an essential tool in diverse applications such as robot perception and extended reality, where feature-based methods are prevalent due to their accuracy and robustness. However, existing methods employ either hand-crafted or solely learnable point features and are thus limited by the…
An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model’s parametric memory, external structured knowledge, and external unstructured knowledge. Most existing prompting methods either rely on…
Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents. An important open question is whether large language models can perform such reasoning solely using a provided text document, or whether they can benefit from additional temp…
In recent years, Action Detection has become an active research topic in various fields such as human-robot interaction and assistive robots. Most of the previous methods in this field focus on temporally processing the action representation, without considering the dependencies among the action cla…
Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free domain adaptation. We take algorithms that traditionally assume access to the s…
Most SLAM (Simultaneous Localization and Mapping) algorithms are based on the assumption that the scene is static. However, in practice, most real scenes usually contain moving objects. In this letter, we introduce DymSLAM, a dynamic stereo visual SLAM system being capable of reconstructing a 4D (3D
In sim-to-real transfer of Reinforcement Learning (RL) policies for robot tasks, Domain Randomization (DR) is a widely used technique for improving adaptability. However, in DR there is a conflict between adaptability and training stability, and heavy DR tends to result in instability or even failur…
Beyond machine learning’s success in the specific tasks, research for learning multiple tasks simultaneously is referred to as multi-task learning. However, existing multi-task learning needs manual definition of tasks and manual task annotation. A crucial problem for advanced intelligence is how to…
In this paper, we explore the use of graph-based transforms to capture correlation in light fields. We consider a scheme in which view synthesis is used as a first step to exploit inter-view correlation. Local graph-based transforms (GT) are then considered for energy compaction of the residue signa…