56 accepted papers
Cross-modal hashing has emerged as a pivotal solution for efficient retrieval across diverse modalities, such as images and texts, by mapping them into compact binary hash spaces. However, in real-world scenarios, the modalities data is often missing or misaligned. Existing methods are most rely on
The scarcity of parallel corpora for Mongolian and Chinese constrains the performance of Mongolian-Chinese neural machine translation (NMT), particularly manifesting in inadequate accuracy in translating specialized terminology. To address this limitation, this study adopts a lexically constrained a
Designing molecules with desired properties, aka the oRiented molEcule Design (RED), is a fundamental task in chemistry and materials science. While graph diffusion models (GDMs) and reinforcement learning techniques (RL) show promise in molecule structure generation and property optimization stages
Generative recommendation as a new paradigm is influencing the current development of recommender systems. It aims to assign identifiers that capture richer semantic and collaborative information to items, and subsequently predict item identifiers via autoregressive generation using Large Language M
Discrete Flow Matching (DFM) presents a promising approach for graph generation; however, existing adaptations often introduce substantial complexity by incorporating task-specific heuristics, compromising the continuity equation and significantly expanding the hyperparameter space. Moreover, their …
This article proposes a whole-body impedance coordinative control framework for a wheel-legged humanoid robot to achieve adaptability on complex terrains while maintaining the robot's upper body stability. The framework contains a bi-level control strategy. The outer level is a variable-damping impe
This paper proposes a fair control framework for multi-robot systems, which integrates the newly introduced Alternative Authority Control (AAC) and Flexible Control Barrier Function (F-CBF). Control authority refers to a single robot which can plan its trajectory while considering others as moving o
Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with t
Despite growing interest in Theory of Mind (ToM) tasks for evaluating language models (LMs), little is known about how LMs internally represent mental states of self and others. Understanding these internal mechanisms is critical - not only to move beyond surface-level performance, but also for mode
Long-term time series forecasting has been widely studied, yet two aspects remain insufficiently explored: the interaction learning between different frequency components and the exploitation of periodic characteristics inherent in timestamps. To address the above issues, we propose **CFPT**, a nov…
Message-passing Graph Neural Networks (GNNs) are often criticized for their limited expressiveness, issues like over-smoothing and over-squashing, and challenges in capturing long-range dependencies. Conversely, Graph Transformers (GTs) are regarded as superior due to their employment of global atte…
The demand for multimodal data processing drives the development of information technology. Cross-modal hash retrieval has attracted much attention because it can overcome modal differences and achieve efficient retrieval, and has shown great application potential in many practical scenarios. Existi…
Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have demonstrated significant potential in automated fact-checking. However, existing methods face limitations in insufficient evidence utilization and lack of explicit verification criteria. Specifically, these approaches aggrega
Fire detection technology based on deep learning methods has become a prevalent practice. However, the performance of current YOLO-based detection models is limited by NMS, and DETR-based detection models struggle with real-time performance. To address these challenges, a new fire detection model, F…
Adding imperceptible watermarks to artwork images, such as paintings and photographs, can effectively safeguard the copyright of these images without compromising their usability. However, existing blind watermarking techniques encounter two major challenges in addressing this task: imperceptibility…
Recent advances in retrieval-based in-context learning (ICL) train the retriever using a classification objective, which categorizes in-context examples (ICEs) into the most useful and the rest based on absolute scores. However, during inference, ICEs are retrieved by score ranking rather than class…
Large Language Models (LLMs) enable a new form of digital experimentation where treatments combine human and model-generated content in increasingly sophisticated ways. The main methodological challenge in this setting is representing these high-dimensional treatments without losing their semantic m…
Personality detection aims to deduce a user’s personality from their published posts. The goal of this task is to map posts to specific personality types. Existing methods encode post information to obtain user vectors, which are then mapped to personality labels. However, existing methods face two…
We present a novel end-to-end framework that generates highly compact (typically 6-15 dimensions), discrete (int4 type), and interpretable node representations—termed node identifiers (node IDs)—to tackle inference challenges on large-scale graphs. By employing vector quantization, we compress conti…
The advancements in generative models and the real-world attack of machine-generated text(MGT) create a demand for more robust detection methods. The existing MGT detection methods for adversarial environments primarily consist of manually designed statistical-based methods and fine-tuned classifi…
Radiology Report Generation (RRG) is an important research topic for relieving radiologists’ heavy workload. Existing RRG models mainly rely on supervised fine-tuning (SFT) based on different model architectures using data pairs of radiological images and corresponding radiologist-annotated reports.…
Automatic Radiology Report Generation (RRG) is an important topic for alleviating the substantial workload of radiologists. Existing RRG approaches rely on supervised regression based on different architectures or additional knowledge injection, while the generated report may not align optimally wit…
Object removal has so far been dominated by the mask-and-inpaint paradigm, where the masked region is excluded from the input, leaving models relying on unmasked areas to inpaint the missing region. However, this approach lacks contextual information for the masked area, often resulting in unstable…
The inherent constraint of the "human-in-the-loop" sensing mechanism, imposes mobile crowdsensing with high dynamics and uncertainty, ultimately leading to the issue of incomplete data collection. Current data inference solutions in mobile crowdsensing can be broadly categorized as low-rank models a…
Information diffusion prediction aims to predict the next infected user in the information diffusion, which is a critical task to understand how information spreads on social platforms. Existing methods mainly focus on the sequences or topology structure in euclidean space. However, they fail to suf…
Geo-entity resolution involves linking records that refer to the same entities across different spatial datasets, which underpins location-based services. Given the varying quality of geo-data, this task is known to be challenging, as directly comparing the semantic-centric representations of two en…
Many real-world bandit applications are characterized by sparse rewards, which can significantly hinder learning efficiency. Leveraging problem-specific structures for careful distribution modeling is recognized as essential for improving estimation efficiency in statistics. However, this approach r…
Due to its low storage cost and fast search speed, cross-modal retrieval based on hashing has attracted widespread attention and is widely used in real-world applications of social media search. However, most existing hashing methods are often limited by uncomprehensive feature representations and s…
Graph Transformers (GTs) have recently emerged as popular alternatives to traditional message-passing Graph Neural Networks (GNNs), due to their theoretically superior expressiveness and impressive performance reported on standard node classification benchmarks, often significantly outperforming GNN…
Graph transformers need strong inductive biases to derive meaningful attention scores. Yet, current methods often fall short in capturing longer ranges, hierarchical structures, or community structures, which are common in various graphs such as molecules, social networks, and citation networks. Thi…
Despite advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), their integration into language-grounded, human-like embodied agents remains incomplete, hindering complex real-life task performance in 3D environments. Existing integrations often feature limited open-sourcing…
Recent work on dialogue-based collaborative plan acquisition (CPA) has suggested that Theory of Mind (ToM) modelling can improve missing knowledge prediction in settings with asymmetric skill-sets and knowledge. Although ToM was claimed to be important for effective collaboration, its real impact on…
"We present figures/mixeri con.pdf −−anovelvideodialogmodeloperatingoveragenericmulti− modalstatetrackingscheme.Currentmodelsthatclaimtoperf ormmulti−modalstatetrackingf allshortintwoma (1)T heyeithertrackonlyonemodality(mostlythevisualinput)or(2)theytargetsyntheticdatasetsthatdonotref lec worldin−t…
We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state represent…
In this article, we introduce a lightweight lower limb exoskeleton that provides auxiliary torque to both the ankle and knee joints during the stance phase of gait in a real-world environment, using one quasi-direct-drive (QDD) motor .This lightweight exoskeleton incorporates a novel driving mechani
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the shared information among multiple augmented views of sample…
Explaining the decisions made by Graph Neural Networks (GNNs) is vital for establishing trust and ensuring fairness in critical applications such as medicine and science. The prevalence of hierarchical structure in real-world graphs/networks raises an important question on GNN interpretability: "On…
Link prediction is a fundamental task of graph machine learning, and Graph Neural Network (GNN) based methods have become the mainstream approach due to their good performance. However, the typical practice learns node representations through neighborhood aggregation, lacking awareness of the struct…
Graph Neural Network (GNN) is powerful in graph embedding learning, but its performance has been shown to be heavily degraded under adversarial attacks. Deep graph structure learning (GSL) is proposed to defend attack by jointly learning graph structure and graph embedding, typically in node classif…
Covariate-adjusted response-adaptive randomization (CARA) designs are gaining increasing attention. These designs combine the advantages of randomized experiments with the ability to adaptively revise treatment allocations based on data collected across multiple stages, enhancing estimation efficien…
To fully explore the potential of robots for dexterous manipulation, this paper presents a whole dynamic grasping process to achieve fluent grasping of a target object by the robot end-effector. The process starts from the phase of approaching the object over the phases of colliding with the object…
Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence often only small training datasets. The importanc…
Multi armed bandit (MAB) algorithms have been increasingly used to complement or integrate with A/B tests and randomized clinical trials in e-commerce, healthcare, and policymaking. Recent developments incorporate possible delayed feedback. While existing MAB literature often focuses on maximizing t…
Transformer models have recently gained popularity in graph representation learning as they have the potential to learn complex relationships beyond the ones captured by regular graph neural networks. The main research question is how to inject the structural bias of graphs into the transformer arch…
Unsupervised learning has received more attention due to the superior performance of contrastive learning methods. Most contrastive methods use data augmentation techniques to construct positive and negative pairs. The augmented view of the same sample is regarded as a positive sample, while the res…
Decentralized optimization is an emerging paradigm in distributed learning in which agents achieve network-wide solutions by peer-to-peer communication without the central server. Since communication tends to be slower than computation, when each agent communicates with only a few neighboring agent…
A predictive model for mobility systems capable of understanding the trajectory a user intends to follow in the environment is proposed. Understanding user intention is paramount for any shared-control navigation strategy between a user and an active robotic agent. Equally important however is being…
Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered. Recently, there are some works trying to speed up the skeleton modeling by designing light-weight modules. However, in addition to the…
A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work. The model learns from past observed trajectories and leverages traversability information derived from the visual surroundings to produce a set of future trajectories, suitable…
In skeleton-based action recognition, graph convolutional networks (GCNs) have achieved remarkable success. Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment. In this paper, we re…
Multi-modality fusion technologies have greatly improved the performance of neural network-based Video Description/Caption, Visual Question Answering (VQA) and Audio Visual Scene-aware Dialog (AVSD) over the recent years. Most previous approaches only explore the last layers of multiple layer featur…
The skeleton data have been widely used for the action recognition tasks since they can robustly accommodate dynamic circumstances and complex backgrounds. In existing methods, both the joint and bone information in skeleton data have been proved to be of great help for action recognition tasks. How…
In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance. However, in existing GCN-based methods, the topology of the graph is set manually, and it is fixed over all layers and input…
Acquiring the accurate 3-D position of a target person around a robot provides fundamental and valuable information that is applicable to a wide range of robotic tasks, including home service, navigation and entertainment. This paper presents a real-time robotic 3-D human tracking system which combi…
This work exploits modeling spatial correlation in 2.5D data using Gaussian Processes (GPs), and produces constrained sampling realizations on these models to improve certainty in the predictions by means of integrating additional sparse information. Data organized in 2.5D such as elevation and thic…
Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene understanding, particularly in robotics applications. As scene images