52 accepted papers
Dual-arm robots are widely used to cooperatively manipulate large, heavy objects that exceed single-arm payload limits. However, conventional dual-arm planners typically assume that the object is already positioned within the reachable and graspable workspace of both end-effectors. When the object l
Computer-Aided Design (CAD) models are widely used across industrial design, simulation, and manufacturing processes. Text-to-CAD systems aim to generate editable, general-purpose CAD models from textual descriptions, significantly reducing the complexity and entry barrier associated with traditiona…
Clustered-object environments challenge robotic grasp planning and implementation mainly for two reasons: (i) the limited inter-object clearance leaves insufficient space for conventional gripper fingers to approach and wrap the target object without collisions, and (ii) perception-induced position
Incomplete Multi-View Clustering (IMVC) is fundamentally challenged by structural degradation induced by missing views, rather than the absence of feature values. Existing graph-based approaches either rely on costly data imputation or adopt first-order linear fusion, which acts as a weak low-pass f…
With the growing demand for decentralized collaborative analysis of privacy-sensitive data, federated multi-view clustering (FMVC) has attracted widespread attention due to its ability to balance privacy protection and collaborative modeling. However, current methods still face the following challen
Ensemble clustering aims to derive a consensus partition from multiple base clustering results. Anchor-based methods construct compact similarity representations via anchors, substantially improving computational efficiency. However, when outliers contaminate the data, reconstructing the base cluste
Similarity-graph-based multi-view clustering is effective in capturing non-Gaussian cluster structures, yet it suffers from an inherent conflict between scalability and geometry-consistent cluster assignment. In particular, cluster labels are typically inferred via secondary clustering rather than b
While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces remains a critical challenge. In this work, we propose a geometric perspective: Reasoning on the Manifold. We hypothesiz…
Image clustering aims to partition unlabeled image datasets into distinct groups. A core aspect of this task is constructing and leveraging prior knowledge to guide the clustering process. Recent approaches introduce semantic descriptions as prior information, most of which typically relying on matc
In multi-view classification tasks (MVC), each view provides an unique perspective on the data, offering complementary information that can improve classification performance when properly integrated. However, traditional methods typically adopt a uniform processing strategy for all views before fus
The success of Vision-Language Models (VLMs) often relies on high-resolution schemes that preserve image details, while these approaches also generate an excess of visual tokens, leading to a substantial decrease in model efficiency. A typical VLM includes a visual encoder, a text encoder, and an LL…
The nonlinearity and uncertainty of dynamics pose significant challenges to ensuring the tracking performance of joint trajectories, especially time-varying effects on the load and temperature. In this letter, we present an adaptive neural computed torque control scheme to improve the tracking accur
Deep learning-based speech enhancement (SE) methods predominantly draw upon two architectural frameworks: generative adversarial networks and diffusion models. In the realm of SE, capturing the local and global relations between signal frames is crucial for the success of these methods. These framew
Multi-view Clustering (MVC) has gained significant attention for its ability to utilize consistent and complementary information from multiple views. Graph filter-based MVC methods have recently demonstrated promising performance, attracting growing interest. However, existing graph filter-based met…
Ensemble clustering learns a consensus result by integrating a set of base clustering results. Recently, anchor-based methods construct an anchor similarity matrix to represent the affinity relationships among samples, significantly improving computational efficiency. However, these methods struggle
Evolutionary multi-view classification (EMVC) methods have gained wide recognition due to their adaptive mechanisms. Fitness evaluation (FE), which aims to calculate the classification performance of each individual in the population and provide reliable performance ranking for subsequent operations…
Automatic Modulation Classification (AMC) serves as a foundational pillar for cognitive radio systems, enabling critical functionalities including dynamic spectrum allocation, non-cooperative signal surveillance, and adaptive waveform optimization. However, practical deployment of AMC faces a fundam…
Despite the recent efforts from the NLP community, balancing the training budget, downstream performance, and general capabilities of large language models (LLM) remains a challenge in many applications. Training the entire model for downstream tasks is expensive, and could easily result in catastro…
Multi-view clustering (MVC) aims to integrate complementary information from multiple views to enhance clustering performance. Late Fusion Multi-View Clustering (LFMVC) has shown promise by synthesizing diverse clustering results into a unified consensus. However, current LFMVC methods struggle with…
Multi-view classification (MVC) based on the Dempster-Shafer theory has gained significant recognition for its reliability in safety-critical applications. However, existing methods predominantly focus on providing confidence levels for decision outcomes without explaining the reasoning behind these…
Unsupervised multi-view outlier detection has garnered increasing attention in recent years, yet existing methods face persistent challenges. Many approaches rely predominantly on first-order neighborhood information, overlooking the richer insights offered by higher-order structures, which can degr…
In multi-view classification tasks, integrating information from multiple views effectively is crucial for improving model performance. However, most existing methods fail to fully leverage the complex relationships between views, often treating them independently or using static fusion strategies.
Medical image segmentation is an important task in medical artificial intelligence. Traditional segmentation methods often suffer from the information loss problem, especially in medical image data which contain many different-scale organs or tissues. To address this problem, we propose a novel medi
Clustering ensemble has been a popular research topic in data science due to its ability to improve the robustness of the single clustering method. Many clustering ensemble methods have been proposed, most of which can be categorized into clustering-view and sample-view methods. The clustering-view…
The ever-increasing token limits of large language models (LLMs) have enabled long context as input. Many LLMs are trained and fine-tuned to perform zero/few-shot inference using instruction-based prompts. Prompts typically include a detailed task instruction, several examples, and a single data poi…
Kernel k-means has been widely studied in machine learning. However, existing kernel k-means methods often ignore the \textit{fairness} issue, which may cause discrimination. To address this issue, in this paper, we propose a novel Fair Kernel K-Means (FKKM) framework. In this framework, we first pr…
In the field of machine learning, multi-view clustering aims to reveal hidden clustering patterns across different data perspectives. However, traditional methods often struggle due to their reliance on low-order similarity data. To overcome this, we propose a new approach that integrates the learni…
Clustering, a key unsupervised learning method, is widely used in various fields. While the classic K-means algorithm is popular, it often neglects valuable high-order information in data. To address this, we have proposed an improved K-means algorithm incorporating a Chebyshev polynomial approximat…
In this letter, we present an innovative, tightly-coupled LiDAR-Visual-Inertial Odometry and Mapping framework, termed LVIO-Fusion, which achives robust and precise state estimation and map construction in environments characterized by LiDAR-degenerated and texture-less. The LVIO-Fusion is comprised
Large language models (LLMs) such as GPT-4 have exhibited remarkable performance in a variety of tasks, but this strong performance often comes with the high expense of using paid API services. In this paper, we are motivated to study building an LLM "cascade" to save the cost of using LLMs, particu…
Click-through rate (CTR) prediction is a critical task in recommendation systems, serving as the ultimate filtering step to sort items for a user. Most recent cutting-edge methods primarily focus on investigating complex implicit and explicit feature interactions; however, these methods neglect the…
Large Language Models (LLMs) have limited performance when solving arithmetic reasoning tasks and often provide incorrect answers. Unlike natural language understanding, math problems typically have a single correct answer, making the task of generating accurate solutions more challenging for LLMs.…
This paper mathematically conceives a novel walking support device that leverages passive dynamics and coupling effects. In this model, a passive human walker is flexibly connected to an active humanoid, where the coupling effect induces a stable walking gait of the human. To understand the key mech…
Compliance is good. However, it is challenging for one compliant continuum robot to finish both high precision manipulation and environmental-adapted motions. In this paper, a modular continuum robot with the alterable compliance characteristic is proposed. Besides, an actuation module is also propo…
Regular maintenance of pipelines is an important task to ensure oil transportation and other operation (sewers, nature gas). Precise localization of pipeline damage can greatly improve the efficiency of maintenance work. Since the texture similarity and illumination change of pipe, traditional local…
Although considerable progress has been achieved regarding the transformers in recent years, the large number of parameters, quadratic computational complexity, and memory cost conditioned on long sequences make the transformers hard to train and implement, especially in edge computing configuration…
The performance of a robot is closely related to its structure. From the initial design of link lengths to structural optimization, it is still the research hotspot in recent years. To make the manipulator lightweight and ensure its working range and flexibility, researchers have proposed many optim…
Molecular representation learning plays an essential role in cheminformatics. Recently, language model-based approaches have gained popularity as an alternative to traditional expert-designed features to encode molecules. However, these approaches only utilize a single molecular language for represe…
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a great challenge due to its ill-posed property, which is a critical lack of depth information in the 2D image plane. While ex
The objective of this paper is to learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection. We make following contributions: (i) rather than appealing to the complicated pseudo-LiDAR based approach, we propose a depth-conditioned dynamic message pro…
Particular tasks performed in narrow and confined spaces require a capability of passing through a limited pathway. Consequently, previous research developed a snake-like robot that generates a 1-D rectilinear gait with an appropriate mechanical design. In contrast, a rigorous mathematical model and
Biological observations on tetrapods locomotion deduce that anti-phase synchronization (APS) between fore and rear parts is beneficial for achieving a high-speed walking. On the other hand, theoretical analysis and experimental studies on quadruped robots suggest that a flexible spine potentially im…
Low-cost monocular 3D object detection plays a fundamental role in autonomous driving, whereas its accuracy is still far from satisfactory. Our objective is to dig into the 3D object detection task and reformulate it as the sub-tasks of object localization and appearance perception, which benefits t…
Clustering ensemble generates a consensus clustering result by integrating multiple weak base clustering results. Although it often provides more robust results compared with single clustering methods, it still suffers from the robustness problem if it does not treat the unreliability of base result…
We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptiv…
Creative design of grippers on their configurations, mechatronics control system, and multi-component collaborative algorithms is often utilized to realize complex operations in industrial applications, due to the environmental constraints or specific task requirements. Firstly, this paper introduce…
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to sensors, appearance of a same object varies a lot in point…
Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches. In this paper, we propose a novel domain adaptation based monocular 3D object detection framework named DA-3Ddet, which adapts the featur…
Consensus clustering provides a framework to ensemble multiple clustering results to obtain a consensus and robust result. Most existing consensus clustering methods usually apply all data to ensemble learning, whereas ignoring the side effects caused by some difficult or unreliable instances. To t…
Despite the great success achieved by supervised fully convolutional models in semantic segmentation, training the models requires a large amount of labor-intensive work to generate pixel-level annotations. Recent works exploit synthetic data to train the model for semantic segmentation, but the dom…
Semantic segmentation of 3D unstructured point clouds remains an open research problem. Recent works predict semantic labels of 3D points by virtue of neural networks but take limited context knowledge into consideration. In this paper, a novel end-to-end approach for unstructured point cloud semant…
In this paper we present a novel framework for cross-age face verification (FV) by seeking help from its ``competitor" named cross-face age verification (AV), i.e., deciding whether two face photos are taken at similar ages. While FV and AV share some common features, FV pursues age insensitivity an…