29 accepted papers
Complex vehicle routing problems (VRPs) remain a fundamental challenge, demanding substantial expert effort for intent interpretation and algorithm design. While large language models (LLMs) offer a promising path toward automation, current approaches still rely on external intervention, which restr…
The growing adoption of compact and cost-effective solid-state LiDARs has greatly advanced robotics. However, their inherently limited Field-of-View (FOV) hinders their application in tasks requiring wide-range depth perception. To overcome this limitation, we introduce the Low Coverage Depth Comple
Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adapt
Neural approaches to the Flexible Job Shop Scheduling Problem (FJSP), particularly those based on deep reinforcement learning (DRL), have gained growing attention in recent years. Yet existing methods often rely on cumbersome state representations (i.e. sometimes requiring more than 20 handcrafted f…
While large language models (LLMs) are increasingly used as automated heuristic designers for vehicle routing problems (VRPs), current state-of-the-art methods predominantly rely on prompting massive, general-purpose models like GPT-4. This work challenges that paradigm by demonstrating that a small…
Foundation Vision-Language Models (VLMs) excel across benchmarks yet remain vulnerable to adversarial attacks. While adversarial fine-tuning improves robustness, attaining a desirable clean–robust performance trade-off typically requires costly hyperparameter searches with multiple retraining runs.…
Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that require specialized processing or up-to-date data. While existing research expands LLMs access to diverse tools (e.g., progr…
Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive RAG enhances this approach by enabling dynamic retrieval during generation, activating retrieval only when the query exce…
Dynamic workflow scheduling (DWS) in cloud computing presents substantial challenges due to heterogeneous machine configurations, unpredictable workflow arrivals/patterns, and constantly evolving environments. However, existing research often assumes homogeneous setups and static conditions, limitin…
Personalized driving refers to an autonomous vehicle’s ability to adapt its driving behavior or control strategies to match individual users’ preferences and driving styles while maintaining safety and comfort standards. However, existing works either fail to capture every individual’s preference pr
The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning an…
Numerous well-established studies have demonstrated the superhuman capabilities of modern Vision-Language Models (VLMs) across a wide range of tasks. However, growing is the doubt about the continuing availability of reliable high-quality labeling (supervision) from human annotators, leading to stag…
This letter focuses on the accuracy of LiDAR-inertial odometry (LIO). We propose a novel high-precision tightly-coupled LIO method, SI-LIO, based on the invariant extended Kalman filter with a single-iteration estimate update. This method utilizes the Lie exponential map between the matrix Lie group
In the pursuit of deeper immersion in human-machine interaction, achieving higher-dimensional tactile input and output on a single interface has become a key research focus. This study introduces the Visual-Electronic Tactile (VET) System, which builds upon vision-based tactile sensors (VBTS) and in
Recent studies in using deep reinforcement learning (DRL) to solve Job-shop scheduling problems (JSSP) focus on construction heuristics. However, their performance is still far from optimality, mainly because the underlying graph representation scheme is unsuitable for modelling partial solutions at…
Deep Neural Networks (DNNs) are vulnerable to adversarial perturbations, raising significant concerns about their security. Numerous methods have been proposed to enhance DNN robustness. However, many methods, including adversarial training and noise injection, improve robustness by incorporating ex…
Existing learning-based methods for solving job shop scheduling problems (JSSP) usually use off-the-shelf GNN models tailored to undirected graphs and neglect the rich and meaningful topological structures of disjunctive graphs (DGs). This paper proposes the topology-aware bidirectional graph attent…
Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and paragraph demarcations. However, the indexing methods of long documents remain under-explored, while existing systems gene…
Image warping a classic task in computer vision aims to use geometric transformations to change the appearance of images. Recent methods learn the resampling kernels for warping through neural networks to estimate missing values in irregular grids which however fail to capture local variations in de…
How to handle an arbitrary number for input images is a fundamental problem of learning-based photometric stereo methods. Existing approaches adopt max-pooling or observation map to fuse an arbitrary number of extracted features. However, these methods discard a large amount of the features from the…
Visual servoing of Unmanned Aerial Vehicles (UAVs) has achieved satisfactory performance in fixed and planar motion targets. Due to highly coupled system dynamics and the sensitivity of the target image to aircraft attitude, the problem for chasing free-flying targets remains challenging. In this pa
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic representations for spoken utterances. Through converting speech s…
The task of phone-to-audio alignment has many applications in speech research. Here we introduce two Wav2Vec2-based models for both text-dependent and text-independent phone-to-audio alignment. The proposed Wav2Vec2-FS, a semi-supervised model, directly learns phone-to-audio alignment through contra…
Speech enhancement is an essential task of improving speech quality in noise scenario. Several state-of-the-art approaches have introduced visual information for speech enhancement, since the visual aspect of speech is essentially unaffected by acoustic environment. This paper proposes a novel frame…
License plate recognition (LPR) is one of the essential components in intelligent transportation systems. Although the image processing algorithms for LPR have been extensively studied in the past several years, the recognition performance is still not satisfactory especially in unconstrained comple…
Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP). However, the design of effective PDRs is a tedious task, requiring a myriad of specialized knowledge and often delivering limited performance. In this paper, we propose to automatically learn PD…
Compliant actuator is widely accepted for physical human-robot interaction due to its safety aspect, dynamic performance improvements and energy saving abilities. In this paper, based on the variable ratio lever mechanism, a new kind of Serial Variable Stiffness Actuator (SVSA) is proposed by using…
Finetuning from a pretrained deep model is found to yield state-of-the-art performance for many vision tasks. This paper investigates many factors that influence the performance in finetuning for object detection. There is a long-tailed distribution of sample numbers for classes in object detectio…
Cross-scene crowd counting is a challenging task where no laborious data annotation is required for counting people in new target surveillance crowd scenes unseen in the training set. The performance of most existing crowd counting methods drops significantly when they are applied to an unseen scene…