54 accepted papers
Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring any target-category training data. Existing approaches render 3D point clouds into 2D images and leverage pre-trained Vision-Language Models (VLMs) for
Adversarial examples pose serious threats to deep neural networks (DNNs), revealing fundamental vulnerabilities in model robustness. However, most existing adversarial attacks directly manipulate densely activated and highly redundant feature representations, which often leads to overfitting on surr…
Accurate state estimation for flexible robotic systems poses significant challenges, particularly for platforms with dynamically deforming structures that invalidate rigid-body assumptions. This paper addresses this problem and enables the extension of existing rigid-body pose estimation methods to …
Large language models (LLMs) with Process Reward Models (PRMs) have shown strong reasoning ability, yet their potential in Operations Research (OR) remains unexplored. We present the first PRM tailored for OR, but find that directly training on mainstream datasets yields surprisingly weak performanc…
The prevailing approach to distilling reasoning from Large Language Models (LLMs)—behavioral cloning from textual rationales—is fundamentally limited. It teaches Small Language Models (SLMs) to mimic surface-level patterns rather than the underlying algorithmic structure of thought, resulting in a c…
Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer.Despite demonstrating strong overall image generation ability, they still underperform on text rendering with blur strokes and disrupt letter shapes. In this work, we trace this lim
Multimodal pretraining has revolutionized visual understanding, but its impact on video-based person re-identification (ReID) remains underexplored. Existing approaches often rely on video-text pairs, yet suffer from two fundamental limitations: (1) lack of genuine multimodal pretraining, and (2) te
Text-conditioned image generation has made rapid progress, yet rendering images with long-form text remains challenging due to the limitations of existing datasets, which predominantly focus on short and simple text. We introduce TextAtlas5M, a large-scale dataset designed to evaluate long-text rend…
Supernumerary robotic limbs (SRLs) are extra robotic appendages that require sensory-motor integration for intuitive control, yet most lack proprioceptive feedback. Existing approaches using vibrotactile or electrotactile cues often feel unnatural and offer limited resolution. We present a real-time
Robotic wrists play a crucial role in enhancing the dexterity and stability of robotic end-effectors. Existing rigid robotic wrists tend to be complex and lack flexibility, while soft robotic wrists often struggle with limited load-bearing capacity and lower accuracy. Human wrists feature multi-degr…
Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output,…
Large language models (LLMs) often produce reasoning steps that are superficially coherent yet internally inconsistent, leading to unreliable outputs. Since such failures typically arise from implicit or poorly-grounded knowledge, we introduce \emph{Grounded Reasoning in Dependency (GRiD)}, a novel…
Anomaly detection suffers from data imbalance, as anomalies are typically rare. Due to the smaller number of anomaly samples, models may overfit the features of the normal samples, resulting in poor performance when detecting anomalies. Historically, this issue has typically been addressed by unders…
Zero-shot multi-intent detection is capable of capturing multiple intents within a single utterance without any training data, which gains increasing attention. Building on the success of large language models (LLM), dominant approaches in the literature explore prompting techniques to enable zero-s…
Current Large Language Models (LLMs) are predominantly designed with English as the primary language, and even the few that are multilingual tend to exhibit strong English-centric biases. Much like speakers who might produce awkward expressions when learning a second language, LLMs often generate un…
In order to address the shortcomings of limited point cloud feature description capability, insufficient real-time performance, and severe feature homogenization in the field of 3D LiDAR SLAM. In this letter, a novel feature extraction and matching method TLG is proposed. First, the method makes ful
Fusing multimodal brain imaging has been a hot topic since different modalities of brain imaging can provide complementary information. However, due to the size of simultaneous recorded fMRI-EEG dataset being limited and the substantial discrepancy between hemodynamic responses of fMRI and neural os…
Multilingual knowledge graphs (KGs) provide high-quality relational and textual information for various NLP applications, but they are often incomplete, especially in non-English languages. Previous research has shown that combining information from KGs in different languages aids either Knowledge G…
Code debugging is a crucial task in software engineering, which attracts increasing attention. While remarkable success has been made in the era of large language models (LLMs), current research still focuses on the simple no-library or single-library setting, ignoring the complex multi-library scen…
Text-to-Image Person Retrieval (TIPR) aims to utilize natural language descriptions as queries to retrieve pedestrian images. However, existing methods only concentrated on aligning individual text-image pairs and ignored the specific self-representations within both visible images and textual descr…
Foundation models (FMs) have shown great promise in single-cell genomics, yet current approaches, such as scGPT, Geneformer, and scFoundation, rely on centralized training and language modeling objectives that overlook the tabular nature of single-cell data and raise significant privacy concerns. We…
Robotic wrists play a crucial role in enhancing the dexterity and stability of robotic end-effectors. Existing rigid robotic wrists tend to be complex and lack flexibility, while soft robotic wrists often struggle with limited load-bearing capacity and lower accuracy. Human wrists feature multi-degr
Knowledge Graphs represent real-world entities and the relationships between them. Multilingual Knowledge Graph Construction (mKGC) refers to the task of automatically constructing or predicting missing entities and links for knowledge graphs in a multilingual setting. In this work, we reformulate t…
Cross-lingual chain-of-thought can effectively complete reasoning tasks across languages, which gains increasing attention.Recently, dominant approaches in the literature improve cross-lingual alignment capabilities by integrating reasoning knowledge from different languages. Despite achieving excel…
Translating entity names, especially when a literal translation is not correct, poses a significant challenge. Although Machine Translation (MT) systems have achieved impressive results, they still struggle to translate cultural nuances and language-specific context. In this work, we show that the i…
In recent years, the computer vision community has increasingly focused on detecting and recognizing human-object interactions (HOIs), which are crucial for tasks such as action recognition and scene understanding. However, the imbalanced distribution of interaction categories presents challenges, e…
Zero-shot text classification aims to handle the text classification task without any annotated training data, which can greatly alleviate the data scarcity problem. Current dominant approaches follow a novel text-image matching paradigm, reformulating zero-shot text classification into a text-image…
Training models with longer in-context lengths is a significant challenge for multimodal machine learning due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rather, it introduces an innovative method designed to increase in-context…
Recently there has been a growing interest in category-level object pose and size estimation, and prevailing methods commonly rely on single view RGB-D images. However, one disadvantage of such methods is that they require accurate depth maps which cannot be produced by consumer-grade sensors. Furth…
Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages. These variations may also be caused by transcreation, an adaptation process that entails more than transliteration and word-for-word translation. In this paper,…
Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-ex…
Anthropomorphic robotic hands are seeking to achieve key features such as multi-degree-of-freedom motion ability, bi-directional actuation, high adaptability, and sufficient stiffness. In this research, we propose a 10 active degrees-of-freedom anthropomorphic robotic hand with a soft-rigid hybrid s
Anchor-based detectors have been continuously developed for object detection. However, the individual anchor box makes it difficult to predict the boundary's offset accurately. Instead of taking each bounding box as a closed individual, we consider using multiple boxes together to get prediction box…
End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity. The advancement of deep neural networks, especially the successful use of large pre-trained models, has further led to significant progres…
Since the introduction of distantly supervised relation extraction methods, numerous approaches have been developed, the most representative of which is multi-instance learning (MIL). To find reliable features that are most representative of multi-instance bags, aggregation strategies such as AVG (a…
Recent work in Natural Language Processing and Computer Vision has been using textual information – e.g., entity names and descriptions – available in knowledge graphs to ground neural models to high-quality structured data. However, when it comes to non-English languages, the quantity and quality o…
The CTC model has been widely applied to many application scenarios because of its simple structure, excellent performance, and fast inference speed. There are many peaks in the probability distribution predicted by the CTC models, and each peak represents a non-blank token. The recognition latency…
Watermarking schemes in plaintext domain usually suffer from high exposure risk of the cover signal. Data hiding in encrypted image (DHEI) can guarantee the security of the cover signal by embedding secret information into encrypted signal. Based on the above, we propose a robust watermarking scheme…
Transformers achieve excellent performance in a variety of domains since they can capture long-distance dependencies through the self-attention mechanism. However, self-attention is computationally costly due to its quadratic complexity and high memory consumption. In this paper, we propose a novel…
This paper presents Uncertainty-aware Contrastive Learning (UCoL): a fully unsupervised framework for discriminative facial representation learning. Our UCoL is built upon a momentum contrastive network, referred to as Dual-path Momentum Network. Specifically, two flows of pairwise contrastive train…
To assist robots in teleoperation tasks, haptic rendering which allows human operators access a virtual touch feeling has been developed in recent years. Most previous haptic rendering methods strongly rely on data collected by tactile sensors. However, tactile data is not widely available for robot…
A fundamental challenge in deep metric learning is the generalization capability of the feature embedding network model since the embedding network learned on training classes need to be evaluated on new test classes. To address this challenge, in this paper, we introduce a new method called coded…
Most stroke patients suffer from a combination of motor and sensory dysfunction and central facial paralysis. Specific rehabilitation training is required to restore those functions. Current research focuses on developing stimulating and straightforward rehabilitation training processes so that pati
Robotic hand exoskeletons can assist people who suffer from hand.functional disabilities caused by a stroke. However, currently existing hand exoskeletons remain inadequate in terms of user-friendly design, lightweight structure, and accurate modeling of hand motion. In this study, a large displacem
This paper introduces a generative system for in-battle real-time commentary in mobile MOBA games. Event commentary is important for battles in MOBA games, which is applicable to a wide range of scenarios like live streaming, e-sports commentary and combat information analysis. The system takes real…
Time series signal analysis plays an essential role in many applications, e.g., activity recognition and healthcare monitoring. Recently, features extracted with deep neural networks (DNNs) have shown to be more effective than conventional hand-crafted ones. However, most existing solutions rely sol…
Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns ar…
Labanotation is an important notation system widely used for recording dances. Numerous methods have been proposed for automatic Labanotation generation from motion capture data. Recently, the sequence-to-sequence (seq2seq) model is proposed. However, the encoder of the model only encodes the tempor…
Robotic hand exoskeletons can provide assistance to people who suffer from hand functional disability or spinal cord injury (SCI). However, the current hand exoskeletons remain challenging with respect to having a user-friendly design that satisfies human motion with a lightweight structure. Here we…
Deep learning (DL) systems are notoriously difficult to test and debug due to the lack of correctness proof and the huge test input space to cover. Given the ubiquitous unlabeled test data and high labeling cost, in this paper, we propose a novel test prioritization technique, namely TestRank, which…
Labanotation is an important notation system for recording dances. Automatically generating Labanotation scores from motion capture data has attracted more interest in recent years. Current methods usually focus on individual movement segments and generate Labanotation symbols one by one. This requi…
In this paper, we propose a preprocessing strategy for refining the pedestrian images in person re-identification(re-id). The accomplishment of the person re-id task depends on the features extracted from pedestrian appearances. The best image matches are verified based on these features as identifi…
This paper presents an energy-efficient digital signal processor (DSP) for rectangular-to-polar conversion in 802.11ad polar transmitter working on 60 GHz band. Firstly, system simulations with a complete transmission chain are conducted with regard to error vector magnitude and output spectrum, whi…
The alternating direction method of multipliers (ADMM) is an important tool for solving complex optimization problems, but it involves minimization sub-steps that are often difficult to solve efficiently. The Primal-Dual Hybrid Gradient (PDHG) method is a powerful alternative that often has simple…