88 accepted papers
Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing methods primarily focus on static objects, while understanding dynamic point cloud sequences remains largely unexplored. This…
As larger language models deliver stronger capabilities, their autoregressive inference becomes increasingly expensive. *Speculative decoding* accelerates generation by letting a fast draft propose tokens that the target model verifies in parallel. Yet under sampling ($T>0$), observed speedups consi…
Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fi
Object-Goal Navigation (OGN) in complex domestic environments remains challenging due to spatial memory and semantic uncertainties. To address this, we introduce EMKG, an embodied multimodal memory knowledge graph framework that enables open-world navigation. In contrast to conventional vision-langu
Most prior deepfake detection methods lack explainable outputs. With the growing interest in multimodal large language models (MLLMs), researchers have started exploring their use in interpretable deepfake detection. However, a major obstacle in applying MLLMs to this task is the scarcity of high-qu…
Vision-Language-Action (VLA) models have recently emerged, demonstrating strong generalization in robotic scene understanding and manipulation. However, when confronted with long-horizon tasks that require defined goal states, such as LEGO assembly or object rearrangement, existing VLA models still
Permanent magnet (PM) actuated micro robotics offers significant advantages for minimally invasive medicine, but faces three critical challenges: nonlinear magnetic force relationships, directional control asymmetry between horizontal and vertical motion, and imaging–capturing frequency mismatch. Th
Partially View-aligned Clustering (PVC) addresses the challenge of partial view alignment in multi-view learning by leveraging complementary and consistent information. While existing PVC methods show promise, most rely on distance-based strategies that are sensitive to view-specific details and noi
Data scarcity continues to be a critical bottleneck in the field of robotic manipulation, limiting the ability to train robust and generalizable models. While diffusion models provide a promising approach to synthesizing realistic robotic manipulation videos, their effectiveness hinges on the availa
While recent advancements in robotic manipulation video synthesis have shown promise, significant challenges persist in ensuring effective instruction-following and achieving high visual quality. Recent methods, like RoboDreamer, utilize linguistic decomposition to divide instructions into separate…
Object-Goal Navigation in dynamic environments remains challenging because many existing approaches rely primarily on reactive mapping and lack the ability to retain historical experience or establish structured memory associations. To address this limitation, we introduce MemClaw-RAG, an embodied m…
Pansharpening under thin cloudy conditions is a practically significant yet rarely addressed task, challenged by simultaneous spatial resolution degradation and cloud-induced spectral distortions. Existing methods often address cloud removal and pansharpening sequentially, leading to cumulative erro
Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token prediction leads to significantly slows inference. Recent studies have introduced Jacobi-style decoding to accelerate autoregressive image generatio
The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D reconstruction methods have achieved high-fidelity rendering of temporal interpolation, but typically lack physical consist
Scaling up visual autoregressive models improves generation quality but incurs substantial inference costs. Mixture-of-Experts (MoE) architectures mitigate this issue through sparse activation and have proven effective in large language models. However, training MoE models from scratch remains prohi…
Existing diffusion-based object removal and inpainting methods often fail to recover the fine structural and textural details of small objects. This is primarily due to the VAE encoder’s downsampling, which inevitably compresses small masked regions and causes significant detail loss, while the deco…
Hyperspectral image change detection (HSI-CD) suffers from severe annotation scarcity and complex change patterns, which fundamentally limit the effectiveness of directly fine-tuning pre-trained foundation models. Although semi-supervised learning provides a promising direction, existing approaches …
Multi-output Gaussian processes (MOGPs) provide a Bayesian framework for modeling non-linear functions with multiple outputs, in which nonstationary kernels are essential for capturing input-dependent variations in observations. However, from a spectral (dual) perspective, existing nonstationary ker…
Recently, video-language models (VidLMs) have gained widespread attention and adoption. However, existing works primarily focus on terrestrial scenarios, overlooking the highly demanding application needs of underwater observation. To overcome this gap, we introduce UVLM, an under water observation
Maintaining role-awareness in Role-Playing Conversational Agents (RPCAs) is a significant challenging, largely because the creative nature of role-playing makes it difficult to design verifiable reward signals for reinforcement learning (RL). To address this, we propose VeriRole, a new framework des…
Large Language Models (LLMs) have demonstrated significant advancements in various fields, notably in Role-Playing Conversational Agents (RPCAs). However, when confronted with role-specific professional inquiries, LLMs-based RPCAs tend to underperform due to their excessive emphasis on the conversat
Ship detection using remote sensing imagery is a crucial research area with both military and civilian applications. However, it remains challenging due to limitations in current ship datasets, such as insufficient volume, incomplete annotations, and inaccuracies. Additionally, ships often exhibit a…
In recent years, methods based on heterogeneous graph neural networks (HGNNs) have been widely used for embedding heterogeneous graphs (HGs) due to their ability to effectively encode the rich information from HGs into low-dimensional node embeddings. Existing HGNNs focus on neighbor aggregation and…
Deep-learning-based face recognition (FR) systems are susceptible to adversarial examples in both digital and physical domains. Physical attacks present a greater threat to deployed systems as adversaries can easily access the input channel, allowing them to provide malicious inputs to impersonate a…
Pre-trained language models enhanced parsers have achieved outstanding performance in rich-resource languages. Cross-lingual dependency parsing aims to learn useful knowledge from high-resource languages to alleviate data scarcity in low-resource languages. However, effectively reducing the syntacti…
Logs record essential information about system operations and serve as a critical source for anomaly detection, which has generated growing research interest. Utilizing large language models (LLMs) within a retrieval-augmented generation (RAG) framework for log-based anomaly detection is an effectiv…
Financial disclosures such as 10-K filings pose challenging retrieval problems because of their length, regulatory section hierarchy, and domain-specific language, which standard retrieval-augmented generation (RAG) models underuse. We present Financial Mapping-Guided Enhanced Answer Retrieval, a re
Visual AutoRegressive (VAR) modeling employs a next-scale decoding paradigm that progresses from coarse structures to fine details. While enhancing fidelity and scalability, this approach challenges two fundamental assumptions of conventional dynamic inference: semantic stability (intermediate outpu…
Fourier Neural Operators (FNO) have emerged as promising solutions for efficiently solving partial differential equations (PDEs) by learning infinite-dimensional function mappings through frequency domain transformations. However, the sparsity of high-frequency signals limits computational efficienc
Miniature underwater robots play a crucial role in the exploration and development of marine resources, particularly in confined spaces and high-pressure deep-sea environments. This study presents the design, optimization, and performance of a miniature robotic fish, powered by the oscillation of bi
Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of…
Traditional unsupervised clustering methods, which often rely on contrastive training of embedders, suffer from a lack of label knowledge, resulting in suboptimal performance. Furthermore, the presence of potential false negatives can destabilize the training process. Hence, we propose to improve cl
Visual prompting has gained popularity as a method for adapting pre-trained models to specific tasks, particularly in the realm of parameter-efficient tuning. However, existing visual prompting techniques often pad the prompt parameters around the image, limiting the interaction between the visual p…
As deepfake and adversarial attacks evolve, facial recognition systems are encountering increasingly diverse threats. Most existing face liveness detection algorithms focus on single tasks, like spoofing or deepfake attack detection. The corresponding datasets have limited coverage of attack methods…
Large language models (LLMs) demonstrate remarkable text generation and syntax parsing capabilities in high-resource languages. However, their performance notably declines in low-resource languages due to memory forgetting stemming from semantic interference across languages. To address this issue,
The multi-view Gaussian process latent variable model (MV-GPLVM) aims to learn a unified representation from multi-view data but is hindered by challenges such as limited kernel expressiveness and low computational efficiency. To overcome these issues, we first introduce a new duality between the sp…
Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge bases are commonly built by extracting structured data from…
Foundation models have revolutionized language modeling, while whether this success is replicated in scientific computing remains unexplored. We present OmniArch, the first prototype aiming at solving multi-scale and multi-physics scientific computing problems with physical alignment. We addressed a…
The advances in vision-language models (VLMs) have led to a growing interest in autonomous driving to leverage their strong reasoning capabilities. However, extending these capabilities from 2D to full 3D understanding is crucial for real-world applications. To address this challenge, we propose Omn…
Whilst Convolutional Neural Network (CNN)-based object tracking methods can achieve promising results on traditional well-lit datasets, it is challenging to accurately locate targets in low-light images taken in nighttime scenes, even for state-of-the-art (SOTA) trackers. Existing solutions often di…
As Large-scale Language Models (LLMs) advance, the development of engaging Role-Playing Conversational Agents (RPCAs) has gained prominence. Despite this progress, there is a notable absence of benchmarks designed around dialogues, rather than question-answering formats, to assess the effectiveness…
Link prediction in knowledge graphs (KGs) requires integrating structural information and semantic context to infer missing entities. While large language models (LLMs) offer strong generative reasoning capabilities, their limited exploitation of structural signals often results in *structural spars
We investigate safe online convex optimization (SOCO), where each decision must satisfy a set of unknown linear constraints. Assuming that the unknown constraints can be observed with a sub-Gaussian noise for each chosen decision, previous studies have established a high-probability regret bound of…
As Industrial Internet of Things (IIoT) software systems become increasingly complex, precise failure diagnosis has become both essential and challenging. Current log-based failure diagnosis methods lack scalability for different failure types. In IIoT software systems, the number of failure types i…
Spiking neural networks (SNNs) have shown their competence in handling spatial-temporal event-based data with low energy consumption. Similar to conventional artificial neural networks (ANNs), SNNs are also vulnerable to gradient-based adversarial attacks, wherein gradients are calculated by spatial…
Constructing accurate digital twins of articulated objects is essential for robotic simulation training and embodied AI world model building, yet historically requires painstaking manual modeling or multi-stage pipelines. In this work, we propose \textbf{URDF-Anything}, an end-to-end automatic recon…
SLAM is the key technique for localization and surrounding perception in indoor environments. However, the dynamic posture adjustments of wheel-legged robots cast new challenges that affect the accuracy of localization. Therefore, this letter presents the Wheel-Legged SLAM, a novel indoor SLAM metho
Stable diffusion, a generative model used in text-to-image synthesis, frequently encounters resolution-induced composition problems when generating images of varying sizes. This issue primarily stems from the model being trained on pairs of single-scale images and their corresponding text descriptio…
Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources. As a powerful compression technology, binarization can extremely reduce model weights to a mere 1 bit, lowering the expensive…
In real-world situations, federated learning often needs to process non-IID (non-independent and identically distributed) data with multiple skews, causing inadequate model performance. Existing federated learning methods mainly focus on addressing the problem with a single skew of non-IID, and henc…
Rapid sampling from the environment to acquire available frontier points and timely incorporating them into subsequent planning to reduce fragmented regions are critical to improve the efficiency of autonomous exploration. We propose HPHS, a fast and effective method for the autonomous exploration o…
Dysphagia is a prevalent symptom in numerous neurological disorders among older adults. Current dysphagia diagnostic systems either involve invasive procedures or necessitate the ingestion of liquids. Some researchers have devised automatic dysphagia detection methods based on vowels that are easy t…
Gaussian process latent variable models (GPLVMs) are a versatile family of unsupervised learning models commonly used for dimensionality reduction. However, common challenges in modeling data with GPLVMs include inadequate kernel flexibility and improper selection of the projection noise, leading to…
With the strong representational capabilities of pre-trained language models, dependency parsing in resource-rich languages has seen significant advancements. However, the parsing accuracy drops sharply when the model is transferred to low-resource language due to distribution shifts. To alleviate t…
Artifact-free super-resolution (SR) aims to translate low-resolution images into their high-resolution counterparts with a strict integrity of the original content eliminating any distortions or synthetic details. While traditional diffusion-based SR techniques have demonstrated remarkable abilities…
In this work, we develop a pipeline for historical-psychological text analysis in classical Chinese. Humans have produced texts in various languages for thousands of years; however, most of the computational literature is focused on contemporary languages and corpora. The emerging field of historica…
As a cross-modal task, visual storytelling aims to generate a story for an ordered image sequence automatically. Different from the image captioning task, visual storytelling requires not only modeling the relationships between objects in the image but also mining the connections between adjacent im…
The Gaussian process state-space model (GPSSM) has attracted extensive attention for modeling complex nonlinear dynamical systems. However, the existing GPSSM employs separate Gaussian processes (GPs) for each latent state dimension, leading to escalating computational complexity and parameter proli…
Interactive reinforcement learning has shown promise in learning complex robotic tasks. However, the process can be human-intensive due to the requirement of a large amount of interactive feedback. This paper presents a new method that uses scores provided by humans instead of pairwise preferences t…
In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The model is performed in an online manner and the long-term hist…
Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors. Inspired by recent advancements in deep generative mode…
Variational autoencoders (VAE) are one of the most prominent deep generative models for learning the underlying statistical distribution of high-dimensional data. However, training VAEs suffers from a severe issue called posterior collapse; that is, the learned posterior distribution collapses to th…
Deep convolutional neural networks have delivered remarkable aptitude in performing Synthetic Aperture Radar (SAR) image speckle removal tasks. Such approaches are nevertheless constrained in balancing speckle removal and preservation of spatial information, particularly with respect to strong speck…
This paper proposes a Semi-Attention Partition (SAP) method to learn well-aligned part features for occluded person re-identification (re-ID). Currently, the mainstream methods employ either external semantic partition or attention-based partition, and the latter manner is usually better than the fo…
With the rapid development of various satellite sensor techniques, remote sensing imagery has been an important source of data in change detection applications. This paper aims to propose an unsupervised change detection method based on Object-based Markov Random Filed (OMRF) and Inception UNet (IUN…
This paper probes intrinsic factors behind typical failure cases (e.g spatial inconsistency and boundary confusion) produced by the existing state-of-the-art method in face parsing. To tackle these problems, we propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation (DML-CSR) for…
Knowledge-enhanced methods have bridged the gap between human beings and machines in generating dialogue responses. However, most previous works solely seek knowledge from a single source, and thus they often fail to obtain available knowledge because of the insufficient coverage of a single knowled…
In knowledge-grounded dialogue generation, pre-trained language models (PLMs) can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding. Unlike adopting the plain text knowledge, it is thorny to leverage the structural commonse…
Supervised parsing models have achieved impressive results on in-domain texts. However, their performances drop drastically on out-of-domain texts due to the data distribution shift. The shared-private model has shown its promising advantages for alleviating this problem via feature separation, wher…
While achieving remarkable success in remote sensing (RS) scene classification for the past few years, convolutional neural network (CNN) based methods suffer from the demand for large amounts of training data. The bottleneck in prediction accuracy has shifted from data processing limits toward a la…
Thanks to the strong representation learning capability of deep learning, especially pre-training techniques with language model loss, dependency parsing has achieved great performance boost in the in-domain scenario with abundant labeled training data for target domains. However, the parsing commun…
In this paper, we introduce Cirrus, a new long-range bi-pattern LiDAR public dataset for autonomous driving tasks such as 3D object detection, critical to highway driving and timely decision making. Our platform is equipped with a high-resolution video camera and a pair of LiDAR sensors with a 250-m…
Multispectral (MS) pan-sharpening aims at producing a high spatial resolution (HR) MS image by fusing a single-band HR panchromatic (PAN) image and a corresponding MS image with low spatial resolution. In this paper, we propose a heterogeneous two-stream network (HTSNet) with hierarchical feature pr…
Due to limited knowledge carried by queries, traditional dialogue systems often face the dilemma of generating boring responses, leading to poor user experience. To alleviate this issue, this paper proposes a novel infobox knowledge-aware dialogue generation approach, HITA-Graph, with three unique f…
Despite achieving remarkable performance, previous knowledge-enhanced works usually only use a single-source homogeneous knowledge base of limited knowledge coverage. Thus, they often degenerate into traditional methods because not all dialogues can be linked with knowledge entries. This paper propo…
Nowadays, web data is often used to train a dialogue system. However, noises in web data can disturb the training process, as well as can impact the performance. Consequently, dialogue models tend to be brittle when receiving noisy inputs during the inference. This paper proposes a novel framework,…
In this paper, we investigate the adversarial robustness of principal component analysis (PCA) algorithms. In the considered setup, there is a powerful adversary who can add a carefully designed data point to the original data matrix. The goal of the adversary is to maximize the distance between the…
There is a fundamental trade-off between the channel representation resolution of codebooks and the overheads of feedback communications in the fifth generation new radio (5G NR) frequency division duplex (FDD) massive multiple-input and multiple-output (MIMO) systems. In particular, two types of co…
The availability of enormous event data with timestamps has aroused the study of Dynamic Knowledge Graphs (KGs). In dynamic KGs, temporal link prediction is an important task, which predicts future interactions between entities. Compared with conventional statistic link prediction tasks, temporal li…
Recently, neural architecture search (NAS) methods have attracted much attention and outperformed manually designed architectures on a few high-level vision tasks. In this paper, we propose HiNAS (Hierarchical NAS), an effort towards employing NAS to automatically design effective neural network arc…
In recent years, parsing performance is dramatically improved on in-domain texts thanks to the rapid progress of deep neural network models. The major challenge for current parsing research is to improve parsing performance on out-of-domain texts that are very different from the in-domain training d…
Insufficient semantic understanding of dialogue always leads to the appearance of generic responses, in generative dialogue systems. Recently, high-quality knowledge bases have been introduced to enhance dialogue understanding, as well as to reduce the prevalence of boring responses. Although such k…
Person re-identification is one of the key issues in both machine learning and video monitor application. In particular, defining an appropriate distance metric between the person images is very important. Existing metric learning approaches used in person re-identification either learn a single mea…
Accuracy of depth estimation from static images has been significantly improved recently, by exploiting hierarchical features from deep convolutional neural networks (CNNs). Compared with static images, vast information exists among video frames and can be exploited to improve the depth estimation p…
The problem of testing whether an incomplete tensor lies in a given tensor subspace, called tensor matched subspace detection, is significant when it is unavoidable to have missing entries. Compared with the matrix case, the tensor matched subspace detection problem is much more challenging due to t…
This paper introduces a novel approach of classifying voices that elicit a soothing effect on listeners from a domain knowledge inspired application of feature engineering. In particular, we utilize the characteristics of voiced vs, unvoiced speech in order to build a more accurate feature set. Larg…
Following a person is a fundamental requirement for human-robot interaction. In this paper we propose a novel tracking approach for robust human feet tracking which integrates human locomotion into tracking algorithms. The vertical displacement between the two feet is analyzed and we observe that th…