203 accepted papers
Multi-modal remote sensing imagery provides complementary observations of the same geographic scene, yet such observations are frequently incomplete in practice. Existing cross-modal translation methods treat each modality pair as an independent task, resulting in quadratic complexity and limited ge…
Diffusion-based planners have shown great promise for autonomous driving due to their ability to capture multi-modal driving behaviors. However, guiding these models effectively in reactive, closed-loop environments remains a significant challenge. Simple conditioning often fails to provide sufficie…
Time series forecasting remains a critical challenge across numerous domains, yet the effectiveness of complex models often varies unpredictably across datasets. Recent studies highlight the surprising competitiveness of simple linear models, suggesting that their robustness and interpretability wa…
Visuo-tactile sensors have been widely adopted in robotic manipulation. However, inherent heterogeneity in sensor designs hinders the learning of unified tactile representations in cross-sensor scenarios. Existing methods that focus on reconstruction or task-specific supervision often fail to captur…
Developing intelligent agents capable of operating a wide range of Graphical User Interfaces (GUIs) with human-level proficiency is a key milestone on the path toward Artificial General Intelligence. While most existing datasets and benchmarks for training and evaluating GUI agents are static and id
Machine learning promises to revolutionize drug discovery, but its "black-box" nature and narrow focus limit adoption by experts. While Large Language Models (LLMs) offer a path forward with their broad knowledge and interactivity, existing methods remain data-intensive and lack transparent reasonin…
近年来，视觉-语言-行动（VLA）模型通过无缝整合视觉感知、语言理解和动作生成，在端到端的学习框架中彻底革新了机器人作。然而，由于这些模型设计为直接与物理世界和人类交互，其安全性至关重要，即使是小漏洞也可能导致灾难性故障。在本研究中，我们提出了通用对抗对象，这是一种表面纹理优化的球体，当置于机器人视野内时，任务成功率会显著降低。具体来说，我们的方法引入了一个多层次攻击框架，能够共同干扰轨迹规划、任务执行和动作控制。我们在模拟和现实机器人环境中验证了我们的方法。实验结果表明，对抗对象在两种代表性VLA模型（Pi0和RDT&#
Most existing time series forecasting models are trained with backpropagation, which often brings high computational cost and limited transparency, so it can be hard to understand why a model makes a given prediction. This paper presents FIPN, a forward self-organizing interpretable polynomial netwo…
Traditional virtual try-on methods primarily focus on the garment-to-person try-on task, which requires flat garment representations. In contrast, this paper introduces a novel approach to the person-to-person try-on task. Unlike the garment-to-person try-on task, the person-to-person task only invo…
Personalized Federated Learning (PFL) has gained significant attention for enabling participating clients to train customized personalized models on non-IID local data. However, current PFL methods mainly suffer from two limitations: 1) Only the personalized part supports heterogeneous design, while
Collaborative fairness in federated learning ensures that clients are rewarded according to their contributions, thereby fostering long-term participation among clients. However, existing methods often under-reward low-contributing clients in the early training stage and neglect critical issues (con
Hybrid Mamba-Transformer models have emerged as promising alternatives to pure Transformers, offering efficiency and competitive performance. However, they struggle to generalize beyond their training context windows, collapsing on long-context tasks. We provide the first systematic analysis of this…
The inherent semantic ambiguity of "many-to-many", where one video matches multiple texts and vice versa, aggravates the difficulty in text-video retrieval. The dominant deterministic embeddings only struggle to capture the mean semantics, while existing probabilistic methods fail to distinguish har
The learning order of semantic classes significantly impacts unsupervised domain adaptation for semantic segmentation, especially under adverse weather conditions. Most existing curricula rely on handcrafted heuristics (e.g., fixed uncertainty metrics) and follow a static schedule, which fails to ad
Robust Multimodal Learning (RML) aims to address the issues of unreliable predictions of multimodal models. Nevertheless, previous RML works often struggle to distinguish between different categories that rely on identical intra-modal cues, making ambiguous predictions. We defined this degree of ``u
Given the central role of charts in scientific, business, and communication contexts, enhancing the chart understanding capabilities of vision-language models (VLMs) has become increasingly critical. A key limitation of existing VLMs lies in their inaccurate visual grounding of infographic elements,…
The heterogeneity between high-level vision-language understanding and low-level action control remains a fundamental challenge in robotic manipulation. Although recent methods have advanced task-specific action alignment, they often struggle to generate robust and accurate actions for novel or sema
Deep learning (DL) models, despite their remarkable success, remain vulnerable to small input perturbations that can cause erroneous outputs, motivating probabilistic robustness (PR) as a complementary notion to adversarial robustness (AR) for stochastic reliability assessment. However, existing PR …
The longitudinal management of blinding fundus diseases constitutes a Partially Observable Markov Decision Process (POMDP) necessitating a critical precision-risk trade-off between intervention and over-treatment, as true pathology is often obscured in static observations. However, existing paradigm…
Remote sensing (RS) image–text retrieval faces significant challenges in real-world datasets due to the presence of Pseudo-Matched Pairs (PMPs), semantically mismatched or weakly aligned image–text pairs, which hinder the learning of reliable cross-modal alignments. To address this issue, we propose
This paper argues that a systemic lack of Agency constrains the implicit reasoning capabilities of current Vision-Language Models (VLMs). Implicit reasoning refers to the ability to autonomously discover and utilize hidden visual evidence to bridge information gaps, rather than merely relying on exp…
Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the training is often prone to instabilities, especially in Mixture-of-Experts (MoE) architectures. Training instability severel…
Mixture-of-Experts (MoE) have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input. However, their deployment remains limited due to the high memory overhead associated with storing all expert parameters, particularly as the number of e…
The quantity and 3-D shape of wear particles are essential indicators for assessing the health of jet engines, enabling early detection of potential damage and preventing accidents caused by catastrophic failures. However, capturing wear particles is difficult due to their minute sizes and ultra hig…
High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in settings where generative models are most needed to compensate for
Self-supervised 3D point cloud understanding is crucial for scene understanding, where Masked Autoencoders (MAE) have achieved excellent performance in point cloud representation learning. However, existing MAE-style methods fail to consider spatial-semantic variations in masking strategies, and joi
Continual Learning (CL) seeks to build an agent that can continuously learn a sequence of tasks, where a key challenge, namely Catastrophic Forgetting, persists due to the potential knowledge interference among different tasks. On the other hand, deep neural networks (DNNs) are shown to converge to…
Neuroscientific evidence reveals that human visual recognition is not an instantaneous event but a hierarchical process, where the brain constructs a holistic perception by progressively integrating simple features like edges or texture into complex scenes. Ensemble learning successfully utilizes th
LLM-based multi-agent simulations are increasingly adopted across application domains, but remain difficult to scale due to GPU memory pressure. Each agent maintains private GPU-resident states, including models, prefix caches, and adapters, which quickly exhaust device memory as the agent count gro…
Most visual models are designed for sRGB images, yet RAW data offers significant advantages for object detection by preserving sensor information before ISP processing. This enables improved detection accuracy and more efficient hardware designs by bypassing the ISP. However, RAW object detection is
Reinforcement learning (RL) has become central to enhancing reasoning in large language models (LLMs). Yet on-policy algorithms such as Group Relative Policy Optimization (GRPO) often suffer in early training: noisy gradients from low-quality rollouts lead to unstable updates and inefficient explora…
Text-guided stylized image generation has yielded promising advances by leveraging the powerful capabilities of text-to-image diffusion models. However, the inherent coupling of style and content information within the reference image presents a significant challenge. To address this, we propose Sty…
Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rely on complex regularization or constraint mechanisms whose necessity remains unclear. In this work, we systematically investigate the mechanisms under…
Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumulate semantic drift and correlation-driven errors. We argue that long-video reasoning should begin not with reactive retr
Federated clustering addresses the critical challenge of extracting patterns from decentralized, unlabeled data. However, it is hampered by the flaw that current approaches are forced to accept a compromise between performance and privacy: transmitting embedding representations risks sensitive data
This work aims to propose a new unsupervised infrared and visible image fusion method based on salient object segmentation, which can obtain a fused image with more information on salient object and realize the salient object segmentation under poor illumination.The new method can be divided into fo
Large Language Models (LLMs) are transforming healthcare through LLM-based agents that can understand and assist with medical tasks. This survey examines the architectures, applications, and challenges of LLM-based agents in medicine. We analyze key components including system profiles, clinical pla…
Analyzing functional connectivity patterns from resting-state functional magnetic resonance imaging (fMRI) requires unraveling its interrelations across spatial, temporal, and frequency domains. To comprehensively analyze four-dimensional (4D) fMRI data, we propose the Spatiotemporal Frequency Graph…
Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based techniques as well, including sparse autoencoders (SAEs), linear…
The effective utilization of data through Deep Neural Networks (DNNs) has profoundly influenced various aspects of society. The growing demand for high-quality, particularly personalized, data has spurred research efforts to prevent data leakage and protect privacy in recent years. Early privacy-pre…
To adapt to the resource-limited environment, this study introduces the lightweight boundary-aware camouflaged object detection(COD) network LMABnet. We enhance the feature representation capability of the lightweight network through a multi-scale feature fusion architecture, while effectively avoid…
Composed Image Retrieval (CIR) is a multi-modal task that seeks to retrieve target images by harmonizing a reference image with a modified instruction. A key challenge in CIR lies in compositional conflicts between the reference image (e.g., blue, long sleeve) and the modified instruction (e.g., gre…
Human cognition is theorized to operate in two modes: fast, intuitive System 1 thinking and slow, deliberate System 2 thinking. While current Large Reasoning Models (LRMs) excel at System 2 thinking, their inability to perform fast thinking leads to high computational overhead and latency. In this w…
Sketch-based person re-identification (re-ID) enables pedestrian retrieval using sketches. While recent methods have improved modality alignment between sketches and RGB images, the challenge of subjective style variation, where sketches exhibit diverse and unpredictable appearances, remains largely…
Language Models (LMs) are increasingly used for type inference, aiding in error detection and software development. Some real-world deployments of LMs require the model to run on local machines to safeguard the intellectual property of the source code. This setting often limits the size of the LMs…
Wikipedia is the largest open knowledge corpus, widely used worldwide and serving as a key resource for training large language models (LLMs) and retrieval-augmented generation (RAG) systems. Ensuring its accuracy is therefore critical. But how accurate is Wikipedia, and how can we improve it?We foc
This paper targets on the regularization effect of momentum-based methods in regression settings and analyzes the popular diagonal linear networks to precisely characterize the implicit bias of continuous versions of heavy-ball (HB) and Nesterov's method of accelerated gradients (NAG). We show that,…
Diffusion models are increasingly employed in visuomotor policies to achieve promising performance of behavior cloning. However, the slow inference caused by iterative denoising is a notorious disadvantage, which greatly limits its application in resource-limited and real-time interactive robot syst
Federated learning (FL) is emerging as a promising technique for collaborative learning without local data leaving their devices. However, clients' data originating from diverse domains may degrade model performance due to domain shifts, preventing the model from learning consistent representation s…
One-shot subset selection serves as an effective tool to reduce deep learning training costs by identifying an informative data subset based on the information extracted by an information extractor (IE). Traditional IEs, typically pre-trained on the target dataset, are inherently dataset-dependent.…
This paper establishes a continuous time approximation, a piece-wise continuous differential equation, for the discrete Heavy-Ball (HB) momentum method with explicit discretization error. Investigating continuous differential equations has been a promising approach for studying the discrete optimiza…
There has been an emergence of deep models for multivariate time series forecasting. Transformer-based models and recent linear forecasters are currently battling for the leading position. However, most of them focus on model architectures, while leaving time series data itself underexplored. We arg…
Camouflaged object detection (COD) is a task of identifying and locating target objects that are camouflaged, masked, or confused. Research claims that depth cues can provide effective object location cues. However, depth images often contain noise interference, which may negatively affect object re…
State space models (SSMs) achieve efficient sub-quadratic compute complexity but often exhibit significant performance drops as context length increases. Recent work attributes this deterioration to an exponential decay in hidden-state memory. While token filtering has emerged as a promising remedy,…
The representation learning of time series has a wide range of downstream tasks and applications in many practical scenarios. However, due to the complexity, spatiotemporality, and continuity of sequential stream data, compared with the representation learning of structural data such as images/video…
Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences. While prior work mainly extends DPO from the aspect of the objective function, we instead improve DPO from the largely overlooked but critical aspect of data selection.…
Non-Intrusive Load Monitoring (NILM) addresses the challenge of disaggregating total energy consumption into individual appliance usage, which is essential for enhancing energy efficiency and managing smart grids. Existing methods often overlook the impact of window sizes on the separation of applia…
Cross-modal retrieval aims to bridge the semantic gap between different modalities, such as visual and textual data, enabling accurate retrieval across them. Despite significant advancements with models like CLIP that align cross-modal representations, a persistent challenge remains: the hubness pro…
Real-life deployment of federated Learning (FL) often faces non-IID data, which leads to poor accuracy and slow convergence. Personalized FL (pFL) tackles these issues by tailoring local models to individual data sources and using weighted aggregation methods for client-specific learning. However, e
Meteorological disasters, especially extreme precipitation, cause significant socioeconomic damage, highlighting the need for effective quantitative precipitation nowcasting. Existing methods, often data-driven and resource-intensive, struggle to capture the underlying physical laws of meteorology.…
Existing video fact-checking datasets often lack detailed evidence and explanations, compromising the reliability and interpretability of fact-checking methods. To address these gaps, we developed a novel dataset featuring comprehensive annotations for each news item, including veracity labels, the…
Pneumatic soft actuators are known for their versatility and reliability; however, their control presents a major challenge as systems scale beyond tens of actuators. Traditional rigid pneumatic valves add bulk, weight, and complexity, while most soft valves fail to generate programmable independent
Previous physical adversarial attacks have shown that carefully crafted perturbations can deceive face recognition systems, revealing critical security vulnerabilities. However, these attacks often struggle to impersonate multiple targets and frequently fail to bypass liveness detection. For example…
Multi-modality pre-training paradigm that aligns protein sequences and biological descriptions has learned general protein representations and achieved promising performance in various downstream applications. However, these works were still unable to replicate the extraordinary success of language-…
Graph neural networks (GNNs) have shown promise in integrating protein-protein interaction (PPI) networks for identifying cancer genes in recent studies. However, due to the insufficient modeling of the biological information in PPI networks, more faithfully depiction of complex protein interaction…
Label noise in hyperspectral image classification (HIC) can severely degrade model performance by leading to incorrect predictions and overfitting, especially as erroneous labels propagate and compound throughout the training process. To address this, we propose a robust learning framework called Se…
Pneumatic actuated soft robots attract increasing interest of the researchers due to the availability and simplicity in actuation. The soft robots driven by soft pneumatic actuators (SPAs) of various active volumes demand pneumatic systems with various range of flow rate. However, the usually bulky
We introduce the concept of a subjective camera to reconstruct meaningful moments that physical cameras fail to capture. We propose Subjective Camera 1.0, a framework for reconstructing real-world scenes from readily accessible subjective readouts, i.e., textual descriptions and progressively drawn…
Recent years have witnessed remarkable advances in Large Language Models (LLMs). However, in the task of social relation recognition, Large Language Models (LLMs) encounter significant challenges due to their reliance on sequential training data, which inherently restricts their capacity to effectiv
Antibodies defend our health by binding to antigens with high specificity and potentiality, primarily relying on the Complementarity-Determining Region (CDR). Yet, current experimental methods of discovering new antibody CDRs are heavily time-consuming. Computational design could alleviate this burd…
Nighttime Semantic Segmentation (NSS) is essential to many cutting-edge vision applications. However, existing technologies overly rely on massive labeled data, whose annotation is time-consuming and laborious. In this paper, we pioneer a new task focusing on exploring the potential of training stra…
Unsupervised visible-infrared person re-identification (US-VI-ReID) seeks to match infrared and visible images of the same individual without the use of annotations. Current methods typically derive cross-modal correspondences through a single global feature matching process for generating pseudo la…
Rapid advances in Large Language Models (LLMs) have spurred demand for processing extended context sequences in contemporary applications. However, this progress faces two challenges: performance degradation due to sequence lengths out-of-distribution, and excessively long inference times caused by
Social Intelligence Queries (Social-IQ) serve as the primary multimodal benchmark for evaluating a model’s social intelligence level. While impressive multiple-choice question (MCQ) accuracy is achieved by current solutions, increasing evidence shows that they are largely, and in some cases entire…
Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtime assumptions. We present Yggdrasil, a co-designed system that enables latency-o…
Text to Motion aims to generate human motions from texts. Existing settings rely on limited Action Texts that include action labels (e.g., "walk, bend"), which limits flexibility and practicability in scenarios difficult to describe directly. This paper extends limited Action Texts to arbitrary ones…
Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying. Conventional approaches with semi-supervised clustering schemes encounter high query costs when applied to large datasets with numerous classes. To address these…
Inverse protein folding is a fundamental task in computational protein design, which aims to design protein sequences that fold into the desired backbone structures. While the development of machine learning algorithms for this task has seen significant success, the prevailing approaches, which pred…
Neural Radiance Fields (NeRF) has recently overhauled novel view synthesis, but it requires extensive computations for training and captures variations in detail with difficulty. In this paper, we propose a novel framework, termed CD-TDRF, to mitigate these dilemmas. CD-TDRF factorizes a density vox…
Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to determine the specific model used, particularly for purposes such as protecting Intellectual Property (IP) in industry and preventing cheating…
Coreset selection seeks to choose a subset of crucial training samples for efficient learning. It has gained traction in deep learning, particularly with the surge in training dataset sizes. Sample selection hinges on two main aspects: a sample's representation in enhancing performance and the role…
In the age of mobile internet, user data, often referred to as memories, is continuously generated on personal devices. Effectively managing and utilizing this data to deliver services to users is a compelling research topic. In this paper, we introduce a novel task of crafting personalized agents p…
In recent years, the rapid increase in online video content has underscored the limitations of static Video Question Answering (VideoQA) models trained on fixed datasets, as they struggle to adapt to new questions or tasks posed by newly available content. In this paper, we explore the novel challen…
With the advent of ensemble-based attacks the transferability of generated adversarial examples is elevated by a noticeable margin despite many methods only employing superficial integration yet ignoring the diversity between ensemble models. However most of them compromise the latent value of the d…
The rise of online shopping and social media has spurred the Video-to-Shop Retrieval (VSR) task, which involves identifying fashion items (e.g., clothing) in videos and matching them with identical products provided by stores. In real-world scenarios, human movement in dynamic video scenes can cause…
Adapting Foundation Models (FMs) for down- stream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs. Existing methods fine- tune FM by allocating sub-FM to clients in FL, however, leading to suboptimal performance due to insufficient tuni…
Soft robotic arms have gained significant attention owing to their flexibility and adaptability. Nonetheless, the instability due to their high-elasticity structure further leads to the difficulty of precise kinematic modeling and control. This letter introduces a novel solution employing foam-embed
Tucker decomposition is a powerful tensor model to handle multi-aspect data. It demonstrates the low-rank property by decomposing the grid-structured data as interactions between a core tensor and a set of object representations (factors). A fundamental assumption of such decomposition is that ther…
Path planning underpins various applications such as transportation, logistics, and robotics. Conventionally, path planning is formulated with explicit optimization objectives such as distance or time. However, real-world data reveals that user intentions are hard-to-model, suggesting a need for dat…
Hydraulic-driven soft robots have received much less attention than their pneumatic counterparts. However, the incompressibility of liquid could bring a series of desirable attributes to soft robotic control, despite the apparent disadvantage of weight addition and compliance compromise resulting fr
We present HumanNeRF-SE a simple yet effective method that synthesizes diverse novel pose images with simple input. Previous HumanNeRF works require a large number of optimizable parameters to fit the human images. Instead we reload these approaches by combining explicit and implicit human represent…
Advanced video frame interpolation (VFI) algorithms approximate intermediate motions between two input frames to synthesize intermediate frame. However they struggle to handle complex scenarios with curvilinear motions since they overlook the latent acceleration information between the input frames.…
Compilers are complex software containing millions of lines of code, taking years to develop. This paper investigates to what extent Large Language Models (LLMs) can replace hand-crafted compilers in translating high-level programming languages to machine instructions, using C to x86 assembly as a c…
Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this project-specific context cannot fit into the prompts of LLMs, we must fin…
Interactions with environmental objects can induce substantial alterations in both exteroceptive and proprioceptive signals. However, the deployment of exteroceptive sensors within underwater soft manipulators encounters numerous challenges and constraints, thereby imposing limitations on their perc
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant memories from an external database. However, existing RAG methods typically organize all memories in a whole database, potentially limiting focus on crucial memories and introducing noise. In this paper…
A significant challenge in multi-view clustering lies in the comprehensive extraction of consistency and complementary information from heterogeneous multi-view data. Numerous methods employ contrastive learning techniques to explore the information between views. However, the basic contrastive lear…
A comprehensive understanding of videos is inseparable from describing the action with its contextual action-object interactions. However, many current video understanding tasks prioritize general action classification and overlook the actors and relationships that shape the nature of the action, re…
In the realm of high-dimensional data analysis, the existence of outliers presents a substantial hurdle to the efficacy of feature selection methods that rely on the assumption of Gaussian distribution. To tackle this issue, we propose an outlier-robust feature selection method, ORFS, which combines…
Time series anomaly detection is a critical task with applications in various domains. Due to annotation challenges, self-supervised methods have become the mainstream approach for time series anomaly detection in recent years. However, current contrastive methods categorize data perturbations int…
Video-based facial analysis is important for autonomous agents to understand human expressions and sentiments. However, limited labeled data is available to learn effective facial representations. This paper proposes a novel self-supervised face-centric pretraining framework, called PrefAce, which l…
Sampling-based planning algorithms such as RRT have been proved to be efficient in solving path planning problems for robotic systems. Various improvements to the RRT algorithm have been presented to improve the performance of the extension and convergence of the random trees, such as Informed RRT*.…
Parameter-efficient finetuning (PEFT) methods seek to adapt large neural models via updates to a small number of *weights*. However, much prior interpretability work has shown that *representations* encode rich semantic information, suggesting that editing representations might be a more powerful al…
Physical adversarial attacks can deceive deep neural networks (DNNs), leading to erroneous predictions in real-world scenarios. To uncover potential security risks, attacking the safety-critical task of person detection has garnered significant attention. However, we observe that existing attack met…
Soft robots undergo complex deformations during actuation and interaction due to the flexibility and compliance of their soft materials. This characteristic presents challenges in proprioception, particularly in characterizing their spatial deformations. Soft optical waveguide sensors have emerged a
Object trajectory prediction is a hot research issue with wide applications in video surveillance and autonomous driving. The previous studies consider the interaction sparsity mainly among the pedestrians instead of multi-type of objects, which brings new types of interactions and consequently supe…
Predicting human pose sequences via existing pose estimators often encounters various estimation errors. Motion refinement methods aim to optimize the predicted human pose sequences from pose estimators while ensuring minimal computational overhead and latency. Prior investigations have primarily co…
The implicit bias of gradient descent has long been considered the primary mechanism explaining the superior generalization of over-parameterized neural networks without overfitting, even when the training error is zero. However, the implicit bias toward adversarial robustness has rarely been consid…
Attention is a fundamental component behind the remarkable achievements of large language models (LLMs). However, our current understanding of the attention mechanism, especially regarding how attention distributions are established, remains limited. Inspired by recent studies that explore the prese…
Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited efficiency due to the sequential processing nature of autoregre…
"Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a critical challenge in current ZOC methods lies in their inability to identify high-quality exemplars effectively. This defic…
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce pyvene, an open-source Python library that supports customizable interventions on a range of different…
Soft robotic manipulators have inherent advantages in underwater applications, as they generate motion by deforming seamless muscles rather than having rotational joints or sliding cylinders, as well as having excellent passive adaptability. However, limited by insufficient structural stiffness, ach
Consistency-based techniques have produced state-of-the-art results in semi-supervised action detection. When the model false detects the dynamic information in the background as an action, spatio-temporal consistency calculations can hardly reflect this false detection result. We consider weakening…
While enlightening progress has been made recently in single-target domain adaptive semantic segmentation (ST-DASS), the multi-peak distributed multi-target domain cannot be directly aligned well with the single-peak distributed source domain. As a result, it is impossible for existing methods to ha…
Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks. However, a significant challenge that arises nowadays is how to maintain performance when we use a lightweight model with limited labeled samples. We present DisCo, a semi-super…
The anonymity of online networks makes tackling fraud increasingly costly. Thanks to the superiority of graph representation learning, graph-based fraud detection has made significant progress in recent years. However, upgrading fraudulent strategies produces more advanced and difficult scams. One c…
Tensor decomposition is an important tool for multiway data analysis. In practice, the data is often sparse yet associated with rich temporal information. Existing methods, however, often under-use the time information and ignore the structural knowledge within the sparsely observed tensor entries.…
While federated learning has shown strong results in opti- mizing a machine learning model without direct access to the original data, its performance may be hindered by in- termittent client availability which slows down the conver- gence and biases the final learned model. There are significant ch…
Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images. However, these methods have limited exploration in another major visibility damage, the glow effects in real night scenes.…
Entangled representation of clothing and identity (ID)-intrinsic clues are potentially concomitant in conventional person Re-IDentification (ReID). Nevertheless, eliminating the negative impact of clothing on ID remains challenging due to the lack of theory and the difficulty of isolating the exact…
Adversarial attacks on thermal infrared imaging expose the risk of related applications. Estimating the security of these systems is essential for safely deploying them in the real world. In many cases, realizing the attacks in the physical space requires elaborate special perturbations. These solut…
Model Agnostic Meta-Learning (MAML) is widely used to find a good initialization for a family of tasks. Despite its success, a critical challenge in MAML is to calculate the gradient w.r.t. the initialization of a long training trajectory for the sampled tasks, because the computation graph can rapi…
Image-text retrieval is a fundamental task to bridge vision and language by exploiting various strategies to fine-grained alignment between regions and words. This is still tough mainly because of one-to-many correspondence, where a set of matches from another modality can be accessed by a random qu…
Soft robots have long been attractive to robotic engineers due to their remarkable dexterity; however, reports that standardize soft actuators into modularized off-shelf devices akin to rigid robots are still rare, and the mechanical efficiency of existing designs is still limited. This work identif…
Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness. Anomalies are rare and hard to collect and supervised models easily over-fit to these seen anomalies with a handful of abnormal samples, producing unsatisfactory performance. On the o…
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance when applied to a multi-class training setting, due to the co-e…
Although Magnetic Resonance Imaging (MRI) is very helpful for brain tumor segmentation and discovery, it often lacks some modalities in clinical practice. As a result, degradation of prediction performance is inevitable. According to current implementations, different modalities are considered to be…
Spatial-temporal graph learning has emerged as the state-of-the-art solution for modeling structured spatial-temporal data in learning region representations for various urban sensing tasks (e.g., crime forecasting, traffic flow prediction). However, most existing models are vulnerable to the qualit…
Existing space-time video super-resolution (ST-VSR) methods fail to achieve high-quality reconstruction since they fail to fully explore the spatial-temporal correlations, long-range components in particular. Although the recurrent structure for ST-VSR adopts bidirectional propagation to aggregate i…
Practical tensor data is often along with time information. Most existing temporal decomposition approaches estimate a set of fixed factors for the objects in each tensor mode, and hence cannot capture the temporal evolution of the objects' representation. More important, we lack an effective approa…
At data mining field, it is a fundamental problem to dispose of high-dimensional data. Many existing unsupervised methods select features by manifold learning or exploring spectral analysis, thus preserving the intrinsic structure of raw data. But most of them follow an assumption that all features…
Physical modeling is critical for many modern science and engineering applications. From a data science or machine learning perspective, where more domain-agnostic, data-driven models are pervasive, physical knowledge {—} often expressed as differential equations {—} is valuable in that it is comple…
Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle to represent and classify the tail classes. Although the pr…
Although considerable progress has been made in semantic scene understanding under clear weather, it is still a tough problem under adverse weather conditions, such as dense fog, due to the uncertainty caused by imperfect observations. Besides, difficulties in collecting and labeling foggy images hi…
"Underwater imaging with red-NIR light illumination can avoid phototropic aggregation-induced observational deviation of marine plankton abundance under white light illumination, but this will lead to the loss of critical color information in the collected grayscale images, which is non-preferable t…
"Stereo depth estimation is of great interest for computer vision research. However, existing methods struggles to generalize and predict reliably in hazardous regions, such as large uniform regions. To overcome these limitations, we propose Context Enhanced Path (CEP). CEP improves the generalizati…
Rain streaks and background components in a rainy input are highly correlated, making the deraining task a composition of the rain streak removal and background restoration. However, the correlation of these two components is barely considered, leading to unsatisfied deraining results. To this end,…
"Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects. Building on a well-known auto-encoding framework to cope with object symmetry and the lack of labeled training data, we achieve scalability by disentangling the latent…
With the ever-increasing elderly population, elder walking assistance is in strong demand. Instead of receiving assistance from a human carer, a smart walker can bring an elder user a more convenient and autonomous walking experience. Towards intelligent and safe walking assistance, we propose a clo…
Many applications, such as in physical simulation and engineering design, demand we estimate functions with high-dimensional outputs. To reduce the expensive cost of generating training examples, we usually choose several fidelities to enable a cost/quality trade-off. In this paper, we consider the…
Low-light image enhancement aims to improve an image's visibility while keeping its visual naturalness. Different from existing methods, which tend to accomplish the relighting task directly, we investigate the intrinsic degradation and relight the low-light image while refining the details and colo…
This paper describes an energy-based learning method that predicts the activities of multiple agents simultaneously. It aims to forecast both upcoming actions and paths of all agents in a scene based on their past activities, which can be jointly formulated by a probabilistic model over time. Learni…
Timeline summarization (TLS) identifies major events and generates short summaries on how the event evolves in a period of time. Existing timeline summarization methods generate summaries by considering the coverage and diversity of the content and temporized information but ignore the importance an…
Contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data. This technique requires a balanced mixture of two ingredients: positive (similar) and negative (dissimilar) samples. This is typically achieved by maintaining a queue of negative samples during tra…
Multi-fidelity modeling and learning is important in physical simulation related applications. It can leverage both low-fidelity and high-fidelity examples for training so as to reduce the cost of data generation yet still achieving good performance. While existing approaches only model finite, disc…
Soft robots, with advantages of high adaptability to the environment, relatively easy and simple fabrication process as well as promising performances, have been thoroughly investigated and widely applied lately, the superiority of which has been proved in areas such as medicine, industry, daily lif
Proprioception and variable stiffness are two trending topics in soft robotics research. The former could endow soft robots with the ability to perceive the environment as well as their internal states without the need of dedicated sensors, while the latter could strengthen the otherwise excessive c…
High-order interaction events are common in real-world applications. Learning embeddings that encode the complex relationships of the participants from these events is of great importance in knowledge mining and predictive tasks. Despite the success of existing approaches, e.g. Poisson tensor factor…
Tensor decomposition is a fundamental framework to analyze data that can be represented by multi-dimensional arrays. In practice, tensor data are often accompanied with temporal information, namely the time points when the entry values were generated. This information implies abundant, complex tempo…
We propose a nonparametric factorization approach for sparsely observed tensors. The sparsity does not mean zero-valued entries are massive or dominated. Rather, it implies the observed entries are very few, and even fewer with the growth of the tensor; this is ubiquitous in practice. Compared with…
Deep kernel learning is a promising combination of deep neural networks and nonparametric function estimation. However, as a data driven approach, the performance of deep kernel learning can still be restricted by scarce or insufficient data, especially in extrapolation tasks. To address these limit…
Scene understanding in adverse weather conditions (e.g. rainy and foggy days) has drawn increasing attention, arising some specific benchmarks and algorithms. However, scene segmentation under rainy weather is still challenging and under-explored due to the following limitations on the datasets and…
Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution (HR) and higher frame rate (HFR). Quite intuitively, pioneering two-stage based methods complete ST-VSR directly combining two sub-tasks: Spatial Video Super-Resolution (S-VSR) and Temporal…
Recognition of soft objects is a critical step to tailor policy for dexterous manipulation. Deformation property is one of the valuable tactile cues for inferring the identities of soft objects, especially those having similar appearance features. In this work, we implemented tactual grasping for di
Action recognition is a hot topic in computer vision due to its wide range of applications in urban surveillance. Although some methods are more advanced from an invariant view perspective, those approaches do not perform well for the viewpoint change. To address this issue, one possible solution is…
The soft robotic manipulators attract extensive interest of researchers due to its conformity to the unstructured environment, safe-interaction with human and fragile objects. The movement of the soft manipulator often include elongation, contraction, 2-DOF rotations due to the parallelly arranged f
We propose a deep visuo-tactile model for real-time estimation of the liquid inside a deformable container in a proprioceptive way. We fuse two sensory modalities, i.e., the raw visual inputs from the RGB camera and the tactile cues from our specific tactile sensor without any extra sensor calibrati…
Estimated time of arrival (ETA) is one of the most important services in intelligent transportation systems (ITS) and becomes a challenging spatial-temporal (ST) data mining task in recent years. Nowadays, deep learning based methods, specifically recurrent neural networks (RNN) based ones are adapt…
Dimension reduction is an effective technology to embed data with high dimension to lower dimension space, where Linear Discriminant Analysis (LDA), one of representative methods, only works with Gaussian distribution data. However, in order to solve non-Gaussian issue that only one cluster cannot w…
Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -- conflicting gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential confl…
Existing inpainting methods have achieved promising performance in recovering defected images of specific scenes. However, filling holes involving multiple semantic categories remains challenging due to the obscure semantic boundaries and the mixture of different semantic textures. In this paper, we…
Recent advances in person re-identification (re-ID) have led to impressive retrieval accuracy. However, existing re-ID models are challenged by the adversarial examples crafted by adding quasi-imperceptible perturbations. Moreover, re-ID systems face the domain shift issue that training and testing…
Location prediction is of great importance in location-based applications for the construction of the smart city. To our knowledge, existing models for location prediction focus on the users' preference on POIs from the perspective of the human side. However, modeling users' interests from the histo…
Although the existing Named Entity Recognition (NER) models have achieved promising performance, they suffer from certain drawbacks. The sequence labeling-based NER models do not perform well in recognizing long entities as they focus only on word-level information, while the segment-based NER model…
The key task of physical simulation is to solve partial differential equations (PDEs) on discretized domains, which is known to be costly. In particular, high-fidelity solutions are much more expensive than low-fidelity ones. To reduce the cost, we consider novel Gaussian process (GP) models that le…
Many applications involve multi-type event data. Understanding the complex influences of the events on each other is critical to discover useful knowledge and to predict future events and their types. Existing methods either ignore or partially account for these influences. Recent works use recurren…
Despite the success of existing tensor factorization methods, most of them conduct a multilinear decomposition, and rarely exploit powerful modeling frameworks, like deep neural networks, to capture a variety of complicated interactions in data. More important, for highly expressive, deep factorizat…
This paper presents a new high-quality dataset for Very Important Person Localization (VIPLoc), named Unconstrained-7k. Generally, current datasets: 1) are limited in scale; 2) built under simple and constrained conditions, where the number of disturbing non-VIPs is not large, the scene is relativel…
Proprioception is the ability to perceive environmental stimulations through internal sensory organs. Enabling proprioception is critical for robots to be aware of the environmental interactions and respond appropriately, particularly for high-payload grippers to ensure safety when handling delicate
Soft-robotic manipulators, with their closed-chamber elastomeric actuators, natural water-sealing and inherent compliance, are ideal for underwater applications for compact, lightweight, and dexterous manipulation tasks. However, their low structure rigidity makes soft robots highly prone to underwa
In this letter, we propose a novel coding architecture for LiDAR point cloud sequences based on clustering and prediction neural networks. LiDAR point clouds are structured, which provides an opportunity to convert the 3D data to a 2D array, represented as range images. Thus, we cast the LiDAR point
Soft robot is known for great safety in human-centered environments due to its inherent compliance. However, the compliance resulting from the soft continuum structure and viscoelastic material also induces challenges for sensing and control of soft robots. In this letter, we propose a proprioceptiv
There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment. We propose a new algorithm, Best-Action Imitation Learning (BAIL), which strives for bot…
An efficient and effective person re-identification (ReID) system relieves the users from painful and boring video watching and accelerates the process of video analysis. Recently, with the explosive demands of practical applications, a lot of research efforts have been dedicated to heterogeneous pe…
Cable-driven robotic manipulators are desirable for medical applications, for their form factor flexibility after separating actuation from the distal end. However, intended to work under high spatial constraints such as dental or other surgical applications, severe cable elongations will raise cont
In this paper, we first propose a novel Structured Sparse Subspace Learning S^3L module to address the long-standing subspace sparsity issue. Elicited by proposed module, we design a new discriminative feature selection method, named Subspace Sparsity Discriminant Feature Selection S^2DFS which enab…
Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge. Since the missing hole in a mixed scene of a corrupted image often contains various semantic information, conventional two-stage approaches utilizing structural information of…
We present a novel approach to category-level 6D object pose and size estimation. To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category. In particular, CASS is modeled as the latent space…
Interaction events among multiple entities are ubiquitous in real-world applications. Although these interactions can be naturally represented by tensors and analyzed by tensor decomposition, most existing approaches are limited to multilinear decomposition forms, and cannot estimate complex, nonlin…
Tensor factorization is a fundamental framework to analyze high-order interactions in data. Despite the success of the existing methods, the valuable temporal information are severely underused. The timestamps of the interactions are either ignored or discretized into crude steps. The recent work al…
Despite the success of the recent nonlinear tensor decomposition models based on Gaussian processes (GPs), they lack an effective way to deal with streaming data, which are important for many applications. Using the standard streaming variational Bayes framework or the recent streaming sparse GP app…
Cross-modal matching has been a highlighted research topic in both vision and language areas. Learning appropriate mining strategy to sample and weight informative pairs is crucial for the cross-modal matching performance. However, most existing metric learning methods are developed for unimodal mat…
Pedestrian detection at nighttime is a crucial and frontier problem in surveillance, but has not been well explored by the computer vision and artificial intelligence communities. Most of existing methods detect pedestrians under favorable lighting conditions (e.g. daytime) and achieve promising per…
A wide range of commonly performed dental procedures, from operative caries removal, crown preparation, filling, to Orthodontia, could potentially benefit from robotic assistance or enhancement. Despite the wide applicability, dental robots have received far less research attention in comparison wit
For an inventory system of a single type perishable product where the demand is dependent in the sale price plus a random variable, and the decay rate is dependent in freshness-keeping effort plus a random variable, due to their quality deterioration the amount of available products that can be used
Expectation propagation (EP) is a powerful approximate inference algorithm. However, a critical barrier in applying EP is that the moment matching in message updates can be intractable. Handcrafting approximations is usually tricky, and lacks generalizability. Importance sampling is very expensive.…
Person re-identification aims to associate images captured by non-overlapping cameras. It is a challenging task because images are often in different conditions such as background clutter, illumination variation, viewpoint changes and different camera settings. Viewpoint changes and pose variations…
Soft robotic arms are receiving more and more attention for their intrinsic safety and natural compliance. Instead of traditional serialized rotary joints, soft robotic arms often have complex joints with coupled degrees of freedom like bending, rotation, and elongation, enabling them with more free
A deep understanding of the movement mechanism of the human fingers is essential for achieving a human-like actuation mechanism for anthropomorphic robotic hands. After carefully analyzing a set of anatomical theories of human fingers, we propose a novel and more reasonable actuation mechanism of th
Infrared-Visible person RE-IDentification (IV-REID) is a rising task. Compared to conventional person re-identification (re-ID), IV-REID concerns the additional modality discrepancy originated from the different imaging processes of spectrum cameras, in addition to the person's appearance discrepanc…
The design of feedback controllers for bipedal robots is challenging due to the hybrid nature of its dynamics and the complexity imposed by high-dimensional bipedal models. In this paper, we present a novel approach for the design of feedback controllers using Reinforcement Learning (RL) and Hybrid…
This letter presents a novel soft robotic glove system for assistive and rehabilitative applications, offering a powerful, low-profile, and convenient solution for the growing elderly and patient population. The low-profile soft glove worn by the user weighs below 50 g, providing cable-driven flexio
This letter presents a dexterous soft robotic hand, BCL-13, with 4 fingers and 13 independently actuated joints capable of in-hand manipulation. The iconic dexterity is enabled by a novel soft robotic finger design with three degrees of freedom (DOFs), significantly improving over existing soft actu
Ostraciiform body/caudal fish locomotion requires high-frequency oscillation of the caudal fin, yielding negligible body oscillations. It is the most ideal form of biomimetic locomotion for underwater robots where body-stabilization is required for photography or manipulation applications. This lett
Face sketch synthesis plays an important role in both digital entertainment and law enforcement. It can bridge the great texture discrepancy between face photos and sketches. Most of the current face sketch synthesis approaches directly learn the relationship between the photos and sketches, and it…
Impact safety and response are critical challenges for robots working under dynamic environments and with close proximity to humans. State-of-the-art rigid robots and soft robots both have limitations and tradeoffs due to their characteristics. In this letter, we introduced a hybrid-antagonistic-pne
This study proposes a simple yet surprisingly effective feature matching approach, termed as guided locality preserving matching (GLPM), for visual homing of panoramic images. The key idea of our approach is merely to preserve the neighborhood structures of potential true matches between two panoram…
This letter presents a biomimetic underwater soft robot design with novel propulsion and maneuvering mechanisms. The robot design took inspirations from cephalopod molluscs. The proposed robot comprises a soft mantle structure with multiple built-in soft actuators, which could deform to provide stee