56 accepted papers
While 3DGS has emerged as a high-fidelity scene representation, encoding rich, general-purpose features directly from its primitives remains under-explored. We address this gap by introducing Chorus, a multi-teacher pretraining framework that learns a holistic feed-forward 3D Gaussian Splatting (3DG
Large vision-language models (VLMs) for autonomous driving (AD) are evolving beyond perception and cognition tasks toward motion planning. However, we identify two critical challenges in this direction: (1) VLMs tend to learn shortcuts by relying heavily on history input information, achieving seemi
Speculative Decodin promises to accelerate Large Language Model inference, yet its efficacy often degrades in production-grade scenarios. Existing evaluations typically overlook the compute-bound nature of high-concurrency regimes, where verification compute becomes the dominant bottleneck. Conseque…
Federated learning (FL) enables collaborative model training without centralizing raw data, but privacy regulations such as the right to be forgotten require FL systems to remove the influence of previously used training data upon request. Retraining a federated model from scratch is prohibitively e
Embodied AI research is undergoing a shift toward vision-centric perceptual paradigms. While massively parallel simulators have catalyzed breakthroughs in proprioception-based locomotion, their potential remains largely untapped for vision-centric tasks due to the prohibitive computational overhead …
Recent neurophysiological studies have revealed that the early visual cortex can rapidly learn global image context, as evidenced by a sparsification of population responses and a reduction in mean activity when exposed to familiar versus novel image contexts. This phenomenon has been attributed pri
Machine unlearning aims to eliminate the influence of specific data from trained models to ensure privacy compliance. However, most existing methods assume full access to the original training dataset, which is often impractical. We address a more realistic yet challenging setting: few-shot zero-gla
Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on balanced datasets, overlooking the challenges posed by real-world l
In the field of medical image processing, the presence of noise can often result in the obfuscation of crucial details, which in turn can have a detrimental impact on the accuracy of clinical diagnoses. In order to effectively remove noise and improve segmentation performance, this paper proposes a…
The large volume of data from the point cloud brings significant demands on network bandwidth. However, the current transmission framework only considers using lossy compression to control the size of data, while ignoring visually redundant information due to the setting of rendering devices. Based…
Speech recognition in Human-Robot Interaction (HRI) fully relies on audio-based Automatic Speech Recognition. However, speech recognition that relies solely on audio faces significant challenges in noisy environments and may lead to poor performance in such environments. One approach to address this
We present Discoverse, the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper-realistic geometry and appearance of complex real-world scenarios, paving the way for analyzing and bridgin
Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they often fail to dynamically adjust semantic embeddings according…
Event-based structured light (SL) systems have attracted increasing attention for their potential in high-performance 3D measurement. Despite the inherent HDR capability of event cameras, reflective and absorptive surfaces still cause event cluttering and absence, which produce overexposed and under…
With the rapid advancement of deep neural networks (DNNs), model watermarking has emerged as a widely adopted technique for safeguarding model copyrights. A prevalent method involves utilizing a watermark decoder to retrieve watermark bits from generated outputs, but such methods are often vulnerabl…
Existing benchmarks for Vision-Language Model (VLM) in autonomous driving (AD) primarily assess interpretability through open-form visual question answering (QA) within coarse-grained tasks, which remain insufficient to assess capabilities in complex driving scenarios. To this end, we introduce VLAD…
Non-line-of-sight (NLOS) imaging, recovering the hidden volume from indirect reflections, has attracted increasing attention due to its potential applications. Despite promising results, existing NLOS reconstruction approaches are constrained by the reliance on empirical physical priors, e.g., singl…
With the increasing size of Large Vision-Language Models (LVLMs), network pruning techniques aimed at compressing models for deployment in resource-constrained environments have garnered significant attention. However, we observe that pruning often leads to a degradation in safety performance. To ad…
Extremely low-resource languages, especially those written in rare scripts, remain largely unsupported by large language models (LLMs). This is due in part to compounding factors such as the lack of training data. This paper delivers the first comprehensive analysis of whether LLMs can acquire such
In-context learning (ICL) performance is highly sensitive to prompt design, yet the impact of class label options (e.g. lexicon or order) in zero-shot classification remains underexplored. This study proposes LOADS (Label set Optimization via Activation Distribution kurtosiS), a post-hoc method for
Resampling-based video coding is a well-established strategy for compressing high-resolution video under limited bandwidth. Recently, super resolution (SR) technologies has been explored for upsampling the low-resolution reconstructed video in the decoder side. Despite the promising rate-distortion…
Recent advances in skeleton-based action recognition have been primarily driven by Graph Convolutional Networks (GCNs) and skeleton transformers. While conventional approaches focus on modeling joint co-occurrences through skeletal connections, they overlook the inherent positional information in 3D
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…
3D Gaussian Splatting (3DGS) serves as a highly performant and efficient encoding of scene geometry, appearance, and semantics. Moreover, grounding language in 3D scenes has proven to be an effective strategy for 3D scene understanding. Current Language Gaussian Splatting line of work fall into thre…
Recognizing arbitrary or previously unseen categories is essential for comprehensive real-world 3D scene understanding. Currently, all existing methods rely on 2D or textual modalities during training, or together at inference. This highlights a clear absence of a model capable of processing 3D data…
Recent advancements in integrating large language models (LLMs) with application programming interfaces (APIs) have gained significant interest in both academia and industry. Recent work demonstrates that these API-based agents exhibit relatively strong autonomy and planning capabilities. However, t…
Considering a conversation thread, rumour stance classification aims to identify the opinion (e.g. agree or disagree) of replies towards a target (rumour story). Although the target is expected to be an essential component in traditional stance classification, we show that rumour stance classificati…
Transcriptome foundation models (TFMs) hold great promises of deciphering the transcriptomic language that dictate diverse cell functions by self-supervised learning on large-scale single-cell gene expression data, and ultimately unraveling the complex mechanisms of human diseases. However, current…
In the realm of video object segmentation (VOS) the challenge of operating under low-light conditions persists resulting in notably degraded image quality and compromised accuracy when comparing query and memory frames for similarity computation. Event cameras characterized by their high dynamic ran…
The field of novel view synthesis from images has seen rapid advancements with the introduction of Neural Radiance Fields (NeRF) and more recently with 3D Gaussian Splatting. Gaussian Splatting became widely adopted due to its efficiency and ability to render novel views accurately. While Gaussian S…
"Novel view synthesis has achieved remarkable quality and efficiency by the paradigm of 3D Gaussian Splatting (3D-GS), but still faces two challenges: 1) significant performance degradation when trained with only few-shot samples due to a lack of geometry constraint, and 2) incapability of rendering…
Force feedback is of importance in Minimally Invasive Surgery (MIS) as it reduces surgical risks and enhances surgical safety. However, equipping force sensing to the tip of surgical instruments presents challenges due to their diminutive dimensions and often curved shapes. To address this issue, a
Hierarchical leaf vein segmentation is a crucial but under-explored task in agricultural sciences, where analysis of the hierarchical structure of plant leaf venation can contribute to plant breeding. While current segmentation techniques rely on data-driven models, there is no publicly available da…
Dynamic reconstruction in confocal non-line-of-sight imaging encounters great challenges since the dense raster-scanning manner limits the practical frame rate. A fewer pioneer works reconstruct high-resolution volumes from the under-scanning transient measurements but overlook temporal consistency…
Soft robotic structures may play a major role in the 4th industrial revolution. Researchers have successfully demonstrated the advantages of soft robotics over traditional robots made of rigid links and joints in many application areas. Variable stiffness links (VSL) and joints (VSJ) have been inves…
Active confocal non-line-of-sight (NLOS) imaging has successfully enabled seeing around corners relying on high-quality transient measurements. However, acquiring spatial-dense transient measurement is time-consuming, raising the question of how to reconstruct satisfactory results from under-scannin…
The scarcity of labeled far-field speech is a constraint for training superior far-field speaker verification systems. In general, fine-tuning the model pre-trained on large-scale near- field speech through a small amount of far-field speech substantially outperforms training from scratch. However,…
The use of visually-rich documents in various fields has created a demand for Document AI models that can read and comprehend documents like humans, which requires the overcoming of technical, linguistic, and cognitive barriers. Unfortunately, the lack of appropriate datasets has significantly hinde…
In this paper, we address the limitations of the common data annotation and training methods for objective single-label classification tasks. Typically, when annotating such tasks annotators are only asked to provide a single label for each sample and annotator disagreement is discarded when a final…
Time-resolved non-line-of-sight (NLOS) imaging is based on the multi-bounce indirect reflections from the hidden objects for 3D sensing. Reconstruction from NLOS measurements remains challenging especially for complicated scenes. To boost the performance, we present NLOST, the first transformer-base…
We propose a dense neural simultaneous localization and mapping (SLAM) approach for monocular RGBD input which anchors the features of a neural scene representation in a point cloud that is iteratively generated in an input-dependent data-driven manner. We demonstrate that both tracking and mapping…
Swarm robotics plays a non-negligible role in actual practice because of its scalability and robustness. Besides some specific studies, there is still a lack of overall approaches to solving the search and rescue problem in a communication-denied environment. This paper presents a bee-inspired swarm…
Missing data imputation aims to accurately impute the unobserved regions with complete data in real world. Although many recent methods have made remarkable advances, the local homogenous regions especially in boundary and the reasonable of the imputed data are still two most challenging issues. To…
A conversation is a sequence of utterances, where each utterance plays a specific discourse role while expressing a particular emotion. This paper proposes a novel method to exploit latent discourse role information of an utterance to determine the emotion it conveys in a conversation. Specifically,…
To realize dexterous robotic manipulation and enhance the human-machine interaction, nowadays increasing efforts have been made towards multi-dimensional force sensing. However, there are still bottlenecks in integrating these sensors into robots because of the limitation on conformability to comple
Elastic lattice-like materials whose structures can be tuned to achieve desired mechanical properties hold great promise for many applications in robotics. However, existing methods rely on all-fused connections at lattice nodes, which limits the range of mechanical properties that can be achieved.
Recent advances in implicit neural representations show great promise when it comes to generating numerical solutions to partial differential equations. Compared to conventional alternatives, such representations employ parameterized neural networks to define, in a mesh-free manner, signals that are…
Ternary neural networks (TNNs) are potential for network acceleration by reducing the full-precision weights in network to ternary ones, e.g., {-1,0,1}. However, existing TNNs are mostly calculated based on rule-of-thumb quantization methods by simply thresholding operations, which causes a signifi…
We investigate the problem of testing the global null in the high-dimensional regression models when the feature dimension $p$ grows proportionally to the number of observations $n$. Despite a number of prior work studying this problem, whether there exists a test that is model-agnostic, efficient t…
In visual object recognition problems essential to surveillance and navigation problems in a variety of military and civilian use cases, low-resolution and low-quality images present great challenges to this problem. Recent advancements in deep learning based methods like EDSR/VDSR have boosted pixe…
In video coding frameworks, the essence of intra coding is leveraging the spatial correlation within a frame to remove redundancy thus achieving compact transmitting data. With modern video acquisition devices improvement, more high-definition videos emerge into people's lives which has set a new ch…
In this work we consider the one-dimensional (1D) inverse scattering problem of super-resolving the location of discrete point scatters satisfying the 1D Helmholtz equation. This inverse problem has important applications in the detection of shunt faults in electrical transmission lines and leaks in…
This work presents a novel variable stiffness structure consisting of a fiber-constrained dielectric elastomer tube filled with insulating oil. The tensile stiffness of the structure can be adjusted by voltages and its initial value can be customized according to the initial pre-stretch of the mater…
This work presents a novel variable stiffness structure consisting of a fiber-constrained dielectric elastomer tube filled with insulating oil. The tensile stiffness of the structure can be adjusted by voltages and its initial value can be customized according to the initial pre-stretch of the mater
This paper presents an inchworm inspired soft robot composed of the soft body, the front foot as well as the back foot. Compared to the traditional inchworm-type robot consisting of rigid components, the driven mode for the soft robot is more simple. The soft robot inspired by the inchworm has highe…
Reachability is an important dynamic property of Petri nets. Its determination given an unbounded net and initial marking has remained an open problem since 1960s. Due to its extreme difficulty, a great deal of research has been focused on some subclasses of unbounded nets. For arbitrary ones, this…