44 accepted papers
Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, even though the visual change is obvious to humans. This raises a fundamental question: do VLMs perceive visual changes or
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…
Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on exte
Precise alignment is a prerequisite for hyperspectral and multispectral image fusion, yet existing methods struggle with complex non-rigid deformations. Existing techniques either suffer from inter-task error accumulation by treating registration and fusion as disjoint processes or neglect the geome…
Reinforcement learning from demonstrations (RLfD) offers a promising method for robotic manipulation with sparse rewards. However, limited demonstrations often cause agents to encounter out-of-distribution states where world models produce poor predictions. In multi-stage tasks, jointly optimizing a…
The emergence of the tool agent paradigm has broadened the capability boundaries of the Large Language Model (LLM), enabling it to complete more complex tasks. However, the effectiveness of this paradigm is limited due to the issue of parameter failure during its execution. To explore this phenomeno
Generative Adversarial Networks (GANs) have been widely applied to image super-resolution (SR) to enhance the perceptual quality. However, most existing GAN-based SR methods typically perform coarse-grained discrimination directly on images and ignore the semantic information of images, making it ch…
Tool-calling has changed Large Language Model (LLM) applications by integrating external tools, significantly enhancing their functionality across diverse tasks. However, this integration also introduces new security vulnerabilities, particularly in the tool scheduling mechanisms of LLM, which have…
Information theft attacks pose a significant risk to Large Language Model (LLM) tool-learning systems. Adversaries can inject malicious commands through compromised tools, manipulating LLMs to send sensitive information to these tools, which leads to potential privacy breaches. However, existing att…
Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly ac
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-…
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…
Tactile perception is essential for embodied agents to understand the physical attributes of objects that cannot be determined through visual inspection alone. While existing methods have made progress in visual and language modalities for physical understanding, they fail to effectively incorporate…
The ability to detect manipulation in multimedia data is vital in digital forensics. Existing Image Manipulation Detection (IMD) methods are mainly based on detecting anomalous features arisen from image editing or double compression artifacts. All existing IMD techniques encounter challenges when i…
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…
Multi-Agent Search and Rescue (MASAR) tasks, challenged by unknown environments and the unpredictable movements of unknown dynamic targets, suffer from inefficiencies in traditional map coverage techniques which require repeated sweeps. Addressing this, our study introduces a novel MASAR framework b
"Image Manipulation Detection (IMD) is becoming increasingly important as tampering technologies advance. However, most state-of-the-art (SoTA) methods require high-quality training datasets featuring image- and pixel-level annotations. The effectiveness of these methods suffers when applied to mani…
Achieving efficient and consistent localization with a prior map remains challenging in robotics. Conventional keyframe-based approaches often suffer from sub-optimal viewpoints due to limited field of view (FOV) and/or constrained motion, thus degrading the localization performance. To address this…
With the development of LLMs, the security threats of LLMs are getting more and more attention. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks primarily utilize scenario camouflage techniques. However their explicitly mention of malici…
Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions.However, these models often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies.The most prominent…
Event cameras characterized by high temporal resolution high dynamic range low power consumption and high pixel bandwidth offer unique capabilities for object detection in specialized contexts. Despite these advantages the inherent sparsity and asynchrony of event data pose challenges to existing ob…
This work proposes a minimal computational model for learning structured memories of multiple object classes in an incremental setting. Our approach is based on establishing a {\em closed-loop transcription} between the classes and a corresponding set of subspaces, known as a linear discriminative…
In retinal surgery clinicians access the internal volume of the eyeball through small scale trocar ports, typically 0.65 mm in diameter, to treat vitreoretinal disorders like idiopathic epiretinal membrane and age-related macular holes. The treatment of these conditions involves the removal of thin
Among various cross-modal retrieval methods, the supervised methods achieve the best performance by exploiting the semantic labels. However, in realistic applications, the data are not always complete with labels and full multi-modal data, which makes these methods hard to be used. In this paper, we…
Existing permutation-invariant methods can be divided into two categories according to the aggregation scope, i.e. global aggregation and local one. Although the global aggregation methods, e. g., PointNet and Deep Sets, get involved in simpler structures, their performance is poorer than the local…
Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be expressed by a linear combination of a few elements from a…
"Poles and building edges are frequently observable objects on urban roads, conveying reliable hints for various computer vision tasks. To repetitively extract them as features and perform association between discrete LiDAR frames for registration, we propose the first learning-based feature segment…
Recently, the community has witnessed numerous datasets built for developing and testing state estimators. However, for some applications such as aerial transportation or search-and-rescue, the contact force or other disturbance must be perceived for robust planning and control, which is beyond the…
Global point cloud registration is an essential module for localization, of which the main difficulty exists in estimating the rotation globally without initial value. With the aid of gravity alignment, the degree of freedom in point cloud registration could be reduced to 4DoF, in which only the hea…
In this work, we propose a novel method for performing inertial aided navigation, by using deep neural net-works (DNNs). To date, most DNN inertial navigation methods focus on the task of inertial odometry, by taking gyroscope and accelerometer readings as input and regressing for integrated IMU pos…
We present a novel method for visual mapping and localization for autonomous vehicles, by extracting, modeling, and optimizing semantic road elements. Specifically, our method integrates cascaded deep models to detect standardized road elements instead of traditional point features, to seek for impr
This paper proposes a novel inertial-aided localization approach by fusing information from multiple inertial measurement units (IMUs) and exteroceptive sensors. IMU is a low-cost motion sensor which provides measurements on angular velocity and gravity compensated linear acceleration of a moving pl
This paper proposes a knowledge distillation method for foreground object search (FoS). Given a background and a rectangle specifying the foreground location and scale, FoS retrieves compatible foregrounds in a certain category for later image composition. Foregrounds within the same category can be…
Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible. Most detectors consider each 3D object as an independent training target, inevitably resulting in a lack of useful informa…
The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values. Then the majority of computation costs focus on the integer mat…
This work studies the sparse adversarial attack, which aims to generate adversarial perturbations onto partial positions of one benign image, such that the perturbed image is incorrectly predicted by one deep neural network (DNN) model. The sparse adversarial attack involves two challenges, i.e., wh…
It is a significant problem to predict the 2D LiDAR map at next moment for robotics navigation and path-planning. To tackle this problem, we resort to the motion flow between adjacent maps, as motion flow is a powerful tool to process and analyze the dynamic data, which is named optical flow in vide…
In recent years, camera-based localization has been widely used for robotic applications, and most proposed algorithms rely on local features extracted from recorded images. For better performance, the features used for open-loop localization are required to be short-term globally static, and the on…
For commercially successful ground robots, high degree of autonomy, low manufacturing and maintenance cost, as well as minimized deployment limitations in different environments are essential attributes. To deliver an `anywhere deployable' product, it is impractical to rely on one single sensor or o…
Generating semantic layout from scene graph is a crucial intermediate task connecting text to image. We present a conceptually simple, flexible and general framework using sequence to sequence (seq-to-seq) learning for this task. The framework, called Seq-SG2SL, derives sequence proxies for the two…
In this paper, we focus on the problem of vision-based localization for ground robotic applications. In recent years, camera only or camera-IMU (inertial measurement unit) based localization methods are widely studied, in terms of theoretical properties, algorithm design, and real-world applications…
In this paper we present a novel direct visual-inertial odometry algorithm, for estimating motion in unknown environments. The algorithm utilizes image patches extracted around image features, and formulates measurement residuals in the image intensity space directly. One key characteristic of the p…
Environmental conditions and external effects, such as shocks, have a significant impact on the calibration parameters of visual-inertial sensor systems. Thus long-term operation of these systems cannot fully rely on factory calibration. Since the observability of certain parameters is highly depend…
In this paper we present a novel approach for the parameterization of the trajectory of a moving platform, which facilitates the development of real-time pose-estimation methods. The key idea of the proposed approach is the decoupling of the parameterization of the trajectory estimate from the param…