VSSD: Vision Mamba with Non-Causal State Space DualityYuheng Shi, Minjing Dong, Mingjia Li et al.
Vision transformers have significantly advanced the field of computer vision, offering robust modeling capabilities and global receptive field. However, their high computational demands limit their applicability in processing long sequences. To tackle this issue, State Space Models (SSMs) have gained prominence in vision tasks as they offer linear computational complexity. Recently, State Space Duality (SSD), an improved variant of SSMs, was introduced in Mamba2 to enhance model performance and efficiency. However, the inherent causal nature of SSD/SSMs restricts their applications in non-causal vision tasks. To address this limitation, we introduce Visual State Space Duality (VSSD) model, which has a non-causal format of SSD. Specifically, we propose to discard the magnitude of interactions between the hidden state and tokens while preserving their relative weights, which relieves the dependencies of token contribution on previous tokens. Together with the involvement of multi-scan strategies, we show that the scanning results can be integrated to achieve non-causality, which not only improves the performance of SSD in vision tasks but also enhances its efficiency. We conduct extensive experiments on various benchmarks including image classification, detection, and segmentation, where VSSD surpasses existing state-of-the-art SSM-based models. Code and weights are available at \url{https://github.com/YuHengsss/VSSD}.
GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid EnvironmentsKechen Li, Yaotian Tao, Ximing Wen et al.
Recent advancements in Large Language Models (LLMs) have demonstrated their potential in planning and reasoning tasks, offering a flexible alternative to classical pathfinding algorithms. However, most existing studies focus on LLMs' independent reasoning capabilities and overlook the potential synergy between LLMs and traditional algorithms. To fill this gap, we propose a comprehensive evaluation benchmark GridRoute to assess how LLMs can take advantage of traditional algorithms. We also propose a novel hybrid prompting technique called Algorithm of Thought (AoT), which introduces traditional algorithms' guidance into prompting. Our benchmark evaluates six LLMs ranging from 7B to 72B parameters across various map sizes, assessing their performance in correctness, optimality, and efficiency in grid environments with varying sizes. Our results show that AoT significantly boosts performance across all model sizes, particularly in larger or more complex environments, suggesting a promising approach to addressing path planning challenges. Our code is open-sourced at https://github.com/LinChance/GridRoute.
10.4SEJun 24, 2021
Runtime Permission Issues in Android Apps: Taxonomy, Practices, and Ways ForwardYing Wang, Yibo Wang, Sinan Wang et al.
Android introduces a new permission model that allows apps to request permissions at runtime rather than at the installation time since 6.0 (Marshmallow, API level 23). While this runtime permission model provides users with greater flexibility in controlling an app's access to sensitive data and system features, it brings new challenges to app development. First, as users may grant or revoke permissions at any time while they are using an app, developers need to ensure that the app properly checks and requests required permissions before invoking any permission-protected APIs. Second, Android's permission mechanism keeps evolving and getting customized by device manufacturers. Developers are expected to comprehensively test their apps on different Android versions and device models to make sure permissions are properly requested in all situations. Unfortunately, these requirements are often impractical for developers. In practice, many Android apps suffer from various runtime permission issues (ARP issues). While existing studies have explored ARP issues, the understanding of such issues is still preliminary. To better characterize ARP issues, we performed an empirical study using 135 Stack Overflow posts that discuss ARP issues and 199 real ARP issues archived in popular open-source Android projects on GitHub. Via analyzing the data, we observed 11 types of ARP issues that commonly occur in Android apps. Furthermore, we conducted a field survey and in-depth interviews among practitioners, to gain insights from industrial practices and learn practitioners' requirements of tools that can help combat ARP issues. We hope that our findings can shed light on future research and provide useful guidance to practitioners.
19.4CLMay 29, 2025
Revisiting Uncertainty Estimation and Calibration of Large Language ModelsLinwei Tao, Yi-Fan Yeh, Minjing Dong et al.
As large language models (LLMs) are increasingly deployed in high-stakes applications, robust uncertainty estimation is essential for ensuring the safe and trustworthy deployment of LLMs. We present the most comprehensive study to date of uncertainty estimation in LLMs, evaluating 80 models spanning open- and closed-source families, dense and Mixture-of-Experts (MoE) architectures, reasoning and non-reasoning modes, quantization variants and parameter scales from 0.6B to 671B. Focusing on three representative black-box single-pass methods, including token probability-based uncertainty (TPU), numerical verbal uncertainty (NVU), and linguistic verbal uncertainty (LVU), we systematically evaluate uncertainty calibration and selective classification using the challenging MMLU-Pro benchmark, which covers both reasoning-intensive and knowledge-based tasks. Our results show that LVU consistently outperforms TPU and NVU, offering stronger calibration and discrimination while being more interpretable. We also find that high accuracy does not imply reliable uncertainty, and that model scale, post-training, reasoning ability and quantization all influence estimation performance. Notably, LLMs exhibit better uncertainty estimates on reasoning tasks than on knowledge-heavy ones, and good calibration does not necessarily translate to effective error ranking. These findings highlight the need for multi-perspective evaluation and position LVU as a practical tool for improving the reliability of LLMs in real-world settings.
3.7CVApr 7, 2024
NeRF2Points: Large-Scale Point Cloud Generation From Street Views' Radiance Field OptimizationPeng Tu, Xun Zhou, Mingming Wang et al.
Neural Radiance Fields (NeRF) have emerged as a paradigm-shifting methodology for the photorealistic rendering of objects and environments, enabling the synthesis of novel viewpoints with remarkable fidelity. This is accomplished through the strategic utilization of object-centric camera poses characterized by significant inter-frame overlap. This paper explores a compelling, alternative utility of NeRF: the derivation of point clouds from aggregated urban landscape imagery. The transmutation of street-view data into point clouds is fraught with complexities, attributable to a nexus of interdependent variables. First, high-quality point cloud generation hinges on precise camera poses, yet many datasets suffer from inaccuracies in pose metadata. Also, the standard approach of NeRF is ill-suited for the distinct characteristics of street-view data from autonomous vehicles in vast, open settings. Autonomous vehicle cameras often record with limited overlap, leading to blurring, artifacts, and compromised pavement representation in NeRF-based point clouds. In this paper, we present NeRF2Points, a tailored NeRF variant for urban point cloud synthesis, notable for its high-quality output from RGB inputs alone. Our paper is supported by a bespoke, high-resolution 20-kilometer urban street dataset, designed for point cloud generation and evaluation. NeRF2Points adeptly navigates the inherent challenges of NeRF-based point cloud synthesis through the implementation of the following strategic innovations: (1) Integration of Weighted Iterative Geometric Optimization (WIGO) and Structure from Motion (SfM) for enhanced camera pose accuracy, elevating street-view data precision. (2) Layered Perception and Integrated Modeling (LPiM) is designed for distinct radiance field modeling in urban environments, resulting in coherent point cloud representations.
7.9LGOct 16, 2024
Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed NeighborsLinwei Tao, Haolan Guo, Minjing Dong et al.
Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from miscalibration, with reliability diagrams and Expected Calibration Error (ECE) being the only standard perspective for evaluating calibration performance. In this paper, we introduce the concept of consistency as an alternative perspective on model calibration, inspired by uncertainty estimation literature in large language models (LLMs). We highlight its advantages over the traditional reliability-based view. Building on this concept, we propose a post-hoc calibration method called Consistency Calibration (CC), which adjusts confidence based on the model's consistency across perturbed inputs. CC is particularly effective in locally uncertainty estimation, as it requires no additional data samples or label information, instead generating input perturbations directly from the source data. Moreover, we show that performing perturbations at the logit level significantly improves computational efficiency. We validate the effectiveness of CC through extensive comparisons with various post-hoc and training-time calibration methods, demonstrating state-of-the-art performance on standard datasets such as CIFAR-10, CIFAR-100, and ImageNet, as well as on long-tailed datasets like ImageNet-LT.
3.6CVOct 7, 2025
Efficient Conditional Generation on Scale-based Visual Autoregressive ModelsJiaqi Liu, Tao Huang, Chang Xu
Recent advances in autoregressive (AR) models have demonstrated their potential to rival diffusion models in image synthesis. However, for complex spatially-conditioned generation, current AR approaches rely on fine-tuning the pre-trained model, leading to significant training costs. In this paper, we propose the Efficient Control Model (ECM), a plug-and-play framework featuring a lightweight control module that introduces control signals via a distributed architecture. This architecture consists of context-aware attention layers that refine conditional features using real-time generated tokens, and a shared gated feed-forward network (FFN) designed to maximize the utilization of its limited capacity and ensure coherent control feature learning. Furthermore, recognizing the critical role of early-stage generation in determining semantic structure, we introduce an early-centric sampling strategy that prioritizes learning early control sequences. This approach reduces computational cost by lowering the number of training tokens per iteration, while a complementary temperature scheduling during inference compensates for the resulting insufficient training of late-stage tokens. Extensive experiments on scale-based AR models validate that our method achieves high-fidelity and diverse control over image generation, surpassing existing baselines while significantly improving both training and inference efficiency.
2.7CRFeb 12, 2019
A Privacy-Preserving Traffic Monitoring Scheme via Vehicular CrowdsourcingChuan Zhang, Liehuang Zhu, Chang Xu et al.
The explosive growth of vehicle amount has given rise to a series of traffic problems, such as traffic congestion, road safety, and fuel waste. Collecting vehicles' speed information is an effective way to monitor the traffic condition and avoid vehicles being congested, which however may bring threats to vehicles' location and trajectory privacy. Motivated by the fact that traffic monitoring does not need to know each individual vehicle's speed and the average speed would be sufficient, we propose a privacy-preserving traffic monitoring (PPTM) scheme to aggregate vehicles' speeds at different locations. In PPTM, the roadside unit (RSU) collects vehicles' speed information at multiple road segments, and further cooperates with a service provider to calculate the average speed information for every road segment. To preserve vehicles' privacy, both homomorphic Paillier cryptosystem and super-increasing sequence are adopted. A comprehensive security analysis indicates that the proposed PPTM can preserve vehicles' identities, speeds, locations, and trajectories privacy from being disclosed. In addition, extensive simulations are conducted to validate the effectiveness and efficiency of the proposed PPTM scheme.
2.7CRFeb 12, 2019
Achieving Trust-Based and Privacy-Preserving Customer Selection in Ubiquitous ComputingChuan Zhang, Liehuang Zhu, Chang Xu et al.
The recent proliferation of smart devices has given rise to ubiquitous computing, an emerging computing paradigm which allows anytime & anywhere computing possible. In such a ubiquitous computing environment, customers release different computing or sensing tasks, and people, also known as data processors, participate in these tasks and get paid for providing their idle computing and communication resources. Thus, how to select an appropriate and reliable customer while not disclosing processors' privacy has become an interesting problem. In this article, we present a trust-based and privacy-preserving customer selection scheme in ubiquitous computing, called TPCS, to enable potential processors select the customers with good reputation. The basic concept of TPCS is that each data processor holds a trust value, and the reputation score of the customer is calculated based on processors' trust values and feedbacks via a truth discovery process. To preserve processors' privacy, pseudonyms and Paillier cryptosystem are applied to conceal each processor's real identity. In addition, three authentication protocols are designed to ensure that only the valid data processors (i.e., the processors registering in the system, holding the truthful trust values, and joining the computing tasks) can pass the authentication. A comprehensive security analysis is conducted to prove that our proposed TPCS scheme is secure and can defend against several sophisticated attacks. Moreover, extensive simulations are conducted to demonstrate the correctness and effectiveness of the proposed scheme.
8.5CRApr 6, 2018
PRIF: A Privacy-Preserving Interest-Based Forwarding Scheme for Social Internet of VehiclesLiehuang Zhu, Chuan Zhang, Chang Xu et al.
Recent advances in Socially Aware Networks (SANs) have allowed its use in many domains, out of which social Internet of vehicles (SIOV) is of prime importance. SANs can provide a promising routing and forwarding paradigm for SIOV by using interest-based communication. Though able to improve the forwarding performance, existing interest-based schemes fail to consider the important issue of protecting users' interest information. In this paper, we propose a PRivacy-preserving Interest-based Forwarding scheme (PRIF) for SIOV, which not only protects the interest information, but also improves the forwarding performance. We propose a privacy-preserving authentication protocol to recognize communities among mobile nodes. During data routing and forwarding, a node can know others' interests only if they are affiliated with the same community. Moreover, to improve forwarding performance, a new metric {\em community energy} is introduced to indicate vehicular social proximity. Community energy is generated when two nodes encounter one another and information is shared among them. PRIF considers this energy metric to select forwarders towards the destination node or the destination community. Security analysis indicates PRIF can protect nodes' interest information. In addition, extensive simulations have been conducted to demonstrate that PRIF outperforms the existing algorithms including the BEEINFO, Epidemic, and PRoPHET.
2.3CRApr 6, 2018
PPLS: A Privacy-Preserving Location-Sharing Scheme in Vehicular Social NetworksChang Xu, Xuan Xie, Liehuang Zhu et al.
Recent advances in Socially Aware Networks (SANs) have allowed its use in many domains, out of which social Internet of vehicles (SIOV) is of prime importance. SANs can provide a promising routing and forwarding paradigm for SIOV by using interest-based communication. Though able to improve the forwarding performance, existing interest-based schemes fail to consider the important issue of protecting users' interest information. In this paper, we propose a PRivacy-preserving Interest-based Forwarding scheme (PRIF) for SIOV, which not only protects the interest information, but also improves the forwarding performance. We propose a privacy-preserving authentication protocol to recognize communities among mobile nodes. During data routing and forwarding, a node can know others' interests only if they are affiliated with the same community. Moreover, to improve forwarding performance, a new metric {\em community energy} is introduced to indicate vehicular social proximity. Community energy is generated when two nodes encounter one another and information is shared among them. PRIF considers this energy metric to select forwarders towards the destination node or the destination community. Security analysis indicates PRIF can protect nodes' interest information. In addition, extensive simulations have been conducted to demonstrate that PRIF outperforms the existing algorithms including the BEEINFO, Epidemic, and PRoPHET.
7.2CRApr 5, 2018
LPTD: Achieving Lightweight and Privacy-Preserving Truth Discovery in CIoTChuan Zhang, Liehuang Zhu, Chang Xu et al.
In recent years, cognitive Internet of Things (CIoT) has received considerable attention because it can extract valuable information from various Internet of Things (IoT) devices. In CIoT, truth discovery plays an important role in identifying truthful values from large scale data to help CIoT provide deeper insights and value from collected information. However, the privacy concerns of IoT devices pose a major challenge in designing truth discovery approaches. Although existing schemes of truth discovery can be executed with strong privacy guarantees, they are not efficient or cannot be applied in real-life CIoT applications. This article proposes a novel framework for lightweight and privacy-preserving truth discovery called LPTD-I, which is implemented by incorporating fog and cloud platforms, and adopting the homomorphic Paillier encryption and one-way hash chain techniques. This scheme not only protects devices' privacy, but also achieves high efficiency. Moreover, we introduce a fault tolerant (LPTD-II) framework which can effectively overcome malfunctioning CIoT devices. Detailed security analysis indicates the proposed schemes are secure under a comprehensively designed threat model. Experimental simulations are also carried out to demonstrate the efficiency of the proposed schemes.