arXiv subjects

Chenyi Wang

Publications and source records attributed to Chenyi Wang.

17 recordsLinked to original sources

arXiv2026

Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies

Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned demonstration clip contains this missing supervision because its $K$ frame transitions record the geometry, motion, visibility, and camera change produced during the corresponding $K$ actions. We introduce Track4Action, a framework that distills this realized transition from a frozen world-centric 3D tracker into a current-observation VLA policy. During training, Track4World encodes the clip $V_{t:t+K}$ into a pooled tracker feature. Learnable track queries infer this feature from current VLA hidden states, match it in a shared space, and condition a flow-matching action head through a feature-wise gate. The tracker feature only defines the alignment target, so neither the clip nor the tracker is used at deployment. Track4Action reaches 82.3% on zero-shot LIBERO-Plus, improving the alignment-free variant by 7.6 points and LaMP by 3.0 points. It obtains 80.44% and 81.48% on the clean and randomized RoboTwin 2.0 splits, and 67.5% average success across four physical bimanual tasks, 25.0 points above the alignment-free variant. The gains across simulation and physical tasks support action-aligned 3D tracker features as privileged supervision for tracker-free VLA deployment. Our project page is available at https://wing0night.github.io/track4action-project-page.

cs.RO↗

arXiv2026

Sub-40 nm resolution deep tissue imaging by image scanning emission saturation nanoscopy

The development of deep-tissue super-resolution imaging serves as an essential bridge toward non-invasive in vivo optical observation. However, there remain challenges to balance spatial resolution, imaging depth and phototoxicity. Here, we present a nanoscopy namely Image Scanning Emission Saturation (ISES) nanoscopy, achieving a lateral resolution of 37 nm, 1/25th of the excitation wavelength, at an imaging depth of 200 {\mu}m. Using a 976-nm doughnut-shaped excitation beam within an imaging-scanning microscopy configuration, we apply saturation-based point spread function (PSF) engineering and pixel-level confocal-pinhole enhancement to improve spatial resolution. As the high- and low-frequency components of the image OTF are concurrently acquired in a single scan via different camera pixels, Fourier-domain fusion can be employed with a single scanning dataset to further improve image quality. Compared with the traditional doughnut excitation beam-based adaptive pixel reassignment method, our strategy preserves the original frequency distributions and mitigates reconstruction artifacts in complex biological sample imaging. This strategy is generalizable and compatible with a variety of probes displaying saturation behavior. Beyond enabling a versatile and practical approach for deep tissue super-resolution imaging, it also informs the development of next-generation nanoprobes for imaging.

physics.optics↗

arXiv2026

Adversarial Trust Poisoning in Vehicular Collaborative Perception

Collaborative perception (CP) enables connected and autonomous vehicles to share sensor data and jointly reason about their environment. To defend against adversaries that fabricate or manipulate shared data, existing systems employ cross-vehicle inconsistency detection and trust estimation, penalizing vehicles whose observations conflict with the majority. In this work, we show that these defenses themselves introduce a new attack surface. We present TrustFlip, a novel attack that weaponizes consistency-based defenses to poison the trust assigned to benign vehicles. Instead of injecting false data into the collaboration pipeline, it deploys physical adversarial objects that are genuine but induce inconsistent observations among benign vehicles. The resulting inconsistencies are misattributed by the defense to the targeted vehicle, causing its trust score to degrade and eventually leading to its downweighting or exclusion from collaboration. Consequently, the system loses reliable sensing contributors, degrading perception capability and potentially inducing safety-critical failures. We evaluate TrustFlip across multiple collaborative perception architectures and defense mechanisms. Our results show that state-of-the-art defenses can be significantly affected: the attack removes the targeted benign vehicle from collaboration in up to 87.7% of scenarios and drops Average Precision (AP) by up to 13%. As an initial mitigation, we introduce TrustReflect, a lightweight self-reflection mechanism that marks disputed regions as uncertain and excludes them from trust evaluation, reducing the attack success rate by 35-100%.

cs.CR↗

arXiv2026

Systematic Discovery of Semantic Attacks in Online Map Construction through Conditional Diffusion

Autonomous vehicles depend on online HD map construction to perceive lane boundaries, dividers, and pedestrian crossings -- safety-critical road elements that directly govern motion planning. While existing pixel perturbation attacks can disrupt the mapping, they can be neutralized by standard adversarial defenses. We present MIRAGE, a framework for systematic discovery of semantic attacks that bypass adversarial defenses and degrade mapping predictions by finding plausible environmental variation (e.g. shadows, wet roads). MIRAGE exploits the latent manifold of real-world data learned by diffusion models, and searches for semantically mutated scenes neighboring the ground truth with the same road topology yet mislead the mapping predictions. We evaluate MIRAGE on nuScenes and demonstrate two attacks: (1) boundary removal, suppressing 57.7% of detections and corrupting 96% of planned trajectories; and (2) boundary injection, the only method that successfully injects fictitious boundaries, while pixel PGD and AdvPatch fail entirely. Both attacks remain potent under various adversarial defenses. We use two independent VLM judges to quantify realism, where MIRAGE passes as realistic 80--84% of the time (vs. 97--99% for clean nuScenes), while AdvPatch only 0--9%. Our findings expose a categorical gap in current adversarial defenses: semantic-level perturbations that manifest as legitimate environmental variation are substantially harder to mitigate than pixel-level perturbations.

cs.CV↗

arXiv2026

LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior

We introduce \textbf{LaMP}, a dual-expert Vision-Language-Action framework that embeds dense 3D scene flow as a latent motion prior for robotic manipulation.Existing VLA models regress actions directly from 2D semantic visual features, forcing them to learn complex 3D physical interactions implicitly.This implicit learning strategy degrades under unfamiliar spatial dynamics.LaMP addresses this limitation by aligning a flow-matching \emph{Motion Expert} with a policy-predicting \emph{Action Expert} through gated cross-attention.Specifically, the Motion Expert generates a one-step partially denoised 3D scene flow, and its hidden states condition the Action Expert without full multi-step reconstruction.We evaluate LaMP on the LIBERO, LIBERO-Plus, and SimplerEnv-WidowX simulation benchmarks as well as real-world experiments.LaMP consistently outperforms evaluated VLA baselines across LIBERO, LIBERO-Plus, and SimplerEnv-WidowX benchmarks, achieving the highest reported average success rates under the same training budgets. On LIBERO-Plus OOD perturbations, LaMP shows improved robustness with an average 9.7\% gain over the strongest prior baseline.Our project page is available at https://summerwxk.github.io/lamp-project-page/.

cs.CV↗

arXiv2026

Harnessing Non-Boltzmann Steady States in Lanthanide Nanocrystals for Mid-Infrared Optoelectronics

Converting mid-infrared (MIR) radiation to visible or near-infrared wavelengths is essential for imaging and sensing, yet achieving sensitive, low-power, and scalable detection remains challenging. Lanthanide nanocrystals provide an alternative through ratiometric luminescence but are typically constrained by Boltzmann statistics, which tie population distributions to lattice temperature and limit signal contrast. Here we show that MIR irradiation rebalances dissipative relaxation pathways, driving lanthanide emitters into a non-Boltzmann steady state that enables non-thermal control of population distributions. This allows emission behaviors inaccessible under thermal equilibrium. We exploit this regime to achieve linear MIR detection with respect to MIR power across 6.8 to 8.6 micrometers. The ratiometric response is intrinsically independent of the pump power, enabling operation at an ultralow excitation power of 10 uW, several orders of magnitude lower than conventional approaches. Using standard silicon photodetectors, we then demonstrate room-temperature MIR imaging with detection limits approaching 4 nW um-2. Our results establish lanthanide nanoparticles as an efficient platform for MIR conversion and sensing in nanophotonic systems.

physics.optics↗

arXiv2026

JigsawComm: Joint Semantic Feature Encoding and Transmission for Communication-Efficient Cooperative Perception

Multi-agent cooperative perception (CP) promises to overcome the inherent occlusion and range limitations of single-agent systems in autonomous driving, yet its practicality is severely constrained by limited Vehicle-to-Everything (V2X) communication bandwidth. Existing approaches attempt to improve bandwidth efficiency via compression or heuristic message selection, but neglect the semantic relevance and cross-agent redundancy of the transmitted data. In this paper, we formulate a joint semantic feature encoding and transmission problem that maximizes CP accuracy under a communication budget, and introduce JigsawComm, an end-to-end semantic-aware framework that learns to ``assemble the puzzle'' of multi-agent feature transmission. JigsawComm uses a regularized encoder to extract \emph{sparse, semantically relevant features}, and a lightweight Feature Utility Estimator (FUE) to predict each agent's per-cell contribution to the downstream perception task. The FUE-generated compact meta utility maps are exchanged among agents and used to compute an optimal transmission policy under the learned utility proxy. This policy inherently \emph{eliminates cross-agent redundancy}, bounding the feature transmission payload to $\mathcal{O}(1)$ as the number of agents grows, while the meta information overhead remains negligible. The whole pipeline is trained end-to-end through a differentiable scheduling module, informing the FUE to be aligned with the task objective. On the OPV2V and DAIR-V2X benchmarks, JigsawComm reduces total data volume by over 20--500${\times}$ while matching or exceeding the accuracy of state-of-the-art methods.

cs.CV↗

arXiv2026

A Long-term Value Prediction Framework In Video Ranking

Accurately modeling long-term value (LTV) at the ranking stage of short-video recommendation remains challenging. While delayed feedback and extended engagement have been explored, fine-grained attribution and robust position normalization at billion-scale are still underdeveloped. We propose a practical ranking-stage LTV framework addressing three challenges: position bias, attribution ambiguity, and temporal limitations. (1) Position bias: We introduce a Position-aware Debias Quantile (PDQ) module that normalizes engagement via quantile-based distributions, enabling position-robust LTV estimation without architectural changes. (2) Attribution ambiguity: We propose a multi-dimensional attribution module that learns continuous attribution strengths across contextual, behavioral, and content signals, replacing static rules to capture nuanced inter-video influence. A customized hybrid loss with explicit noise filtering improves causal clarity. (3) Temporal limitations: We present a cross-temporal author modeling module that builds censoring-aware, day-level LTV targets to capture creator-driven re-engagement over longer horizons; the design is extensible to other dimensions (e.g., topics, styles). Offline studies and online A/B tests show significant improvements in LTV metrics and stable trade-offs with short-term objectives. Implemented as task augmentation within an existing ranking model, the framework supports efficient training and serving, and has been deployed at billion-scale in Taobao's production system, delivering sustained engagement gains while remaining compatible with industrial constraints.

cs.IR↗

arXiv2025

Physical ID-Transfer Attacks against Multi-Object Tracking via Adversarial Trajectory

Multi-Object Tracking (MOT) is a critical task in computer vision, with applications ranging from surveillance systems to autonomous driving. However, threats to MOT algorithms have yet been widely studied. In particular, incorrect association between the tracked objects and their assigned IDs can lead to severe consequences, such as wrong trajectory predictions. Previous attacks against MOT either focused on hijacking the trackers of individual objects, or manipulating the tracker IDs in MOT by attacking the integrated object detection (OD) module in the digital domain, which are model-specific, non-robust, and only able to affect specific samples in offline datasets. In this paper, we present AdvTraj, the first online and physical ID-manipulation attack against tracking-by-detection MOT, in which an attacker uses adversarial trajectories to transfer its ID to a targeted object to confuse the tracking system, without attacking OD. Our simulation results in CARLA show that AdvTraj can fool ID assignments with 100% success rate in various scenarios for white-box attacks against SORT, which also have high attack transferability (up to 93% attack success rate) against state-of-the-art (SOTA) MOT algorithms due to their common design principles. We characterize the patterns of trajectories generated by AdvTraj and propose two universal adversarial maneuvers that can be performed by a human walker/driver in daily scenarios. Our work reveals under-explored weaknesses in the object association phase of SOTA MOT systems, and provides insights into enhancing the robustness of such systems.

cs.CV↗

arXiv2025

BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Web

The rapid development of large language models (LLMs) has significantly propelled the development of artificial intelligence (AI) agents, which are increasingly evolving into diverse autonomous entities, advancing the LLM-based multi-agent systems (LaMAS). However, current agentic ecosystems remain fragmented and closed. Establishing an interconnected and scalable paradigm for Agentic AI has become a critical prerequisite. Although Agentic Web proposes an open architecture to break the ecosystem barriers, its implementation still faces core challenges such as privacy protection, data management, and value measurement. Existing centralized or semi-centralized paradigms suffer from inherent limitations, making them inadequate for supporting large-scale, heterogeneous, and cross-domain autonomous interactions. To address these challenges, this paper introduces the blockchain-enabled trustworthy Agentic Web (BetaWeb). By leveraging the inherent strengths of blockchain, BetaWeb not only offers a trustworthy and scalable infrastructure for LaMAS but also has the potential to advance the Web paradigm from Web3 (centered on data ownership) towards Web3.5, which emphasizes ownership of agent capabilities and the monetization of intelligence. Beyond a systematic examination of the BetaWeb framework, this paper presents a five-stage evolutionary roadmap, outlining the path of LaMAS from passive execution to advanced collaboration and autonomous governance. We also conduct a comparative analysis of existing products and discuss key challenges of BetaWeb from multiple perspectives. Ultimately, we argue that deep integration between blockchain and LaMAS can lay the foundation for a resilient, trustworthy, and sustainably incentivized digital ecosystem. A summary of the enabling technologies for each stage is available at https://github.com/MatZaharia/BetaWeb.

cs.MA↗

arXiv2025

CP-FREEZER: Latency Attacks against Vehicular Cooperative Perception

Cooperative perception (CP) enhances situational awareness of connected and autonomous vehicles by exchanging and combining messages from multiple agents. While prior work has explored adversarial integrity attacks that degrade perceptual accuracy, little is known about CP's robustness against attacks on timeliness (or availability), a safety-critical requirement for autonomous driving. In this paper, we present CP-FREEZER, the first latency attack that maximizes the computation delay of CP algorithms by injecting adversarial perturbation via V2V messages. Our attack resolves several unique challenges, including the non-differentiability of point cloud preprocessing, asynchronous knowledge of the victim's input due to transmission delays, and uses a novel loss function that effectively maximizes the execution time of the CP pipeline. Extensive experiments show that CP-FREEZER increases end-to-end CP latency by over $90\times$, pushing per-frame processing time beyond 3 seconds with a 100% success rate on our real-world vehicle testbed. Our findings reveal a critical threat to the availability of CP systems, highlighting the urgent need for robust defenses.

cs.CR↗

arXiv2025

Lanthanide upconversion nonlinearity: a key probe feature for background-free deep-tissue imaging

Lanthanide-based upconversion nanoparticles (UCNPs) have attracted considerable attention in biomedical applications, largely due to their anti-Stokes shifted emission enabling autofluorescence-free signal detection. However, residual excitation light can still interfere with their relatively low brightness. While commonly used lock-in detection can distinguish weak signals from substantial random background, concurrently modulated residual excitation light is not eliminated. This remains a challenge, particularly under demanding experimental conditions. Here, we explore the inherent nonlinear response of UCNPs and discover that UCNPs can act as frequency mixers in response to intensity-modulated excitation. Particularly, modulated excitation with more than one base modulation frequency can generate additional low-frequency beating-signals. We show how these signals are resolvable by low-speed detectors such as cameras, are devoid of ambient and residual excitation light, and how they can be enhanced through nanoparticle engineering. Detection of beating-signals thus provides a strategy to significantly enhance signal-to-background conditions in UCNP-based bioimaging and biosensing.

physics.optics↗

arXiv2024

NAND-like SOT-MRAM-based Approximate Storage for Error-Tolerant Applications

We demonstrate approximate storage based on NAND-like spin-orbit torque (SOT) MRAM, through "device-modeling-architecture" explorations. We experimentally achieve down to 1E-5 level selectivity. Selectivity and low-power solutions are established by numerical calculation workflow. System-level power consumption is evaluated in the 512 KB last-level cache according to 5 quality levels. Error-tolerant applications, such as image processing, alleviate the demand for selectivity down to the 5E-2 level, leading to 54% ~ 61% energy-saving. Our proposal paves the novel and suitable path for high-density and low-power NAND-like SOT-MRAM.

physics.app-ph↗

arXiv2024

Industrial Internet of Things Intelligence Empowering Smart Manufacturing: A Literature Review

The fiercely competitive business environment and increasingly personalized customization needs are driving the digital transformation and upgrading of the manufacturing industry. IIoT intelligence, which can provide innovative and efficient solutions for various aspects of the manufacturing value chain, illuminates the path of transformation for the manufacturing industry. It's time to provide a systematic vision of IIoT intelligence. However, existing surveys often focus on specific areas of IIoT intelligence, leading researchers and readers to have biases in their understanding of IIoT intelligence, that is, believing that research in one direction is the most important for the development of IIoT intelligence, while ignoring contributions from other directions. Therefore, this paper provides a comprehensive overview of IIoT intelligence. We first conduct an in-depth analysis of the inevitability of manufacturing transformation and study the successful experiences from the practices of Chinese enterprises. Then we give our definition of IIoT intelligence and demonstrate the value of IIoT intelligence for industries in fucntions, operations, deployments, and application. Afterwards, we propose a hierarchical development architecture for IIoT intelligence, which consists of five layers. The practical values of technical upgrades at each layer are illustrated by a close look on lighthouse factories. Following that, we identify seven kinds of technologies that accelerate the transformation of manufacturing, and clarify their contributions. The ethical implications and environmental impacts of adopting IIoT intelligence in manufacturing are analyzed as well. Finally, we explore the open challenges and development trends from four aspects to inspire future researches.

cs.AI↗

arXiv2023

"Can You Move It?": The Design and Evaluation of Moving VR Shots in Sport Broadcast

Virtual Reality (VR) broadcasting has seen widespread adoption in major sports events, attributed to its ability to generate a sense of presence, curiosity, and excitement among viewers. However, we have noticed that still shots reveal a limitation in the movement of VR cameras and hinder the VR viewing experience in current VR sports broadcasts. This paper aims to bridge this gap by engaging in a quantitative user analysis to explore the design and impact of dynamic VR shots on viewing experiences. We conducted two user studies in a digital hockey game twin environment and asked participants to evaluate their viewing experience through two questionnaires. Our findings suggested that the viewing experiences demonstrated no notable disparity between still and moving shots for single clips. However, when considering entire events, moving shots improved the viewer's immersive experience, with no notable increase in sickness compared to still shots. We further discuss the benefits of integrating moving shots into VR sports broadcasts and present a set of design considerations and potential improvements for future VR sports broadcasting.

cs.HC↗

arXiv2023

ABC: Attention with Bilinear Correlation for Infrared Small Target Detection

Infrared small target detection (ISTD) has a wide range of applications in early warning, rescue, and guidance. However, CNN based deep learning methods are not effective at segmenting infrared small target (IRST) that it lack of clear contour and texture features, and transformer based methods also struggle to achieve significant results due to the absence of convolution induction bias. To address these issues, we propose a new model called attention with bilinear correlation (ABC), which is based on the transformer architecture and includes a convolution linear fusion transformer (CLFT) module with a novel attention mechanism for feature extraction and fusion, which effectively enhances target features and suppresses noise. Additionally, our model includes a u-shaped convolution-dilated convolution (UCDC) module located deeper layers of the network, which takes advantage of the smaller resolution of deeper features to obtain finer semantic information. Experimental results on public datasets demonstrate that our approach achieves state-of-the-art performance. Code is available at https://github.com/PANPEIWEN/ABC

cs.CV↗

arXiv2023

Local Contrast and Global Contextual Information Make Infrared Small Object Salient Again

Infrared small object detection (ISOS) aims to segment small objects only covered with several pixels from clutter background in infrared images. It's of great challenge due to: 1) small objects lack of sufficient intensity, shape and texture information; 2) small objects are easily lost in the process where detection models, say deep neural networks, obtain high-level semantic features and image-level receptive fields through successive downsampling. This paper proposes a reliable detection model for ISOS, dubbed UCFNet, which can handle well the two issues. It builds upon central difference convolution (CDC) and fast Fourier convolution (FFC). On one hand, CDC can effectively guide the network to learn the contrast information between small objects and the background, as the contrast information is very essential in human visual system dealing with the ISOS task. On the other hand, FFC can gain image-level receptive fields and extract global information while preventing small objects from being overwhelmed.Experiments on several public datasets demonstrate that our method significantly outperforms the state-of-the-art ISOS models, and can provide useful guidelines for designing better ISOS deep models. Code are available at https://github.com/wcyjerry/BasicISOS.

cs.CV↗