arXiv subjects

Xin Gong

Publications and source records attributed to Xin Gong.

At least 19 recordsLinked to original sources

arXiv2026

OZ-TAL: Online Zero-Shot Temporal Action Localization

Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent advancements in this field focus on developing more sophisticated frameworks, shifting from Online Action Detection (OAD)-based aggregation paradigm to instance-level understanding. However, existing approaches are typically trained on specific domains and often exhibit limited generalization capabilities when applied to arbitrary videos, particularly in the presence of previously unseen actions. In this paper, we introduce a new task called Online Zero-shot Temporal Action Localization (OZ-TAL), which aims to detect previously unseen actions in an online fashion. Furthermore, we propose a training-free framework that leverages off-the-shelf Vision-Language Models (VLMs) while introducing additional mechanisms to enhance visual representations and mitigate their inherent biases. We establish new benchmarks and representative baselines for OZ-TAL on THUMOS14 and ActivityNet-1.3, and extensive experiments demonstrate that our method substantially outperforms existing state-of-the-art approaches under both offline and online zero-shot settings.

cs.CV↗

arXiv2026

DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models

Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often struggle with complex, multi-step tasks requiring logical planning, as well as precise manipulations demanding fine-grained spatial perception. Recent efforts have incorporated Chain-of-Thought (CoT) reasoning to endow VLA models with a ``thinking before acting'' capability. However, current CoT-based VLA models face two critical limitations: 1) an inability to simultaneously capture low-level visual details and high-level logical planning due to their reliance on isolated, single-modal CoT; 2) high inference latency with compounding errors caused by step-by-step autoregressive decoding. To address these limitations, we propose DualCoT-VLA, a visual-linguistic CoT method for VLA models with a parallel reasoning mechanism. To achieve comprehensive multi-modal reasoning, our method integrates a visual CoT for low-level spatial understanding and a linguistic CoT for high-level task planning. Furthermore, to overcome the latency bottleneck, we introduce a parallel CoT mechanism that incorporates two sets of learnable query tokens, shifting autoregressive reasoning to single-step forward reasoning. Extensive experiments demonstrate that our DualCoT-VLA achieves state-of-the-art performance on the LIBERO and RoboCasa GR1 benchmarks, as well as in real-world platforms.

cs.CV↗

arXiv2026

S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight

Video action models (VAMs) have emerged as a promising paradigm for robot learning, owing to their powerful visual foresight for complex manipulation tasks. However, current VAMs, typically relying on either slow multi-step video generation or noisy one-step feature extraction, cannot simultaneously guarantee real-time inference and high-fidelity foresight. To address this limitation, we propose S-VAM, a shortcut video-action model that foresees coherent geometric and semantic representations via a single forward pass. Serving as a stable blueprint, these foreseen representations significantly simplify the action prediction. To enable this efficient shortcut, we introduce a novel self-distillation strategy that condenses structured generative priors of multi-step denoising into one-step inference. Specifically, vision foundation model (VFM) representations extracted from the diffusion model's own multi-step generated videos provide teacher targets. Lightweight decouplers, as students, learn to directly map noisy one-step features to these targets. Extensive experiments in simulation and the real world demonstrate that our S-VAM outperforms state-of-the-art methods, enabling efficient and precise manipulation in complex environments. Our project page is https://haodong-yan.github.io/S-VAM/

cs.CV↗

arXiv2025

Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation

Generating realistic hand-object interactions (HOI) videos is a significant challenge due to the difficulty of modeling physical constraints (e.g., contact and occlusion between hands and manipulated objects). Current methods utilize HOI representation as an auxiliary generative objective to guide video synthesis. However, there is a dilemma between 2D and 3D representations that cannot simultaneously guarantee scalability and interaction fidelity. To address this limitation, we propose a structure and contact-aware representation that captures hand-object contact, hand-object occlusion, and holistic structure context without 3D annotations. This interaction-oriented and scalable supervision signal enables the model to learn fine-grained interaction physics and generalize to open-world scenarios. To fully exploit the proposed representation, we introduce a joint-generation paradigm with a share-and-specialization strategy that generates interaction-oriented representations and videos. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on two real-world datasets in generating physics-realistic and temporally coherent HOI videos. Furthermore, our approach exhibits strong generalization to challenging open-world scenarios, highlighting the benefit of our scalable design. Our project page is https://hgzn258.github.io/SCAR/.

cs.CV↗

arXiv2025

FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Models

Many Vision-Language-Action (VLA) models are built upon an internal world model trained via next-frame prediction ``$v_t \rightarrow v_{t+1}$''. However, this paradigm attempts to predict the future frame's appearance directly, without explicitly reasoning about the underlying dynamics. \textbf{This lack of an explicit motion reasoning step} often leads to physically implausible visual forecasts and inefficient policy learning. To address this limitation, we introduce the \textbf{Visual Chain of Thought (Visual CoT)}, a paradigm that compels the model to first reason about \textbf{motion dynamics} before generating the future frame. We instantiate this paradigm by proposing \textbf{FlowVLA}, an autoregressive Transformer that explicitly materializes this reasoning process as ``$v_t \rightarrow f_t \rightarrow v_{t+1}$'', where $f_t$ is an intermediate optical flow prediction that inherently encodes motion. By forcing the model to first follow the motion plan encoded by $f_t$, this process inherently \textbf{aligns the pre-training objective of dynamics prediction with the downstream task of action generation.} We conduct experiments on challenging robotics manipulation benchmarks, as well as real-robot evaluations. Our FlowVLA not only generates \textbf{more coherent and physically plausible visual predictions}, but also achieves state-of-the-art policy performance with \textbf{substantially improved sample efficiency}, pointing toward a more principled foundation for world modeling in VLAs. Project page: https://irpn-lab.github.io/FlowVLA/

cs.RO↗

arXiv2025

Deep Learning-Based Point Cloud Registration: A Comprehensive Survey and Taxonomy

Point cloud registration involves determining a rigid transformation to align a source point cloud with a target point cloud. This alignment is fundamental in applications such as autonomous driving, robotics, and medical imaging, where precise spatial correspondence is essential. Deep learning has greatly advanced point cloud registration by providing robust and efficient methods that address the limitations of traditional approaches, including sensitivity to noise, outliers, and initialization. However, a well-constructed taxonomy for these methods is still lacking, making it difficult to systematically classify and compare the various approaches. In this paper, we present a comprehensive survey and taxonomy on deep learning-based point cloud registration (DL-PCR). We begin with a formal description of the point cloud registration problem, followed by an overview of the datasets, evaluation metrics, and loss functions commonly used in DL-PCR. Next, we categorize existing DL-PCR methods into supervised and unsupervised approaches, as they focus on significantly different key aspects. For supervised DL-PCR methods, we organize the discussion based on key aspects, including the registration procedure, optimization strategy, learning paradigm, network enhancement, and integration with traditional methods; For unsupervised DL-PCR methods, we classify them into correspondence-based and correspondence-free approaches, depending on whether they require explicit identification of point-to-point correspondences. To facilitate a more comprehensive and fair comparison, we conduct quantitative evaluations of all recent state-of-the-art approaches, using a unified training setting and consistent data partitioning strategy. Lastly, we highlight the open challenges and discuss potential directions for future study. A comprehensive collection is available at https://github.com/yxzhang15/PCR.

cs.CV↗

arXiv2024

Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models

Learning-based methods for underwater image enhancement (UWIE) have undergone extensive exploration. However, learning-based models are usually vulnerable to adversarial examples so as the UWIE models. To the best of our knowledge, there is no comprehensive study on the adversarial robustness of UWIE models, which indicates that UWIE models are potentially under the threat of adversarial attacks. In this paper, we propose a general adversarial attack protocol. We make a first attempt to conduct adversarial attacks on five well-designed UWIE models on three common underwater image benchmark datasets. Considering the scattering and absorption of light in the underwater environment, there exists a strong correlation between color correction and underwater image enhancement. On the basis of that, we also design two effective UWIE-oriented adversarial attack methods Pixel Attack and Color Shift Attack targeting different color spaces. The results show that five models exhibit varying degrees of vulnerability to adversarial attacks and well-designed small perturbations on degraded images are capable of preventing UWIE models from generating enhanced results. Further, we conduct adversarial training on these models and successfully mitigated the effectiveness of adversarial attacks. In summary, we reveal the adversarial vulnerability of UWIE models and propose a new evaluation dimension of UWIE models.

eess.IV↗

arXiv2024

A Meta-analysis of College Students' Intention to Use Generative Artificial Intelligence

It is of critical importance to analyse the factors influencing college students' intention to use generative artificial intelligence (GenAI) to understand and predict learners' learning behaviours and academic outcomes. Nevertheless, a lack of congruity has been shown in extant research results. This study, therefore, conducted a meta-analysis of 27 empirical studies under an integrated theoretical framework, including 87 effect sizes of independent research and 33,833 sample data. The results revealed that the main variables are strongly correlated with students' behavioural intention to use GenAI. Among them, performance expectancy (r = 0.389) and attitudes (r = 0.576) play particularly critical roles, and effort expectancy and habit are moderated by locational factors. Gender, notably, only moderated attitudes on students' behavioural intention to use GenAI. This study provides valuable insights for addressing the debate regarding students' intention to use GenAI in existed research, improving educational technology, as well as offering support for school decision-makers and educators to apply GenAI in school settings.

cs.CY↗

arXiv2023

Resilient Output Containment Control of Heterogeneous Multiagent Systems Against Composite Attacks: A Digital Twin Approach

This paper studies the distributed resilient output containment control of heterogeneous multiagent systems against composite attacks, including denial-of-services (DoS) attacks, false-data injection (FDI) attacks, camouflage attacks, and actuation attacks. Inspired by digital twins, a twin layer (TL) with higher security and privacy is used to decouple the above problem into two tasks: defense protocols against DoS attacks on TL and defense protocols against actuation attacks on cyber-physical layer (CPL). First, considering modeling errors of leader dynamics, we introduce distributed observers to reconstruct the leader dynamics for each follower on TL under DoS attacks. Second, distributed estimators are used to estimate follower states according to the reconstructed leader dynamics on the TL. Third, according to the reconstructed leader dynamics, we design decentralized solvers that calculate the output regulator equations on CPL. Fourth, decentralized adaptive attack-resilient control schemes that resist unbounded actuation attacks are provided on CPL. Furthermore, we apply the above control protocols to prove that the followers can achieve uniformly ultimately bounded (UUB) convergence, and the upper bound of the UUB convergence is determined explicitly. Finally, two simulation examples are provided to show the effectiveness of the proposed control protocols.

eess.SY↗

arXiv2023

Data-Driven Leader-following Consensus for Nonlinear Multi-Agent Systems against Composite Attacks: A Twins Layer Approach

This paper studies the leader-following consensuses of uncertain and nonlinear multi-agent systems against composite attacks (CAs), including Denial of Service (DoS) attacks and actuation attacks (AAs). A double-layer control framework is formulated, where a digital twin layer (TL) is added beside the traditional cyber-physical layer (CPL), inspired by the recent Digital Twin technology. Consequently, the resilient control task against CAs can be divided into two parts: One is distributed estimation against DoS attacks on the TL and the other is resilient decentralized tracking control against actuation attacks on the CPL. %The data-driven scheme is used to deal with both model non-linearity and model uncertainty, in which only the input and output data of the system are employed throughout the whole control process. First, a distributed observer based on switching estimation law against DoS is designed on TL. Second, a distributed model free adaptive control (DMFAC) protocol based on attack compensation against AAs is designed on CPL. Moreover, the uniformly ultimately bounded convergence of consensus error of the proposed double-layer DMFAC algorithm is strictly proved. Finally, the simulation verifies the effectiveness of the resilient double-layer control scheme.

eess.SY↗

arXiv2023

Resilient Output Consensus Control of Heterogeneous Multi-agent Systems against Byzantine Attacks: A Twin Layer Approach

This paper studies the problem of cooperative control of heterogeneous multi-agent systems (MASs) against Byzantine attacks. The agent affected by Byzantine attacks sends different wrong values to all neighbors while applying wrong input signals for itself, which is aggressive and difficult to be defended. Inspired by the concept of Digital Twin, a new hierarchical protocol equipped with a virtual twin layer (TL) is proposed, which decouples the above problems into the defense scheme against Byzantine edge attacks on the TL and the defense scheme against Byzantine node attacks on the cyber-physical layer (CPL). On the TL, we propose a resilient topology reconfiguration strategy by adding a minimum number of key edges to improve network resilience. It is strictly proved that the control strategy is sufficient to achieve asymptotic consensus in finite time with the topology on the TL satisfying strongly $(2f+1)$-robustness. On the CPL, decentralized chattering-free controllers are proposed to guarantee the resilient output consensus for the heterogeneous MASs against Byzantine node attacks. Moreover, the obtained controller shows exponential convergence. The effectiveness and practicality of the theoretical results are verified by numerical examples.

eess.SY↗

arXiv2023

Optimal Resource Allocation between Two Nonfully Cooperative Wireless Networks under Malicious Attacks: A Gestalt Game Perspective

In this paper, the problem of seeking optimal distributed resource allocation (DRA) policies on cellular networks in the presence of an unknown malicious adding-edge attacker is investigated. This problem is described as the games of games (GoG) model. Specifically, two subnetwork policymakers constitute a Nash game, while the confrontation between each subnetwork policymaker and the attacker is captured by a Stackelberg game. First, we show that the communication resource allocation of cellular networks based on the Foschini-Miljanic (FM) algorithm can be transformed into a \emph{geometric program} and be efficiently solved via convex optimization. Second, the upper limit of attack magnitude that can be tolerated by the network is calculated by the corresponding theory, and it is proved that the above geometric programming (GP) framework is solvable within the attack bound, that is, there exists a Gestalt Nash equilibrium (GNE) in our GoG. Third, a heuristic algorithm that iteratively uses GP is proposed to identify the optimal policy profiles of both subnetworks, for which asymptotic convergence is also confirmed. Fourth, a greedy heuristic adding-edge strategy is developed for the attacker to determine the set of the most vulnerable edges. Finally, simulation examples illustrate that the proposed theoretical results are robust and can achieve the GNE. It is verified that the transmission gains and interference gains of all channels are well tuned within a limited budget, despite the existence of malicious attacks.

eess.SY↗

arXiv2022

Towards Safe and Efficient Swarm-Human Collaboration: A Hierarchical Multi-Agent Pickup and Delivery framework

The multi-Agent Pickup and Delivery (MAPD) problem is crucial in the realm of Intelligent Storage Systems (ISSs), where multiple robots are assigned with time-varying, heterogeneous, and potentially uncertain tasks. When it comes to Human-Swarm Hybrid System ((HS)$_2$), robots and human workers will accomplish the MAPD tasks in collaboration. Herein, we propose a Human-Swarm Hybrid System Pickup and Delivery ((HS)$_2$PD) framework, which is predominant in future ISSs. A two-layer decision framework based on the prediction horizon window is established in light of the unpredictability of human behavior and the dynamic changes of tasks. The first layer is a two-level programming problem to solve the problems of mode assignment and TA. The second layer is devoted to the exact path of each agent via solving mixed-integer programming (MIP) problems. An integrated algorithm for the (HS)$_2$PD problem is summarized. The practicality and validity of the above algorithm are illustrated via a numerical simulation example towards (HS)$_2$PD tasks.

cs.MA↗

arXiv2021

Resilient Path Planning of UAVs against Covert Attacks on UWB Sensors

In this letter, a resilient path planning scheme is proposed to navigate a UAV to the planned (nominal) destination with minimum energy-consumption in the presence of a smart attacker. The UAV is equipped with two sensors, a GPS sensor, which is vulnerable to the spoofing attacker, and a well-functioning Ultra-Wideband (UWB) sensor, which is possible to be fooled. We show that a covert attacker can significantly deviate the UAV's path by simultaneously corrupting the GPS signals and forging control inputs without being detected by the UWB sensor. The prerequisite for the attack occurrence is first discussed. Based on this prerequisite, the optimal attack scheme is proposed, which maximizes the deviation between the nominal destination and the real one. Correspondingly, an energy-efficient and resilient navigation scheme based on Pontryagin's maximum principle \cite{gelfand2000calculus} is formulated, which depresses the above covert attacker effectively. To sum up, this problem can be seen as a Stackelberg game \cite{bacsar1998dynamic} between a secure path planner (defender) and a covert attacker. The effectiveness and practicality of our theoretical results are illustrated via two series of simulation examples and a UAV experiment.

cs.RO↗

arXiv2019

Current-driven skyrmion motion in granular films

Current-driven skyrmion motion in random granular films is investigated with interesting findings. For a given current, there exists a critical disorder strength below which its transverse motion could either be boosted below a critical damping or be hindered above the critical damping, resulting in current and disorder dependences of skyrmion Hall angle. The boosting comes mainly from the random force that is opposite to the driving force (current). The critical damping depends on the current density and disorder strength. However, the longitudinal motion of a skyrmion is always hindered by the disorder. Above the critical disorder strength, skyrmions are pinned. The disorder-induced random force on a skyrmion can be classified as static and kinetic ones, similar to the friction force in the Newtonian mechanics. In the pinning phase, the static (pinning) random force is transverse to the current density. The kinetic random force is opposite to the skyrmion velocity when skyrmions are in motion. Furthermore, we provide strong evidences that the Thiele equation can perfectly describe skyrmion dynamics in granular films. These findings provide insight to skyrmion motion and should be important for skyrmiontronics.

cond-mat.mes-hall↗

arXiv2014

The suppression of Curie temperature by Sr doping in diluted ferromagnetic semiconductor (La1-xSrx)(Zn1-yMny)AsO

(La1-xSrx)(Zn1-yMny)AsO is a two dimensional diluted ferromagnetic semiconductor that has the advantage of decoupled charge and spin doping. The substitution of Sr2+ for La3+ and Mn2+ for Zn2+ into the parent semiconductor LaZnAsO introduces hole carriers and spins, respectively. This advantage enables us to investigate the influence of carrier doping on the ferromagnetic ordered state through the control of Sr concentrations in (La1-xSrx)(Zn0.9Mn0.1)AsO. 10 % Sr doping results in a ferromagnetic ordering below TC ~ 30 K. Increasing Sr concentration up to 30 % heavily suppresses the Curie temperature and saturation moments. Neutron scattering measurements indicate that no structural transition occurs for (La0.9Sr0.1)(Zn0.9Mn0.1)AsO below 300 K.

cond-mat.mtrl-sci↗

arXiv2014

MuSR Investigation and Suppression of TC by overdoped Li in Diluted Ferromagnetic Semiconductor Li1+y(Zn1-xMnx)P

We use muon spin relaxation (muSR) to investigate the magnetic properties of a bulk form diluted ferromagnetic semiconductor (DFS) Li1.15(Zn0.9Mn0.1)P with T_C ~ 22 K. MuSR results confirm the gradual development of ferromagnetic ordering below T_C with a nearly 100% magnetic ordered volume. Despite its low carrier density, the relation between static internal field and Curie temperature observed for Li(Zn,Mn)P is consistent with the trend found in (Ga,Mn)As and other bulk DFSs, indicating these systems share a common mechanism for the ferromagnetic exchange interaction. Li1+y(Zn1-xMnx)P has the advantage of decoupled carrier and spin doping, where Mn2+ substitution for Zn2+ introduces spins and Li+ off-stoichiometry provides carriers. This advantage enables us to investigate the influence of overdoped Li on the ferromagnetic ordered state. Overdoping Li suppresses both T_C and saturation moments for a certain amount of spins, which indicates that more carriers are detrimental to the ferromagnetic exchange interaction, and that a delicate balance between charge and spin densities is required to achieve highest T_C.

cond-mat.mtrl-sci↗

arXiv2014

Li1.1(Zn1-xCrx)As: Cr doped I-II-V Diluted Magnetic Semiconductors in Bulk Form

We report the synthesis and characterization of bulk form diluted magnetic semiconductors I-II-V Li1.1(Zn1-xCrx)As (x = 0.03, 0.05, 0.10, 0.15)with a cubic crystal structure identical to that of III-V GaAs and II-VI zinc-blende ZnSe. With p-type carriers created by excess Li, 10% Cr substitution for Zn results in a ferromagnetic ordering below TC ~ 218 K. Li(Zn,Cr)As represents another magnetic semiconducting system with the advantage of decoupling carriers and spins, where carriers are created by adding extra Li and spins are introduced by Cr substitution for Zn.

cond-mat.str-el↗