arXiv subjects

Cong Wang

Publications and source records attributed to Cong Wang.

At least 181 records · Page 10Linked to original sources

arXiv2025

4DRadar-GS: Self-Supervised Dynamic Driving Scene Reconstruction with 4D Radar

3D reconstruction and novel view synthesis are critical for validating autonomous driving systems and training advanced perception models. Recent self-supervised methods have gained significant attention due to their cost-effectiveness and enhanced generalization in scenarios where annotated bounding boxes are unavailable. However, existing approaches, which often rely on frequency-domain decoupling or optical flow, struggle to accurately reconstruct dynamic objects due to imprecise motion estimation and weak temporal consistency, resulting in incomplete or distorted representations of dynamic scene elements. To address these challenges, we propose 4DRadar-GS, a 4D Radar-augmented self-supervised 3D reconstruction framework tailored for dynamic driving scenes. Specifically, we first present a 4D Radar-assisted Gaussian initialization scheme that leverages 4D Radar's velocity and spatial information to segment dynamic objects and recover monocular depth scale, generating accurate Gaussian point representations. In addition, we propose a Velocity-guided PointTrack (VGPT) model, which is jointly trained with the reconstruction pipeline under scene flow supervision, to track fine-grained dynamic trajectories and construct temporally consistent representations. Evaluated on the OmniHD-Scenes dataset, 4DRadar-GS achieves state-of-the-art performance in dynamic driving scene 3D reconstruction.

cs.CV↗

arXiv2025

Task-agnostic Lifelong Robot Learning with Retrieval-based Weighted Local Adaptation

A fundamental objective in intelligent robotics is to move towards lifelong learning robot that can learn and adapt to unseen scenarios over time. However, continually learning new tasks would introduce catastrophic forgetting problems due to data distribution shifts. To mitigate this, we store a subset of data from previous tasks and utilize it in two manners: leveraging experience replay to retain learned skills and applying a novel Retrieval-based Local Adaptation technique to restore relevant knowledge. Since a lifelong learning robot must operate in task-free scenarios, where task IDs and even boundaries are not available, our method performs effectively without relying on such information. We also incorporate a selective weighting mechanism to focus on the most "forgotten" skill segment, ensuring effective knowledge restoration. Experimental results across diverse manipulation tasks demonstrate that our framework provides a scalable paradigm for lifelong learning, enhancing robot performance in open-ended, task-free scenarios.

cs.RO↗

arXiv2025

IMAGGarment: Fine-Grained Garment Generation for Controllable Fashion Design

This paper presents IMAGGarment, a fine-grained garment generation (FGG) framework that enables high-fidelity garment synthesis with precise control over silhouette, color, and logo placement. Unlike existing methods that are limited to single-condition inputs, IMAGGarment addresses the challenges of multi-conditional controllability in personalized fashion design and digital apparel applications. Specifically, IMAGGarment employs a two-stage training strategy to separately model global appearance and local details, while enabling unified and controllable generation through end-to-end inference. In the first stage, we propose a global appearance model that jointly encodes silhouette and color using a mixed attention module and a color adapter. In the second stage, we present a local enhancement model with an adaptive appearance-aware module to inject user-defined logos and spatial constraints, enabling accurate placement and visual consistency. To support this task, we release GarmentBench, a large-scale dataset comprising over 180K garment samples paired with multi-level design conditions, including sketches, color references, logo placements, and textual prompts. Extensive experiments demonstrate that our method outperforms existing baselines, achieving superior structural stability, color fidelity, and local controllability performance. Code, models, and datasets are publicly available at https://github.com/muzishen/IMAGGarment.

cs.CV↗

arXiv2025

Robust Mottness and tunable interlayer magnetism in Nb3X8 (X = F, Cl, Br, I) bilayers

Kagome materials have attracted extensive attention due to their correlated properties. The breathing kagome material system Nb3X8 (X = F, Cl, Br, I) is regarded as a Mott insulator. However, studies on the influence of interlayer coupling on its magnetic and Mott properties are lacking. In this work, we investigated the effect of interlayer coupling on bilayer properties of each Nb3X8 (X = F, Cl, Br, I) compound via density functional theory (DFT) calculations, considering 24 stacking configurations per material. We found that each bilayer material is a Mott insulator. Due to the competition between interlayer Pauli repulsion and hopping, most interlayer magnetism is AFM, a small number of cases show AFM-FM degeneracy, and the magnetic ground state of 3 configurations is interlayer FM, i.e., tunable interlayer magnetism occurs. This robustness of Mott states coexisting with tunable interlayer magnetism provide novel and comprehensive analysis and insights for the research of breathing kagome Mott insulators.

cond-mat.str-el↗

arXiv2025

SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing

Creating high-fidelity and editable head avatars is a pivotal challenge in computer vision and graphics, boosting many AR/VR applications. While recent advancements have achieved photorealistic renderings and plausible animation, head editing, especially real-time appearance editing, remains challenging due to the implicit representation and entangled modeling of the geometry and global appearance. To address this, we propose Surface-Volumetric Gaussian Head Avatar (SVG-Head), a novel hybrid representation that explicitly models the geometry with 3D Gaussians bound on a FLAME mesh and leverages disentangled texture images to capture the global appearance. Technically, it contains two types of Gaussians, in which surface Gaussians explicitly model the appearance of head avatars using learnable texture images, facilitating real-time texture editing, while volumetric Gaussians enhance the reconstruction quality of non-Lambertian regions (e.g., lips and hair). To model the correspondence between 3D world and texture space, we provide a mesh-aware Gaussian UV mapping method, which leverages UV coordinates given by the FLAME mesh to obtain sharp texture images and real-time rendering speed. A hierarchical optimization strategy is further designed to pursue the optimal performance in both reconstruction quality and editing flexibility. Experiments on the NeRSemble dataset show that SVG-Head not only generates high-fidelity rendering results, but also is the first method to obtain explicit texture images for Gaussian head avatars and support real-time appearance editing.

cs.CV↗

arXiv2025

Variational free complement method with Gaussian complements

The complement functions in the free complement (FC) method are constructed by decontracting the Gaussian expansions of the Slater functions formed by the initial wavefunction and the $g$ functions. The helium ground state is used to demonstrate the accuracy.

physics.chem-ph↗

arXiv2025

Quantifying Conversation Drift in MCP via Latent Polytope

The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. However, its non-isolated execution context introduces critical security and privacy risks. In particular, adversarially crafted content can induce tool poisoning or indirect prompt injection, leading to conversation hijacking, misinformation propagation, or data exfiltration. Existing defenses, such as rule-based filters or LLM-driven detection, remain inadequate due to their reliance on static signatures, computational inefficiency, and inability to quantify conversational hijacking. To address these limitations, we propose SecMCP, a secure framework that detects and quantifies conversation drift, deviations in latent space trajectories induced by adversarial external knowledge. By modeling LLM activation vectors within a latent polytope space, SecMCP identifies anomalous shifts in conversational dynamics, enabling proactive detection of hijacking, misleading, and data exfiltration. We evaluate SecMCP on three state-of-the-art LLMs (Llama3, Vicuna, Mistral) across benchmark datasets (MS MARCO, HotpotQA, FinQA), demonstrating robust detection with AUROC scores exceeding 0.915 while maintaining system usability. Our contributions include a systematic categorization of MCP security threats, a novel latent polytope-based methodology for quantifying conversation drift, and empirical validation of SecMCP's efficacy.

cs.CL↗

arXiv2025

Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights

Developing reliable defenses against patch attacks on object detectors has attracted increasing interest. However, we identify that existing defense evaluations lack a unified and comprehensive framework, resulting in inconsistent and incomplete assessments of current methods. To address this issue, we revisit 11 representative defenses and present the first patch defense benchmark, involving 2 attack goals, 13 patch attacks, 11 object detectors, and 4 diverse metrics. This leads to the large-scale adversarial patch dataset with 94 types of patches and 94,000 images. Our comprehensive analyses reveal new insights: (1) The difficulty in defending against naturalistic patches lies in the data distribution, rather than the commonly believed high frequencies. Our new dataset with diverse patch distributions can be used to improve existing defenses by 15.09% AP@0.5. (2) The average precision of the attacked object, rather than the commonly pursued patch detection accuracy, shows high consistency with defense performance. (3) Adaptive attacks can substantially bypass existing defenses, and defenses with complex/stochastic models or universal patch properties are relatively robust. We hope that our analyses will serve as guidance on properly evaluating patch attacks/defenses and advancing their design. Code and dataset are available at https://github.com/Gandolfczjh/APDE, where we will keep integrating new attacks/defenses.

cs.CV↗

arXiv2025

D3: Training-Free AI-Generated Video Detection Using Second-Order Features

The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the dissemination of synthetic content. However, existing detection methodologies remain limited by their insufficient exploration of temporal artifacts in synthetic videos. To bridge this gap, we establish a theoretical framework through second-order dynamical analysis under Newtonian mechanics, subsequently extending the Second-order Central Difference features tailored for temporal artifact detection. Building on this theoretical foundation, we reveal a fundamental divergence in second-order feature distributions between real and AI-generated videos. Concretely, we propose Detection by Difference of Differences (D3), a novel training-free detection method that leverages the above second-order temporal discrepancies. We validate the superiority of our D3 on 4 open-source datasets (Gen-Video, VideoPhy, EvalCrafter, VidProM), 40 subsets in total. For example, on GenVideo, D3 outperforms the previous best method by 10.39% (absolute) mean Average Precision. Additional experiments on time cost and post-processing operations demonstrate D3's exceptional computational efficiency and strong robust performance. Our code is available at https://github.com/Zig-HS/D3.

cs.CV↗

arXiv2025

The Dark Side of Upgrades: Uncovering Security Risks in Smart Contract Upgrades

Smart contract upgrades are increasingly common due to their flexibility in modifying deployed contracts, such as fixing bugs or adding new functionalities. Meanwhile, upgrades compromise the immutability of contracts, introducing significant security concerns. While existing research has explored the security impacts of contract upgrades, these studies are limited in collection of upgrade behaviors and identification of insecurities. To address these limitations, we conduct a comprehensive study on the insecurities of upgrade behaviors. First, we build a dataset containing 83,085 upgraded contracts and 20,902 upgrade chains. To our knowledge, this is the first large-scale dataset about upgrade behaviors, revealing their diversity and exposing gaps in public disclosure. Next, we develop a taxonomy of insecurities based on 37 real-world security incidents, categorizing eight types of upgrade risks and providing the first complete view of upgrade-related insecurities. Finally, we survey public awareness of these risks and existing mitigations. Our findings show that four types of security risks are overlooked by the public and lack mitigation measures. We detect these upgrade risks through a preliminary study, identifying 31,407 related issues - a finding that raises significant concerns.

cs.CR↗

arXiv2025

Revisiting the Fermion Sign Problem from the Structure of Lee-Yang Zeros. I. The Form of Partition Function for Indistinguishable Particles and Its Zeros at 0~K

To simulate indistinguishable particles, recent studies of path-integral molecular dynamics formulated their partition function $Z$ as a recurrence relation involving a variable $ξ$, with $ξ=1$(-1) for bosons (fermions). Inspired by Lee-Yang phase transition theory, we extend $ξ$ into the complex plane and reformulate $Z$ as a polynomial in $ξ$. By analyzing the distribution of the partition function zeros, we gain insights into the analytical properties of indistinguishable particles, particularly regarding the fermion sign problem (FSP). We found that at 0~K, the partition function zeros for $N$-particles are located at $ξ=-1$, $-1/2$, $-1/3$, $\cdots$, $-1/(N-1)$. This distribution disrupts the analytic continuation of thermodynamic quantities, expressed as functions of $ξ$ and typically performed along $ξ=1\to-1$, whenever the paths intersect these zeros. Moreover, we highlight the zero at $ξ= -1$, which induces an extra term in the free energy of the fermionic systems compared to ones at other $ξ=e^{iθ}$ values. If a path connects this zero to a bosonic system with identical potential energies, it brings a transition resembling a phase transition. These findings provide a fresh perspective on the successes and challenges of emerging FSP studies based on analytic continuation techniques.

cond-mat.stat-mech↗

arXiv2025

H$_2$O$_2$RAM: A High-Performance Hierarchical Doubly Oblivious RAM

The combination of Oblivious RAM (ORAM) with Trusted Execution Environments (TEE) has found numerous real-world applications due to their complementary nature. TEEs alleviate the performance bottlenecks of ORAM, such as network bandwidth and roundtrip latency, and ORAM provides general-purpose protection for TEE applications against attacks exploiting memory access patterns. The defining property of this combination, which sets it apart from traditional ORAM designs, is its ability to ensure that memory accesses, both inside and outside of TEEs, are made oblivious, thus termed doubly oblivious RAM (O$_2$RAM). Efforts to develop O$_2$RAM with enhanced performance are ongoing. In this work, we propose H$_2$O$_2$RAM, a high-performance doubly oblivious RAM construction. The distinguishing feature of our approach, compared to the existing tree-based doubly oblivious designs, is its first adoption of the hierarchical framework that enjoys inherently better data locality and parallelization. While the latest hierarchical solution, FutORAMa, achieves concrete efficiency in the classic client-server model by leveraging a relaxed assumption of sublinear-sized client-side private memory, adapting it to our scenario poses challenges due to the conflict between this relaxed assumption and our doubly oblivious requirement. To this end, we introduce several new efficient oblivious components to build a high-performance hierarchical O$_2$RAM (H$_2$O$_2$RAM). We implement our design and evaluate it on various scenarios. The results indicate that H$_2$O$_2$RAM reduces execution time by up to $\sim 10^3$ times and saves memory usage by $5\sim44$ times compared to state-of-the-art solutions.

cs.CR↗

arXiv2025

ReviewInstruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models

The effectiveness of large language models (LLMs) in conversational AI is hindered by their reliance on single-turn supervised fine-tuning (SFT) data, which limits contextual coherence in multi-turn dialogues. Existing methods for generating multi-turn dialogue data struggle to ensure both diversity and quality in instructions. To address this, we propose Review-Instruct, a novel framework that synthesizes multi-turn conversations through an iterative "Ask-Respond-Review" process involving three agent roles: a Candidate, multiple Reviewers, and a Chairman. The framework iteratively refines instructions by incorporating Reviewer feedback, enhancing dialogue diversity and difficulty. We construct a multi-turn dataset using the Alpaca dataset and fine-tune the LLaMA2-13B model. Evaluations on MT-Bench, MMLU-Pro, and Auto-Arena demonstrate significant improvements, achieving absolute gains of 2.9\% on MMLU-Pro and 2\% on MT-Bench compared to prior state-of-the-art models based on LLaMA2-13B. Ablation studies confirm the critical role of the Review stage and the use of multiple Reviewers in boosting instruction diversity and difficulty. Our work highlights the potential of review-driven, multi-agent frameworks for generating high-quality conversational data at scale.

cs.CL↗

arXiv2025

Tunable altermagnetism via inter-chain engineering in parallelassembled atomic chains

Altermagnetism has recently drawn considerable attention in three- and twodimensional materials. Here, we extend this concept to quasi-one-dimensional (Q1D) monolayers assembled from single-atomic magnetic chains. Through systematically examining nine types of structures, two stacking orders, and intra-/inter-chain magnetic couplings, we identify four out of thirty promising structural prototypes for hosting altermagnetism, which yields 192 potential monolayer materials. We further confirm eight thermodynamically stable Q1D monolayers via high-throughput calculations. Using symmetry analysis and first-principles calculations, we find that the existence of altermagnetism is determined by the type of inter-chain magnetic coupling and predict three intrinsic altermagnets,$CrBr_3$,$VBr_3$,$MnBr_3$,due to their ferromagnetic inter-chain couplings and five extrinsic ones,$CrF_3$,$CrCl_3$,$CrI_3$,$FeCl_3$and $CoTe_3$, ascribed to their neglectable or antiferromagnetic inter-chain couplings. Moreover, the inter-chain magnetic coupling here is highly tunable by manipulating the inter-chain spacing, leading to experimentally feasible transitions between altermagnetic and nodal-line semiconducting states. In addition, applying external electric fields can further modulate the spin splitting. Our findings establish a highly tunable family of Q1D altermagnets, offering fundamental insights into the intricate relationship between geometry, electronic structure, and magnetism.These discoveries hold significant promises for experimental realization and future spintronic applications.

cond-mat.mtrl-sci↗

arXiv2025

Effective Explanations for Belief-Desire-Intention Robots: When and What to Explain

When robots perform complex and context-dependent tasks in our daily lives, deviations from expectations can confuse users. Explanations of the robot's reasoning process can help users to understand the robot intentions. However, when to provide explanations and what they contain are important to avoid user annoyance. We have investigated user preferences for explanation demand and content for a robot that helps with daily cleaning tasks in a kitchen. Our results show that users want explanations in surprising situations and prefer concise explanations that clearly state the intention behind the confusing action and the contextual factors that were relevant to this decision. Based on these findings, we propose two algorithms to identify surprising actions and to construct effective explanations for Belief-Desire-Intention (BDI) robots. Our algorithms can be easily integrated in the BDI reasoning process and pave the way for better human-robot interaction with context- and user-specific explanations.

cs.RO↗

arXiv2025

SoK: Stablecoin Designs, Risks, and the Stablecoin LEGO

Stablecoins have become significant assets in modern finance, with a market capitalization exceeding USD 246 billion (May 2025). Yet, despite their systemic importance, a comprehensive and risk-oriented understanding of crucial aspects like their design trade-offs, security dynamics, and interdependent failure pathways often remains underdeveloped. This SoK confronts this gap through a large-scale analysis of 157 research studies, 95 active stablecoins, and 44 major security incidents. Our analysis establishes four pivotal insights: 1) stability is best understood not an inherent property but an emergent, fragile state reliant on the interplay between market confidence and continuous liquidity; 2) stablecoin designs demonstrate trade-offs in risk specialization instead of mitigation; 3) the widespread integration of yield mechanisms imposes a "dual mandate" that creates a systemic tension between the core mission of stability and the high-risk financial engineering required for competitive returns; and 4) major security incidents act as acute "evolutionary pressures", forging resilience by stress-testing designs and aggressively redefining the security frontier. We introduce the Stablecoin LEGO framework, a quantitative methodology mapping historical failures to current designs. Its application reveals that a lower assessed risk strongly correlates with integrating lessons from past incidents. We hope this provides a systematic foundation for building, evaluating, and regulating more resilient stablecoins.

cs.CR↗

arXiv2025

Physics-Informed Deep Learning Model for Line-integral Diagnostics Across Fusion Devices

Rapid reconstruction of 2D plasma profiles from line-integral measurements is important in nuclear fusion. This paper introduces a physics-informed model architecture called Onion, that can enhance the performance of models and be adapted to various backbone networks. The model under Onion incorporates physical information by a multiplication process and applies the physics-informed loss function according to the principle of line integration. Prediction results demonstrate that the additional input of physical information improves the deep learning model's ability, leading to a reduction in the average relative error E_1 between the reconstruction profiles and the target profiles by approximately 0.84x10^(-2) on synthetic datasets and about 0.06x10^(-2) on experimental datasets. Furthermore, the implementation of the Softplus activation function in the final two fully connected layers improves model performance. This enhancement results in a reduction in the E_1 by approximately 1.06x10^(-2) on synthetic datasets and about 0.11x10^(-2) on experimental datasets. The incorporation of the physics-informed loss function has been shown to correct the model's predictions, bringing the back-projections closer to the actual inputs and reducing the errors associated with inversion algorithms. Besides, we have developed a synthetic data model to generate customized line-integral diagnostic datasets and have also collected soft x-ray diagnostic datasets from EAST and HL-2A. This study achieves reductions in reconstruction errors, and accelerates the development of surrogate models in fusion research.

cs.LG↗

arXiv2025

Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples

Adversarial detection protects models from adversarial attacks by refusing suspicious test samples. However, current detection methods often suffer from weak generalization: their effectiveness tends to degrade significantly when applied to adversarially trained models rather than naturally trained ones, and they generally struggle to achieve consistent effectiveness across both white-box and black-box attack settings. In this work, we observe that an auxiliary model, differing from the primary model in training strategy or model architecture, tends to assign low confidence to the primary model's predictions on adversarial examples (AEs), while preserving high confidence on normal examples (NEs). Based on this discovery, we propose Prediction Inconsistency Detector (PID), a lightweight and generalizable detection framework to distinguish AEs from NEs by capturing the prediction inconsistency between the primal and auxiliary models. PID is compatible with both naturally and adversarially trained primal models and outperforms four detection methods across 3 white-box, 3 black-box, and 1 mixed adversarial attacks. Specifically, PID achieves average AUC scores of 99.29\% and 99.30\% on CIFAR-10 when the primal model is naturally and adversarially trained, respectively, and 98.31% and 96.81% on ImageNet under the same conditions, outperforming existing SOTAs by 4.70%$\sim$25.46%.

cs.CR↗