Zhi Zeng

Zhi Zeng, Yifei Yang, Jiaying Wu et al.

The rise of micro-videos has reshaped how misinformation spreads, amplifying its speed, reach, and impact on public trust. Existing benchmarks typically focus on a single deception type, overlooking the diversity of real-world cases that involve multimodal manipulation, AI-generated content, cognitive bias, and out-of-context reuse. Meanwhile, most detection models lack fine-grained attribution, limiting interpretability and practical utility. To address these gaps, we introduce WildFakeBench, a large-scale benchmark of over 10,000 real-world micro-videos covering diverse misinformation types and sources, each annotated with expert-defined attribution labels. Building on this foundation, we develop FakeAgent, a Delphi-inspired multi-agent reasoning framework that integrates multimodal understanding with external evidence for attribution-grounded analysis. FakeAgent jointly analyzes content and retrieved evidence to identify manipulation, recognize cognitive and AI-generated patterns, and detect out-of-context misinformation. Extensive experiments show that FakeAgent consistently outperforms existing MLLMs across all misinformation types, while WildFakeBench provides a realistic and challenging testbed for advancing explainable micro-video misinformation detection. Data and code are available at: https://github.com/Aiyistan/FakeAgent.

Nan Gao, Zeyu Zhao, Zhi Zeng et al.

Gesture synthesis has gained significant attention as a critical research field, aiming to produce contextually appropriate and natural gestures corresponding to speech or textual input. Although deep learning-based approaches have achieved remarkable progress, they often overlook the rich semantic information present in the text, leading to less expressive and meaningful gestures. In this letter, we propose GesGPT, a novel approach to gesture generation that leverages the semantic analysis capabilities of large language models , such as ChatGPT. By capitalizing on the strengths of LLMs for text analysis, we adopt a controlled approach to generate and integrate professional gestures and base gestures through a text parsing script, resulting in diverse and meaningful gestures. Firstly, our approach involves the development of prompt principles that transform gesture generation into an intention classification problem using ChatGPT. We also conduct further analysis on emphasis words and semantic words to aid in gesture generation. Subsequently, we construct a specialized gesture lexicon with multiple semantic annotations, decoupling the synthesis of gestures into professional gestures and base gestures. Finally, we merge the professional gestures with base gestures. Experimental results demonstrate that GesGPT effectively generates contextually appropriate and expressive gestures.

Zhi Zeng, Ting Wang

The Copula is widely used to describe the relationship between the marginal distribution and joint distribution of random variables. The estimation of high-dimensional Copula is difficult, and most existing solutions rely either on simplified assumptions or on complicating recursive decompositions. Therefore, people still hope to obtain a generic Copula estimation method with both universality and simplicity. To reach this goal, a novel neural network-based method (named Neural Copula) is proposed in this paper. In this method, a hierarchical unsupervised neural network is constructed to estimate the marginal distribution function and the Copula function by solving differential equations. In the training program, various constraints are imposed on both the neural network and its derivatives. The Copula estimated by the proposed method is smooth and has an analytic expression. The effectiveness of the proposed method is evaluated on both real-world datasets and complex numerical simulations. Experimental results show that Neural Copula's fitting quality for complex distributions is much better than classical methods. The relevant code for the experiments is available on GitHub. (We encourage the reader to run the program for a better understanding of the proposed method).

Herun Wan, Jiaying Wu, Minnan Luo et al.

Misinformation detection models often rely on superficial cues (i.e., \emph{shortcuts}) that correlate with misinformation in training data but fail to generalize to the diverse and evolving nature of real-world misinformation. This issue is exacerbated by large language models (LLMs), which can easily generate convincing misinformation through simple prompts. We introduce TruthOverTricks, a unified evaluation paradigm for measuring shortcut learning in misinformation detection. TruthOverTricks categorizes shortcut behaviors into intrinsic shortcut induction and extrinsic shortcut injection, and evaluates seven representative detectors across 14 popular benchmarks, along with two new factual misinformation datasets, NQ-Misinfo and Streaming-Misinfo. Empirical results reveal that existing detectors suffer severe performance degradation when exposed to both naturally occurring and adversarially crafted shortcuts. To address this, we propose SMF, an LLM-augmented data augmentation framework that mitigates shortcut reliance through paraphrasing, factual summarization, and sentiment normalization. SMF consistently enhances robustness across 16 benchmarks, encouraging models to rely on deeper semantic understanding rather than shortcut cues. To promote the development of misinformation detectors, we have published the resources publicly at https://github.com/whr000001/TruthOverTricks.

Herun Wan, Jiaying Wu, Minnan Luo et al.

To reliably assist human decision-making, LLMs must maintain factual internal beliefs against misleading injections. While current models resist explicit misinformation, we uncover a fundamental vulnerability to sophisticated, hard-to-falsify evidence. To systematically probe this weakness, we introduce MisBelief, a framework that generates misleading evidence via collaborative, multi-round interactions among multi-role LLMs. This process mimics subtle, defeasible reasoning and progressive refinement to create logically persuasive yet factually deceptive claims. Using MisBelief, we generate 4,800 instances across three difficulty levels to evaluate 7 representative LLMs. Results indicate that while models are robust to direct misinformation, they are highly sensitive to this refined evidence: belief scores in falsehoods increase by an average of 93.0\%, fundamentally compromising downstream recommendations. To address this, we propose Deceptive Intent Shielding (DIS), a governance mechanism that provides an early warning signal by inferring the deceptive intent behind evidence. Empirical results demonstrate that DIS consistently mitigates belief shifts and promotes more cautious evidence evaluation.

Fei Ge, Ying Huang, Jie Liu et al.

Existing deep image watermarking methods follow a fixed embedding-distortion-extraction pipeline, where the embedder and extractor are weakly coupled through a final loss and optimized in isolation. This design lacks explicit collaboration, leaving no structured mechanism for the embedder to incorporate decoding-aware cues or for the extractor to guide embedding during training. To address this architectural limitation, we rethink deep image watermarking by reformulating embedding and extraction as explicitly collaborative components. To realize this reformulation, we introduce a Collaborative Interaction Mechanism (CIM) that establishes direct, bidirectional communication between the embedder and extractor, enabling a mutual-teacher training paradigm and coordinated optimization. Built upon this explicitly collaborative architecture, we further propose an Adaptive Feature Modulation Module (AFMM) to support effective interaction. AFMM enables content-aware feature regulation by decoupling modulation structure and strength, guiding watermark embedding toward stable image features while suppressing host interference during extraction. Under CIM, the AFMMs on both sides form a closed-loop collaboration that aligns embedding behavior with extraction objectives. This architecture-level redesign changes how robustness is learned in watermarking systems. Rather than relying on exhaustive distortion simulation, robustness emerges from coordinated representation learning between embedding and extraction. Experiments on real-world and AI-generated datasets demonstrate that the proposed method consistently outperforms state-of-the-art approaches in watermark extraction accuracy while maintaining high perceptual quality, showing strong robustness and generalization.

Deqing Yang, Yingying Liu, Qicong Wang et al.

Image restoration under adverse conditions, such as underwater, haze or fog, and low-light environments, remains a highly challenging problem due to complex physical degradations and severe information loss. Existing datasets are predominantly limited to a single degradation type or heavily rely on synthetic data without stereo consistency, inherently restricting their applicability in real-world scenarios. To address this, we introduce M3D-Stereo, a stereo dataset with 7904 high-resolution image pairs for image restoration research acquired in multiple media with multiple controlled degradation levels. It encompasses four degradation scenarios: underwater scatter, haze/fog, underwater low-light, and haze low-light. Each scenario forms a subset, and is divided into six levels of progressive degradation, allowing fine-grained evaluations of restoration methods with increasing severity of degradation. Collected via a laboratory setup, the dataset provides aligned stereo image pairs along with their pixel-wise consistent clear ground truths. Two restoration tasks, single-level and mixed-level degradation, were performed to verify its validity. M3D-Stereo establishes a better controlled and more realistic benchmark to evaluate image restoration and stereo matching methods in complex degradation environments. It is made public under LGPLv3 license.

Di Zhang, Zhangpeng Gong, Xiaobo Pang et al.

Foundation models have recently achieved impressive success in computational pathology, demonstrating strong generalization across diverse histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of pathological regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they often fail to capture the coherent tissue architecture beyond isolated patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that automatically partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the most representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall.

Hao Guo, Zihan Ma, Zhi Zeng et al.

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset \amg, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model \our to achieve multimodal fake news detection and attribution. Experimental results demonstrate that \amg is a challenging dataset, and its attribution setting opens up new avenues for future research.

Herun Wan, Jiaying Wu, Minnan Luo et al.

Generating textual rationales from large vision-language models (LVLMs) to support trainable multimodal misinformation detectors has emerged as a promising paradigm. However, its effectiveness is fundamentally limited by three core challenges: (i) insufficient diversity in generated rationales, (ii) factual inaccuracies due to hallucinations, and (iii) irrelevant or conflicting content that introduces noise. We introduce DiFaR, a detector-agnostic framework that produces diverse, factual, and relevant rationales to enhance misinformation detection. DiFaR employs five chain-of-thought prompts to elicit varied reasoning traces from LVLMs and incorporates a lightweight post-hoc filtering module to select rationale sentences based on sentence-level factuality and relevance scores. Extensive experiments on four popular benchmarks demonstrate that DiFaR outperforms four baseline categories by up to 5.9% and boosts existing detectors by as much as 8.7%. Both automatic metrics and human evaluations confirm that DiFaR significantly improves rationale quality across all three dimensions.

Nan Gao, Jia Li, Huaibo Huang et al.

Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of degradation patterns. Current methods have low generalization across photorealistic and heterogeneous domains. In this paper, we propose a Diffusion-Information-Diffusion (DID) framework to tackle diffusion manifold hallucination correction (DiffMAC), which achieves high-generalization face restoration in diverse degraded scenes and heterogeneous domains. Specifically, the first diffusion stage aligns the restored face with spatial feature embedding of the low-quality face based on AdaIN, which synthesizes degradation-removal results but with uncontrollable artifacts for some hard cases. Based on Stage I, Stage II considers information compression using manifold information bottleneck (MIB) and finetunes the first diffusion model to improve facial fidelity. DiffMAC effectively fights against blind degradation patterns and synthesizes high-quality faces with attribute and identity consistencies. Experimental results demonstrate the superiority of DiffMAC over state-of-the-art methods, with a high degree of generalization in real-world and heterogeneous settings. The source code and models will be public.

Yahui Li, Zhi Zeng, Liming Pang et al.

Modeling animatable human avatars from monocular or multi-view videos has been widely studied, with recent approaches leveraging neural radiance fields (NeRFs) or 3D Gaussian Splatting (3DGS) achieving impressive results in novel-view and novel-pose synthesis. However, existing methods often struggle to accurately capture the dynamics of loose clothing, as they primarily rely on global pose conditioning or static per-frame representations, leading to oversmoothing and temporal inconsistencies in non-rigid regions. To address this, We propose RealityAvatar, an efficient framework for high-fidelity digital human modeling, specifically targeting loosely dressed avatars. Our method leverages 3D Gaussian Splatting to capture complex clothing deformations and motion dynamics while ensuring geometric consistency. By incorporating a motion trend module and a latentbone encoder, we explicitly model pose-dependent deformations and temporal variations in clothing behavior. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach in capturing fine-grained clothing deformations and motion-driven shape variations. Our method significantly enhances structural fidelity and perceptual quality in dynamic human reconstruction, particularly in non-rigid regions, while achieving better consistency across temporal frames.

Pengpeng Shi, Zhi Zeng, Tianshou Liang

Big-data-based artificial intelligence (AI) supports profound evolution in almost all of science and technology. However, modeling and forecasting multi-physical systems remain a challenge due to unavoidable data scarcity and noise. Improving the generalization ability of neural networks by "teaching" domain knowledge and developing a new generation of models combined with the physical laws have become promising areas of machine learning research. Different from "deep" fully-connected neural networks embedded with physical information (PINN), a novel shallow framework named physics-informed convolutional network (PICN) is recommended from a CNN perspective, in which the physical field is generated by a deconvolution layer and a single convolution layer. The difference fields forming the physical operator are constructed using the pre-trained shallow convolution layer. An efficient linear interpolation network calculates the loss function involving boundary conditions and the physical constraints in irregular geometry domains. The effectiveness of the current development is illustrated through some numerical cases involving the solving (and estimation) of nonlinear physical operator equations and recovering physical information from noisy observations. Its potential advantage in approximating physical fields with multi-frequency components indicates that PICN may become an alternative neural network solver in physics-informed machine learning.

Shang Li, Guixuan Zhang, Zhengxiong Luo et al.

Image downscaling and upscaling are two basic rescaling operations. Once the image is downscaled, it is difficult to be reconstructed via upscaling due to the loss of information. To make these two processes more compatible and improve the reconstruction performance, some efforts model them as a joint encoding-decoding task, with the constraint that the downscaled (i.e. encoded) low-resolution (LR) image must preserve the original visual appearance. To implement this constraint, most methods guide the downscaling module by supervising it with the bicubically downscaled LR version of the original high-resolution (HR) image. However, this bicubic LR guidance may be suboptimal for the subsequent upscaling (i.e. decoding) and restrict the final reconstruction performance. In this paper, instead of directly applying the LR guidance, we propose an additional invertible flow guidance module (FGM), which can transform the downscaled representation to the visually plausible image during downscaling and transform it back during upscaling. Benefiting from the invertibility of FGM, the downscaled representation could get rid of the LR guidance and would not disturb the downscaling-upscaling process. It allows us to remove the restrictions on the downscaling module and optimize the downscaling and upscaling modules in an end-to-end manner. In this way, these two modules could cooperate to maximize the HR reconstruction performance. Extensive experiments demonstrate that the proposed method can achieve state-of-the-art (SotA) performance on both downscaled and reconstructed images.

Shang Li, Guixuan Zhang, Zhengxiong Luo et al.

Most deep learning-based super-resolution (SR) methods are not image-specific: 1) They are trained on samples synthesized by predefined degradations (e.g. bicubic downsampling), regardless of the domain gap between training and testing data. 2) During testing, they super-resolve all images by the same set of model weights, ignoring the degradation variety. As a result, most previous methods may suffer a performance drop when the degradations of test images are unknown and various (i.e. the case of blind SR). To address these issues, we propose an online SR (ONSR) method. It does not rely on predefined degradations and allows the model weights to be updated according to the degradation of the test image. Specifically, ONSR consists of two branches, namely internal branch (IB) and external branch (EB). IB could learn the specific degradation of the given test LR image, and EB could learn to super resolve images degraded by the learned degradation. In this way, ONSR could customize a specific model for each test image, and thus get more robust to various degradations. Extensive experiments on both synthesized and real-world images show that ONSR can generate more visually favorable SR results and achieve state-of-the-art performance in blind SR.

Zhi Zeng, Pengpeng Shi, Fulei Ma et al.

A neural network is essentially a high-dimensional complex mapping model by adjusting network weights for feature fitting. However, the spectral bias in network training leads to unbearable training epochs for fitting the high-frequency components in broadband signals. To improve the fitting efficiency of high-frequency components, the PhaseDNN was proposed recently by combining complex frequency band extraction and frequency shift techniques [Cai et al. SIAM J. SCI. COMPUT. 42, A3285 (2020)]. Our paper is devoted to an alternative candidate for fitting complex signals with high-frequency components. Here, a parallel frequency function-deep neural network (PFF-DNN) is proposed to suppress computational overhead while ensuring fitting accuracy by utilizing fast Fourier analysis of broadband signals and the spectral bias nature of neural networks. The effectiveness and efficiency of the proposed PFF-DNN method are verified based on detailed numerical experiments for six typical broadband signals.

Wenhan Dai, Zhi Zeng, Daowei Dou et al.

The monitoring of Cs-137 in seawater using scintillation detector relies on the spectrum analysis method to extract the Cs-137 concentration. And when in poor statistic situation, the calculation result of the traditional net peak area (NPA) method has a large uncertainty. We present a machine learning based method to better analyze the gamma-ray spectrum with low Cs-137 concentration. We apply multilayer perceptron (MLP) to analyze the 662 keV full energy peak of Cs-137 in the seawater spectrum. And the MLP can be trained with a few measured background spectrums by combining the simulated Cs-137 signal with measured background spectrums. Thus, it can save the time of preparing and measuring the standard samples for generating the training dataset. To validate the MLP-based method, we use Geant4 and background gamma-ray spectrums measured by a seaborne monitoring device to generate an independent test dataset to test the result by our method and the traditional NPA method. We find that the MLP-based method achieves a root mean squared error of 0.159, 2.3 times lower than that of the traditional net peak area method, indicating the MLP-based method improves the precision of Cs-137 concentration calculation