Unveiling Hidden Vulnerabilities in Digital Human Generation via Adversarial Attacks

Expressive human pose and shape estimation (EHPS) is crucial for digital human generation, especially in applications like live streaming. While existing research primarily focuses on reducing estimation errors, it largely neglects robustness and security aspects, leaving these systems vulnerable to adversarial attacks. To address this significant challenge, we propose the \textbf{Tangible Attack (TBA)}, a novel framework designed to generate adversarial examples capable of effectively compromising any digital human generation model. Our approach introduces a \textbf{Dual Heterogeneous Noise Generator (DHNG)}, which leverages Variational Autoencoders (VAE) and ControlNet to produce diverse, targeted noise tailored to the original image features. Additionally, we design a custom \textbf{adversarial loss function} to optimize the noise, ensuring both high controllability and potent disruption. By iteratively refining the adversarial sample through multi-gradient signals from both the noise and the state-of-the-art EHPS model, TBA substantially improves the effectiveness of adversarial attacks. Extensive experiments demonstrate TBA's superiority, achieving a remarkable 41.0\% increase in estimation error, with an average improvement of approximately 17.0\%. These findings expose significant security vulnerabilities in current EHPS models and highlight the need for stronger defenses in digital human generation systems.

Structure-guided Diffusion Transformer for Low-Light Image Enhancement

While the diffusion transformer (DiT) has become a focal point of interest in recent years, its application in low-light image enhancement remains a blank area for exploration. Current methods recover the details from low-light images while inevitably amplifying the noise in images, resulting in poor visual quality. In this paper, we firstly introduce DiT into the low-light enhancement task and design a novel Structure-guided Diffusion Transformer based Low-light image enhancement (SDTL) framework. We compress the feature through wavelet transform to improve the inference efficiency of the model and capture the multi-directional frequency band. Then we propose a Structure Enhancement Module (SEM) that uses structural prior to enhance the texture and leverages an adaptive fusion strategy to achieve more accurate enhancement effect. In Addition, we propose a Structure-guided Attention Block (SAB) to pay more attention to texture-riched tokens and avoid interference from noisy areas in noise prediction. Extensive qualitative and quantitative experiments demonstrate that our method achieves SOTA performance on several popular datasets, validating the effectiveness of SDTL in improving image quality and the potential of DiT in low-light enhancement tasks.

Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streaming

Adaptive video streaming systems are designed to optimize Quality of Experience (QoE) and, in turn, enhance user satisfaction. However, differences in user profiles and video content lead to different weights for QoE factors, resulting in user-specific QoE functions and, thus, varying optimization objectives. This variability poses significant challenges for neural networks, as they often struggle to generalize under evolving targets - a phenomenon known as plasticity loss that prevents conventional models from adapting effectively to changing optimization objectives. To address this limitation, we propose the Plasticity-Aware Mixture of Experts (PA-MoE), a novel learning framework that dynamically modulates network plasticity by balancing memory retention with selective forgetting. In particular, PA-MoE leverages noise injection to promote the selective forgetting of outdated knowledge, thereby endowing neural networks with enhanced adaptive capabilities. In addition, we present a rigorous theoretical analysis of PA-MoE by deriving a regret bound that quantifies its learning performance. Experimental evaluations demonstrate that PA-MoE achieves a 45.5% improvement in QoE over competitive baselines in dynamic streaming environments. Further analysis reveals that the model effectively mitigates plasticity loss by optimizing neuron utilization. Finally, a parameter sensitivity study is performed by injecting varying levels of noise, and the results align closely with our theoretical predictions.

COSINT-Agent: A Knowledge-Driven Multimodal Agent for Chinese Open Source Intelligence

Open Source Intelligence (OSINT) requires the integration and reasoning of diverse multimodal data, presenting significant challenges in deriving actionable insights. Traditional approaches, including multimodal large language models (MLLMs), often struggle to infer complex contextual relationships or deliver comprehensive intelligence from unstructured data sources. In this paper, we introduce COSINT-Agent, a knowledge-driven multimodal agent tailored to address the challenges of OSINT in the Chinese domain. COSINT-Agent seamlessly integrates the perceptual capabilities of fine-tuned MLLMs with the structured reasoning power of the Entity-Event-Scene Knowledge Graph (EES-KG). Central to COSINT-Agent is the innovative EES-Match framework, which bridges COSINT-MLLM and EES-KG, enabling systematic extraction, reasoning, and contextualization of multimodal insights. This integration facilitates precise entity recognition, event interpretation, and context retrieval, effectively transforming raw multimodal data into actionable intelligence. Extensive experiments validate the superior performance of COSINT-Agent across core OSINT tasks, including entity recognition, EES generation, and context matching. These results underscore its potential as a robust and scalable solution for advancing automated multimodal reasoning and enhancing the effectiveness of OSINT methodologies.

MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image

Reconstructing 3D shapes from a single image plays an important role in computer vision. Many methods have been proposed and achieve impressive performance. However, existing methods mainly focus on extracting semantic information from images and then simply concatenating it with 3D point clouds without further exploring the concatenated semantics. As a result, these entangled semantic features significantly hinder the reconstruction performance. In this paper, we propose a novel single-image 3D reconstruction method called Mining Effective Semantic Cues for 3D Reconstruction from a Single Image (MESC-3D), which can actively mine effective semantic cues from entangled features. Specifically, we design an Effective Semantic Mining Module to establish connections between point clouds and image semantic attributes, enabling the point clouds to autonomously select the necessary information. Furthermore, to address the potential insufficiencies in semantic information from a single image, such as occlusions, inspired by the human ability to represent 3D objects using prior knowledge drawn from daily experiences, we introduce a 3D Semantic Prior Learning Module. This module incorporates semantic understanding of spatial structures, enabling the model to interpret and reconstruct 3D objects with greater accuracy and realism, closely mirroring human perception of complex 3D environments. Extensive evaluations show that our method achieves significant improvements in reconstruction quality and robustness compared to prior works. Additionally, further experiments validate the strong generalization capabilities and excels in zero-shot preformance on unseen classes. Code is available at https://github.com/QINGQINGLE/MESC-3D.

Controllable Emotion Generation with Emotion Vectors

In recent years, technologies based on large-scale language models (LLMs) have made remarkable progress in many fields, especially in customer service, content creation, and embodied intelligence, showing broad application potential. However, The LLM's ability to express emotions with proper tone, timing, and in both direct and indirect forms is still insufficient but significant. Few works have studied on how to build the controlable emotional expression capability of LLMs. In this work, we propose a method for emotion expression output by LLMs, which is universal, highly flexible, and well controllable proved with the extensive experiments and verifications. This method has broad application prospects in fields involving emotions output by LLMs, such as intelligent customer service, literary creation, and home companion robots. The extensive experiments on various LLMs with different model-scales and architectures prove the versatility and the effectiveness of the proposed method.

C2PD: Continuity-Constrained Pixelwise Deformation for Guided Depth Super-Resolution

Guided depth super-resolution (GDSR) has demonstrated impressive performance across a wide range of domains, with numerous methods being proposed. However, existing methods often treat depth maps as images, where shading values are computed discretely, making them struggle to effectively restore the continuity inherent in the depth map. In this paper, we propose a novel approach that maximizes the utilization of spatial characteristics in depth, coupled with human abstract perception of real-world substance, by transforming the GDSR issue into deformation of a roughcast with ideal plasticity, which can be deformed by force like a continuous object. Specifically, we firstly designed a cross-modal operation, Continuity-constrained Asymmetrical Pixelwise Operation (CAPO), which can mimic the process of deforming an isovolumetrically flexible object through external forces. Utilizing CAPO as the fundamental component, we develop the Pixelwise Cross Gradient Deformation (PCGD), which is capable of emulating operations on ideal plastic objects (without volume constraint). Notably, our approach demonstrates state-of-the-art performance across four widely adopted benchmarks for GDSR, with significant advantages in large-scale tasks and generalizability.

Ultrasound-QBench: Can LLMs Aid in Quality Assessment of Ultrasound Imaging?

With the dramatic upsurge in the volume of ultrasound examinations, low-quality ultrasound imaging has gradually increased due to variations in operator proficiency and imaging circumstances, imposing a severe burden on diagnosis accuracy and even entailing the risk of restarting the diagnosis in critical cases. To assist clinicians in selecting high-quality ultrasound images and ensuring accurate diagnoses, we introduce Ultrasound-QBench, a comprehensive benchmark that systematically evaluates multimodal large language models (MLLMs) on quality assessment tasks of ultrasound images. Ultrasound-QBench establishes two datasets collected from diverse sources: IVUSQA, consisting of 7,709 images, and CardiacUltraQA, containing 3,863 images. These images encompassing common ultrasound imaging artifacts are annotated by professional ultrasound experts and classified into three quality levels: high, medium, and low. To better evaluate MLLMs, we decompose the quality assessment task into three dimensionalities: qualitative classification, quantitative scoring, and comparative assessment. The evaluation of 7 open-source MLLMs as well as 1 proprietary MLLMs demonstrates that MLLMs possess preliminary capabilities for low-level visual tasks in ultrasound image quality classification. We hope this benchmark will inspire the research community to delve deeper into uncovering and enhancing the untapped potential of MLLMs for medical imaging tasks.

Evaluating the Design Features of an Intelligent Tutoring System for Advanced Mathematics Learning

Xiaomai is an intelligent tutoring system (ITS) designed to help Chinese college students in learning advanced mathematics and preparing for the graduate school math entrance exam. This study investigates two distinctive features within Xiaomai: the incorporation of free-response questions with automatic feedback and the metacognitive element of reflecting on self-made errors.

SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation

Although semi-supervised learning has made significant advances in the field of medical image segmentation, fully annotating a volumetric sample slice by slice remains a costly and time-consuming task. Even worse, most of the existing approaches pay much attention to image-level information and ignore semantic features, resulting in the inability to perceive weak boundaries. To address these issues, we propose a novel Semantic-Guided Triplet Co-training (SGTC) framework, which achieves high-end medical image segmentation by only annotating three orthogonal slices of a few volumetric samples, significantly alleviating the burden of radiologists. Our method consist of two main components. Specifically, to enable semantic-aware, fine-granular segmentation and enhance the quality of pseudo-labels, a novel semantic-guided auxiliary learning mechanism is proposed based on the pretrained CLIP. In addition, focusing on a more challenging but clinically realistic scenario, a new triple-view disparity training strategy is proposed, which uses sparse annotations (i.e., only three labeled slices of a few volumes) to perform co-training between three sub-networks, significantly improving the robustness. Extensive experiments on three public medical datasets demonstrate that our method outperforms most state-of-the-art semi-supervised counterparts under sparse annotation settings. The source code is available at https://github.com/xmeimeimei/SGTC.