Wen Gao

The emergence of Large Vision-Language Models (LVLMs) marks significant strides towards achieving general artificial intelligence. However, these advancements are accompanied by concerns about biased outputs, a challenge that has yet to be thoroughly explored. Existing benchmarks are not sufficiently comprehensive in evaluating biases due to their limited data scale, single questioning format and narrow sources of bias. To address this problem, we introduce VLBiasBench, a comprehensive benchmark designed to evaluate biases in LVLMs. VLBiasBench, features a dataset that covers nine distinct categories of social biases, including age, disability status, gender, nationality, physical appearance, race, religion, profession, social economic status, as well as two intersectional bias categories: race × gender and race × social economic status. To build a large-scale dataset, we use Stable Diffusion XL model to generate 46,848 high-quality images, which are combined with various questions to creat 128,342 samples. These questions are divided into open-ended and close-ended types, ensuring thorough consideration of bias sources and a comprehensive evaluation of LVLM biases from multiple perspectives. We conduct extensive evaluations on 15 open-source models as well as two advanced closed-source models, yielding new insights into the biases present in these models. Our benchmark is available at https://github.com/Xiangkui-Cao/VLBiasBench.

Aims: Women are at higher risk of serious ventricular arrhythmias, including torsades de pointes, when repolarization reserve is reduced, but sex-stratified mechanisms and quantitative risk assessment remain challenging. We aimed to develop scalable, tissue-scale, sex-aware ventricular virtual populations to quantify and explain sex differences in inherited and acquired proarrhythmic susceptibility. Methods and results: We constructed male and female virtual cohorts using a one-dimensional ventricular cable model with pseudo-electrocardiogram (pseudo-ECG), integrating sex-specific ionic conductance backgrounds and acute sex-hormone modulation. Virtual populations were filtered under multi-condition stress tests and calibrated to clinical corrected QT interval (QTc) distributions. We generated long QT syndrome types 1–3 (LQT1–3) cohorts, simulated sympathetic stress, and performed virtual drug trials for 109 compounds using multichannel block profiles at 1× effective free therapeutic plasma concentration. Proarrhythmic risk was defined by tissue-scale instability events (premature ventricular complexes, T-wave alternans, or repolarization failure). Drivers were analysed using regression and channel-sensitivity analysis, and clinical 24 h concentration-ECG data after dosing were used for external validation. The female cohorts exhibited higher simulated event risk across long QT syndrome subtypes and across multichannel drug block profiles, including drugs with <10 ms mean QTc prolongation. Female-to-male risk ratios tracked clinical risk categories. Simulated QTc time-courses and concentration-QTc trends agreed with 24 h clinical ECG data for key reference drugs. Conclusion: Sex-aware tissue-scale virtual populations enable in silico trials that quantify proarrhythmic risk beyond mean ΔQTc, provide mechanistic drivers, and support sex-informed cardiac safety evaluation and monitoring strategies.

Lossless compression of volumetric medical images is of paramount importance for clinical and research applications where data fidelity is essential. Traditional compression methods are often limited in efficiency due to rigid, handcrafted models. Conversely, deep neural network (DNN)-based compression methods, while effective, demand substantial computational resources, hindering deployment in resource-constrained settings. To address these challenges, we propose a novel tri-plane context tree (TCT)-based method for lossless volumetric medical image compression that delivers high performance without relying on DNNs or external training data. To exploit intra-slice and interslice redundancies, we introduce a compact tri-plane context representation that decomposes complex 3D context modeling into efficient 2D modeling on three orthogonal planes. By integrating this representation with a context tree framework, we develop an input-specific TCT model employing an adaptive binary tree structure. At each tree node, the model dynamically selects from a suite of tri-plane based predictors and contextual feature extractors, enabling data-adaptive context modeling tailored to local structural characteristics. Instead of offline training, we sample a subset of the input volume to learn the TCT model by optimizing the minimum description length (MDL) through iterative construction and pruning. With the learned TCT model, each pixel retrieves its corresponding context, computes the prediction residual using the predictor dictated by the context, and performs entropy encoding based on the associated histograms. Experimental results demonstrate that the proposed method achieves compression performance on par with recent DNN-based methods on multiple datasets, while maintaining low computational cost and fast coding speeds, making it highly applicable in practice.

In this article, we propose a multimodal robotic agent that addresses the limitations of passive perception and fixed-model deployment through a flexible large-model architecture. This architecture enables dynamic selection of multimodal large language models based on computational constraints. Building on this foundation, we introduce a logic-guided active perception strategy that decides which skills (e.g., knock and weigh) to employ based on intermediate reasoning, rather than exhaustively executing all possible actions. Our work focuses on cohesive skill integration within a unified control loop, optimizing both perception and action. This allows the agent to strategically probe objects’ visual, auditory, tactile, and weight attributes for accurate material inference and robust task completion. Extensive evaluations in the simulation environment highlight the efficiency and adaptability of our method, especially in active perception and latent information inference for robotic systems.

The rapid proliferation of artificial intelligence in the industrial sector is catalyzing a smart manufacturing paradigm driven by industrial AI agents. In contrast to IT counterparts, future industrial AI agents operate under unique constraints that demand both adaptive intelligence and strictly deterministic communication with ultra-low latency and ultra-high reliability. To address these stringent requirements, the convergence of reinforcement learning (RL) and Time-Sensitive Networking (TSN) has emerged as a critical enabler. This paper presents the fundamentals of RL, TSN, and industrial AI agent communication, and establishes a mapping between AI agent cognitive behaviors, communication requirements, and deterministic networking mechanisms. We propose a four-dimensional framework encompassing intelligent scheduling, dynamic resource management, network convergence and mobility, and application-aware networking to systematically analyze existing RL-for-TSN research and elucidate challenges and requirements for future industrial AI agent communication. Finally, we outline a research roadmap spanning constrained RL algorithms and agent-network co-design to pave the way for deterministic industrial edge intelligence.

Text-video retrieval plays a pivotal role in cross-modal tasks, aiming to match textual descriptions with corresponding video content accurately. Existing methods often employ fine-grained feature matching to improve retrieval accuracy, but such approaches consume extensive computational resources. Conversely, coarse-grained feature matching between entire sentences and videos offers computational efficiency but may overlook the heterogeneous semantic concepts embedded within the data. To overcome these challenges, we develop the Disentangled Concept Matching (DCM) framework, designed as an imitation of human semantic perception processes. The framework utilizes Disentangled Representation Learning (DRL) to divide coarse-grained features into distinct semantic concepts represented as latent factors, effectively generating finer-grained features while reducing computational demands. To improve the accuracy of retrieval, we first propose the Composed Spatial-temporal Module (CSTM) to optimize the quality of multimodal feature extraction. Utilizing a branch-structured temporal modeling approach, CSTM effectively enhances the DCM model’s comprehension of video content and temporal information, leading to the extraction of refined video features. Second, building on the optimized features, we propose the Adaptive Pooling Module (APM) to measure the confidence level of each latent factor matching during the process of decoupling concepts. APM enhances the fidelity of text and video concepts, thereby further ensuring the accuracy of matching after decoupling. With CSTM and APM, DCM accurately matches latent factors in lower dimensions, achieving significant improvements in computing efficiency and retrieval performance. Our experimental evaluations across standard datasets, namely MSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that the DCM framework achieves state-of-the-art performance, with Recall@1 scores of 48.7%, 25.6%, 48.4%, 45.0%, and 48.6%, respectively. Compared to our previous model, the DCM framework shows improvements of 2.54%, 0.08%, 2.11%, 6.89%, and 6.35%, respectively.

Nowadays, high-quality images are pursued by both humans for better viewing experience and by machines for more accurate visual analysis. However, images are usually compressed before being consumed, decreasing their quality. It is meaningful to predict the perceptual quality of compressed images for both humans and machines, which guides the optimization for compression. This issue remains underexplored. In this paper, we propose a unified approach to fill this gap. Specifically, we create a deep learning-based model to predict Satisfied User Ratio (SUR) and Satisfied Machine Ratio (SMR) of compressed images simultaneously. We first pre-train a feature extractor network on a large-scale SMR-annotated dataset with human perception-related quality labels generated by diverse image quality models, which simulates the acquisition of SUR labels. Then, we leverage and fuse the extracted multi-layer features to predict SUR and SMR with a more capable network architecture. We propose a Difference Feature Residual Learning (DFRL) module to learn more discriminative difference features. We also design a Multi-Head Attention Aggregation and Pooling (MHAAP) layer to aggregate difference features and reduce their redundancy. We further introduce an MLP-Mixer module to integrate global spatial and channel information for subsequent SUR and SMR regression. Experimental results indicate that the proposed model significantly outperforms state-of-the-art SUR and SMR prediction methods by up to 48% on several challenging datasets. Moreover, our joint learning scheme of human and machine perceptual quality prediction tasks is effective at improving the performance of both.

The recent development of feedforward 3D Gaussian Splatting (3DGS) presents a new paradigm to reconstruct 3D scenes. Using neural networks trained on large-scale multi-view datasets, it can directly infer 3DGS representations from sparse input views. Although the feedforward approach achieves high reconstruction speed, it still suffers from the substantial storage cost of 3D Gaussians. Existing 3DGS compression methods relying on scene-wise optimization are not applicable due to architectural incompatibilities. To overcome this limitation, we propose TinySplat, a complete feedforward approach for generating compact 3D scene representations. Built upon standard feedforward 3DGS methods, TinySplat integrates a training-free compression framework that systematically eliminates key sources of redundancy. Specifically, we introduce View-Projection Transformation (VPT) to reduce geometric redundancy by projecting geometric parameters into a more compact space. We further present Visibility-Aware Basis Reduction (VABR), which mitigates perceptual redundancy by aligning feature energy along dominant viewing directions via basis transformation. Lastly, spatial redundancy is addressed through an off-the-shelf video codec. Comprehensive experimental results on multiple benchmark datasets demonstrate that TinySplat achieves over 100× compression for 3D Gaussian data generated by feedforward methods. Compared to the state-of-the-art compression approach, we achieve comparable quality with only 6% of the storage size. Meanwhile, our compression framework requires only 25% of the encoding time and 1% of the decoding time.

Learned image compression (LIC) methods have shown promising results and achieved superior performance compared to traditional image compression methods. Due to the neglect of the utilization of cross-component correlations, there is still a potential for further performance improvement. In this paper, we first explore the inter-channel correlations of different color spaces and transform the image compression problem in RGB color space into that in YUV color space, which has cross-component prior information. We propose a novel image compression method that leverages local-to-global cross-component prior modeling, utilizing a cross-component attention mechanism to improve coding performance. First, we design the cross-component prior gate (CPG) to model the cross-component prior information based on attention mechanism. Inspired by common knowledge in data compression, luma component (Y) contains more details and textural/structural information compared to chroma components (UV). The proposed method can make full use of the cross-component guidance information from luma to chroma components to achieve effective image compression. Experimental results demonstrate that the proposed method can achieve superior performance compared to existing learned image compression methods. The proposed method can achieve 9.20% rate savings compared to the image compression standard Versatile Video Coding (VVC) Test Model (VTM-11.0) on Kodak dataset.