Xiaoli Liu

Zhiqiang Shen, Peng Cao, Hua Yang et al.

Consistency regularization and pseudo labeling-based semi-supervised methods perform co-training using the pseudo labels from multi-view inputs. However, such co-training models tend to converge early to a consensus, degenerating to the self-training ones, and produce low-confidence pseudo labels from the perturbed inputs during training. To address these issues, we propose an Uncertainty-guided Collaborative Mean-Teacher (UCMT) for semi-supervised semantic segmentation with the high-confidence pseudo labels. Concretely, UCMT consists of two main components: 1) collaborative mean-teacher (CMT) for encouraging model disagreement and performing co-training between the sub-networks, and 2) uncertainty-guided region mix (UMIX) for manipulating the input images according to the uncertainty maps of CMT and facilitating CMT to produce high-confidence pseudo labels. Combining the strengths of UMIX with CMT, UCMT can retain model disagreement and enhance the quality of pseudo labels for the co-training segmentation. Extensive experiments on four public medical image datasets including 2D and 3D modalities demonstrate the superiority of UCMT over the state-of-the-art. Code is available at: https://github.com/Senyh/UCMT.

Hanliang Du, Zhangji Lu, Zewei Cai et al.

Atmospheric turbulence causes significant image degradation due to pixel displacement (tilt) and blur, particularly in long-range imaging applications. In this paper, we propose a novel framework for atmospheric turbulence mitigation, GSTurb, which integrates optical flow-guided tilt correction and Gaussian splatting for modeling non-isoplanatic blur. The framework employs Gaussian parameters to represent tilt and blur, and optimizes them across multiple frames to enhance restoration. Experimental results on the ATSyn-static dataset demonstrate the effectiveness of our method, achieving a peak PSNR of 27.67 dB and SSIM of 0.8735. Compared to the state-of-the-art method, GSTurb improves PSNR by 1.3 dB (a 4.5% increase) and SSIM by 0.048 (a 5.8% increase). Additionally, on real datasets, including the TSRWGAN Real-World and CLEAR datasets, GSTurb outperforms existing methods, showing significant improvements in both qualitative and quantitative performance. These results highlight that combining optical flow-guided tilt correction with Gaussian splatting effectively enhances image restoration under both synthetic and real-world turbulence conditions. The code for this method will be available at https://github.com/DuhlLiamz/3DGS_turbulence/tree/main.

Siyu Liu, Guangqi Wen, Peng Cao et al.

Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. However, learning the interactions of the underlying subnetworks remains a significant challenge for existing Transformer-based methods due to the limited number of training samples. To address these challenges, we propose KD-Brain, a Prior-Informed Graph Learning framework for explicitly encoding prior knowledge to guide the learning process. Specifically, we design a Semantic-Conditioned Interaction mechanism that injects semantic priors into the attention query, explicitly navigating the subnetwork interactions based on their functional identities. Furthermore, we introduce a Pathology-Consistent Constraint, which regularizes the model optimization by aligning the learned interaction distributions with clinical priors. Additionally, KD-Brain leads to state-of-the-art performance on a wide range of disorder diagnosis tasks and identifies interpretable biomarkers consistent with psychiatric pathophysiology. Our code is available at https://anonymous.4open.science/r/KDBrain.

Xiaolong Li, Guiliang Guo, Guangqi Wen et al.

Mental disorder populations exhibit pronounced heterogeneity -- that is, the significant differences between samples -- poses a significant challenge to the definition of positive pairs in contrastive learning. To address this, we propose a subtype-guided contrastive learning framework that models patient heterogeneity as latent subtypes and incorporates them as structural priors to guide discriminative representation learning. Specifically, we construct multi-view representations by combining patients' clinical text with graph structure adaptively learned from BOLD signals, to uncover latent subtypes via unsupervised spectral clustering. A dual-level attention mechanism is proposed to construct prototypes for capturing stable subtype-specific connectivity patterns. We further propose a subtype-guided contrastive learning strategy that pulls samples toward their subtype prototype graph, reinforcing intra-subtype consistency for providing effective supervisory signals to improve model performance. We evaluate our method on Major Depressive Disorder (MDD), Bipolar Disorder (BD), and Autism Spectrum Disorders (ASD). Experimental results confirm the effectiveness of subtype prototype graphs in guiding contrastive learning and demonstrate that the proposed approach outperforms state-of-the-art approaches. Our code is available at https://anonymous.4open.science/r/BrainSCL-06D7.

Qingshan Hou, Peng Cao, Jiaqi Wang et al.

Retinal fundus images have been applied for the diagnosis and screening of eye diseases, such as Diabetic Retinopathy (DR) or Diabetic Macular Edema (DME). However, both low-quality fundus images and style inconsistency potentially increase uncertainty in the diagnosis of fundus disease and even lead to misdiagnosis by ophthalmologists. Most of the existing image enhancement methods mainly focus on improving the image quality by leveraging the guidance of high-quality images, which is difficult to be collected in medical applications. In this paper, we tackle image quality enhancement in a fully unsupervised setting, i.e., neither paired images nor high-quality images. To this end, we explore the potential of the self-supervised task for improving the quality of fundus images without the requirement of high-quality reference images. Specifically, we construct multiple patch-wise domains via an auxiliary pre-trained quality assessment network and a style clustering. To achieve robust low-quality image enhancement and address style inconsistency, we formulate two self-supervised domain adaptation tasks to disentangle the features of image content, low-quality factor and style information by exploring intrinsic supervision signals within the low-quality images. Extensive experiments are conducted on EyeQ and Messidor datasets, and results show that our DASQE method achieves new state-of-the-art performance when only low-quality images are available.

Lauri Lovén, Abhishek Kumar, Alexander Engelhardt et al.

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and embedding filters. Framed as offline multi-label retrieval over three public datasets spanning social-media, legal, and smart-home sensor domains (six LLMs, seven baselines), our central contribution is a two-crossover cost-accuracy characterisation: an analytical context-window crossover below which a CoverAndMerge compression pipeline reduces LLM invocations, and an empirical discrimination-capacity crossover above which matching accuracy collapses independently of context budget, by a model-dependent factor of parameter count and training generation. Two findings carry practical weight: above the discrimination crossover, compression cannot recover accuracy and only frontier-scale models clear large subscription sets; and there backend choice dominates configuration choice, so model selection, not pipeline tuning, is the primary operator lever. We accompany this with three composable algorithms and a per-cluster Quality-of-Experience framework for autonomic LLM-tier selection.

Jiajun Fu, Fuxing Yang, Yonghao Dang et al.

Human motion prediction is challenging due to the complex spatiotemporal feature modeling. Among all methods, graph convolution networks (GCNs) are extensively utilized because of their superiority in explicit connection modeling. Within a GCN, the graph correlation adjacency matrix drives feature aggregation and is the key to extracting predictive motion features. State-of-the-art methods decompose the spatiotemporal correlation into spatial correlations for each frame and temporal correlations for each joint. Directly parameterizing these correlations introduces redundant parameters to represent common relations shared by all frames and all joints. Besides, the spatiotemporal graph adjacency matrix is the same for different motion samples and cannot reflect sample-wise correspondence variances. To overcome these two bottlenecks, we propose dynamic spatiotemporal decompose GC (DSTD-GC), which only takes 28.6% parameters of the state-of-the-art GC. The key of DSTD-GC is constrained dynamic correlation modeling, which explicitly parameterizes the common static constraints as a spatial/temporal vanilla adjacency matrix shared by all frames/joints and dynamically extracts correspondence variances for each frame/joint with an adjustment modeling function. For each sample, the common constrained adjacency matrices are fixed to represent generic motion patterns, while the extracted variances complete the matrices with specific pattern adjustments. Meanwhile, we mathematically reformulate GCs on spatiotemporal graphs into a unified form and find that DSTD-GC relaxes certain constraints of other GC, which contributes to a better representation capability. By combining DSTD-GC with prior knowledge, we propose a powerful spatiotemporal GCN called DSTD-GCN, which outperforms SOTA methods by $3.9\% \sim 8.7\%$ in prediction accuracy with $55.0\% \sim 96.9\%$ fewer parameters.

Lin Huang, Chengxiang Huang, Ziang Wang et al.

Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems. However, mainstream architectures face critical scalability bottlenecks due to the explicit construction of geometric features or dense tensor products on \textit{every} edge. To overcome this, we introduce \textbf{E2Former-V2}, a scalable architecture that integrates algebraic sparsity with hardware-aware execution. We first propose \textbf{E}quivariant \textbf{A}xis-\textbf{A}ligned \textbf{S}parsification (EAAS). EAAS builds on Wigner-$6j$ convolution by exploiting an $\mathrm{SO}(3) \rightarrow \mathrm{SO}(2)$ change of basis to transform computationally expensive dense tensor contractions into efficient, sparse parity re-indexing operations. Building on this representation, we introduce \textbf{On-the-Fly Equivariant Attention}, a fully node-centric mechanism implemented via a custom fused Triton kernel. By eliminating materialized edge tensors and maximizing SRAM utilization, our kernel achieves a \textbf{20$\times$ improvement in TFLOPS} compared to standard implementations. Extensive experiments on the SPICE and OMol25 datasets demonstrate that E2Former-V2 maintains comparable predictive performance while notably accelerating inference. This work demonstrates that large equivariant transformers can be trained efficiently using widely accessible GPU platforms. The code is avalible at https://github.com/IQuestLab/UBio-MolFM/tree/e2formerv2.

Xin Huang, Junjie Liang, Qingshan Hou et al.

Medical image synthesis is crucial for alleviating data scarcity and privacy constraints. However, fine-tuning general text-to-image (T2I) models remains challenging, mainly due to the significant modality gap between complex visual details and abstract clinical text. In addition, semantic entanglement persists, where coarse-grained text embeddings blur the boundary between anatomical structures and imaging styles, thus weakening controllability during generation. To address this, we propose a Visually-Guided Text Disentanglement framework. We introduce a cross-modal latent alignment mechanism that leverages visual priors to explicitly disentangle unstructured text into independent semantic representations. Subsequently, a Hybrid Feature Fusion Module (HFFM) injects these features into a Diffusion Transformer (DiT) through separated channels, enabling fine-grained structural control. Experimental results in three datasets demonstrate that our method outperforms existing approaches in terms of generation quality and significantly improves performance on downstream classification tasks. The source code is available at https://github.com/hx111/VG-MedGen.

Guiliang Guo, Guangqi Wen, Lingwen Liu et al.

Dynamic functional connectivity captures time-varying brain states for better neuropsychiatric diagnosis and spatio-temporal interpretability, i.e., identifying when discriminative disease signatures emerge and where they reside in the connectivity topology. Reliable interpretability faces major challenges: diagnostic signals are often subtle and sparsely distributed across both time and topology, while nuisance fluctuations and non-diagnostic connectivities are pervasive. To address these issues, we propose BrainSTR, a spatio-temporal contrastive learning framework for interpretable dynamic brain network modeling. BrainSTR learns state-consistent phase boundaries via a data-driven Adaptive Phase Partition module, identifies diagnostically critical phases with attention, and extracts disease-related connectivity within each phase using an Incremental Graph Structure Generator regularized by binarization, temporal smoothness, and sparsity. Then, we introduce a spatio-temporal supervised contrastive learning approach that leverages diagnosis-relevant spatio-temporal patterns to refine the similarity metric between samples and capture more discriminative spatio-temporal features, thereby constructing a well-structured semantic space for coherent and interpretable representations. Experiments on ASD, BD, and MDD validate the effectiveness of BrainSTR, and the discovered critical phases and subnetworks provide interpretable evidence consistent with prior neuroimaging findings. Our code: https://anonymous.4open.science/r/BrainSTR1.

Jingfeng Tang, Peng Cao, Guangqi Wen et al.

Brain network analysis based on functional Magnetic Resonance Imaging (fMRI) is pivotal for diagnosing brain disorders. Existing approaches typically rely on predefined functional sub-networks to construct sub-network associations. However, we identified many cross-network interaction patterns with high Pearson correlations that this strict, prior-based organization fails to capture. To overcome this limitation, we propose the Brain Hierarchical Organization Learning (BrainHO) to learn inherently hierarchical brain network dependencies based on their intrinsic features rather than predefined sub-network labels. Specifically, we design a hierarchical attention mechanism that allows the model to aggregate nodes into a hierarchical organization, effectively capturing intricate connectivity patterns at the subgraph level. To ensure diverse, complementary, and stable organizations, we incorporate an orthogonality constraint loss, alongside a hierarchical consistency constraint strategy, to refine node-level features using high-level graph semantics. Extensive experiments on the publicly available ABIDE and REST-meta-MDD datasets demonstrate that BrainHO not only achieves state-of-the-art classification performance but also uncovers interpretable, clinically significant biomarkers by precisely localizing disease-related sub-networks.

Chengxu Duan, Zhicheng Zhang, Xiaoli Liu et al.

Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks. The adversarial attack will encounter problems against human motion prediction in naturalness and data scale. To solve the problems above, we propose a new adversarial attack method that generates the worst-case perturbation by maximizing the human motion predictor's prediction error with physical constraints. Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example. The evaluating experiments on three datasets show that the prediction errors of all target models are enlarged significantly, which means current convolution-based human motion prediction models are vulnerable to the proposed attack. Based on the experimental results, we provide insights on how to enhance the adversarial robustness of the human motion predictor and how to improve the adversarial attack against human motion prediction.

Jianqiang Lin, Zhiqiang Shen, Peng Cao et al.

Although diffusion models have achieved remarkable progress in multi-modal magnetic resonance imaging (MRI) translation tasks, existing methods still tend to suffer from anatomical inconsistencies or degraded texture details when handling arbitrary missing-modality scenarios. To address these issues, we propose a latent diffusion-based multi-modal MRI translation framework, termed MSG-LDM. By leveraging the available modalities, the proposed method infers complete structural information, which preserves reliable boundary details. Specifically, we introduce a style--structure disentanglement mechanism in the latent space, which explicitly separates modality-specific style features from shared structural representations, and jointly models low-frequency anatomical layouts and high-frequency boundary details in a multi-scale feature space. During the structure disentanglement stage, high-frequency structural information is explicitly incorporated to enhance feature representations, guiding the model to focus on fine-grained structural cues while learning modality-invariant low-frequency anatomical representations. Furthermore, to reduce interference from modality-specific styles and improve the stability of structure representations, we design a style consistency loss and a structure-aware loss. Extensive experiments on the BraTS2020 and WMH datasets demonstrate that the proposed method outperforms existing MRI synthesis approaches, particularly in reconstructing complete structures. The source code is publicly available at https://github.com/ziyi-start/MSG-LDM.

Lin Huang, Arthur Jiang, XiaoLi Liu et al.

All-atom molecular simulation serves as a quintessential ``computational microscope'' for understanding the machinery of life, yet it remains fundamentally limited by the trade-off between quantum-mechanical (QM) accuracy and biological scale. We present UBio-MolFM, a universal foundation model framework specifically engineered to bridge this gap. UBio-MolFM introduces three synergistic innovations: (1) UBio-Mol26, a large bio-specific dataset constructed via a multi-fidelity ``Two-Pronged Strategy'' that combines systematic bottom-up enumeration with top-down sampling of native protein environments (up to 1,200 atoms); (2) E2Former-V2, a linear-scaling equivariant transformer that integrates Equivariant Axis-Aligned Sparsification (EAAS) and Long-Short Range (LSR) modeling to capture non-local physics with up to ~4x higher inference throughput in our large-system benchmarks; and (3) a Three-Stage Curriculum Learning protocol that transitions from energy initialization to energy-force consistency, with force-focused supervision to mitigate energy offsets. Rigorous benchmarking across microscopic forces and macroscopic observables -- including liquid water structure, ionic solvation, and peptide folding -- demonstrates that UBio-MolFM achieves ab initio-level fidelity on large, out-of-distribution biomolecular systems (up to ~1,500 atoms) and realistic MD observables. By reconciling scalability with quantum precision, UBio-MolFM provides a robust, ready-to-use tool for the next generation of computational biology.

Zhiqiang Shen, Peng Cao, Xiaoli Liu et al.

Label scarcity remains a major challenge in deep learning-based medical image segmentation. Recent studies use strong-weak pseudo supervision to leverage unlabeled data. However, performance is often hindered by inconsistencies between pseudo labels and their corresponding unlabeled images. In this work, we propose \textbf{SynMatch}, a novel framework that sidesteps the need for improving pseudo labels by synthesizing images to match them instead. Specifically, SynMatch synthesizes images using texture and shape features extracted from the same segmentation model that generates the corresponding pseudo labels for unlabeled images. This design enables the generation of highly consistent synthesized-image-pseudo-label pairs without requiring any training parameters for image synthesis. We extensively evaluate SynMatch across diverse medical image segmentation tasks under semi-supervised learning (SSL), weakly-supervised learning (WSL), and barely-supervised learning (BSL) settings with increasingly limited annotations. The results demonstrate that SynMatch achieves superior performance, especially in the most challenging BSL setting. For example, it outperforms the recent strong-weak pseudo supervision-based method by 29.71\% and 10.05\% on the polyp segmentation task with 5\% and 10\% scribble annotations, respectively. The code will be released at https://github.com/Senyh/SynMatch.

Haonan Wang, Peng Cao, Xiaoli Liu et al.

Most state-of-the-art methods for medical image segmentation adopt the encoder-decoder architecture. However, this U-shaped framework still has limitations in capturing the non-local multi-scale information with a simple skip connection. To solve the problem, we firstly explore the potential weakness of skip connections in U-Net on multiple segmentation tasks, and find that i) not all skip connections are useful, each skip connection has different contribution; ii) the optimal combinations of skip connections are different, relying on the specific datasets. Based on our findings, we propose a new segmentation framework, named UDTransNet, to solve three semantic gaps in U-Net. Specifically, we propose a Dual Attention Transformer (DAT) module for capturing the channel- and spatial-wise relationships to better fuse the encoder features, and a Decoder-guided Recalibration Attention (DRA) module for effectively connecting the DAT tokens and the decoder features to eliminate the inconsistency. Hence, both modules establish a learnable connection to solve the semantic gaps between the encoder and the decoder, which leads to a high-performance segmentation model for medical images. Comprehensive experimental results indicate that our UDTransNet produces higher evaluation scores and finer segmentation results with relatively fewer parameters over the state-of-the-art segmentation methods on different public datasets. Code: https://github.com/McGregorWwww/UDTransNet.

Xiaoli Liu, Jianqin Yin, Di Guo et al.

Early action prediction (EAP) aims to recognize human actions from a part of action execution in ongoing videos, which is an important task for many practical applications. Most prior works treat partial or full videos as a whole, ignoring rich action knowledge hidden in videos, i.e., semantic consistencies among different partial videos. In contrast, we partition original partial or full videos to form a new series of partial videos and mine the Action-Semantic Consistent Knowledge (ASCK) among these new partial videos evolving in arbitrary progress levels. Moreover, a novel Rich Action-semantic Consistent Knowledge network (RACK) under the teacher-student framework is proposed for EAP. Firstly, we use a two-stream pre-trained model to extract features of videos. Secondly, we treat the RGB or flow features of the partial videos as nodes and their action semantic consistencies as edges. Next, we build a bi-directional semantic graph for the teacher network and a single-directional semantic graph for the student network to model rich ASCK among partial videos. The MSE and MMD losses are incorporated as our distillation loss to enrich the ASCK of partial videos from the teacher to the student network. Finally, we obtain the final prediction by summering the logits of different subnetworks and applying a softmax layer. Extensive experiments and ablative studies have been conducted, demonstrating the effectiveness of modeling rich ASCK for EAP. With the proposed RACK, we have achieved state-of-the-art performance on three benchmarks. The code is available at https://github.com/lily2lab/RACK.git.

Zuozhuo Dai, Guangyuan Wang, Weihao Yuan et al.

State-of-the-art unsupervised re-ID methods train the neural networks using a memory-based non-parametric softmax loss. Instance feature vectors stored in memory are assigned pseudo-labels by clustering and updated at instance level. However, the varying cluster sizes leads to inconsistency in the updating progress of each cluster. To solve this problem, we present Cluster Contrast which stores feature vectors and computes contrast loss at the cluster level. Our approach employs a unique cluster representation to describe each cluster, resulting in a cluster-level memory dictionary. In this way, the consistency of clustering can be effectively maintained throughout the pipline and the GPU memory consumption can be significantly reduced. Thus, our method can solve the problem of cluster inconsistency and be applicable to larger data sets. In addition, we adopt different clustering algorithms to demonstrate the robustness and generalization of our framework. The application of Cluster Contrast to a standard unsupervised re-ID pipeline achieves considerable improvements of 9.9%, 8.3%, 12.1% compared to state-of-the-art purely unsupervised re-ID methods and 5.5%, 4.8%, 4.4% mAP compared to the state-of-the-art unsupervised domain adaptation re-ID methods on the Market, Duke, and MSMT17 datasets. Code is available at https://github.com/alibaba/cluster-contrast.

Xiaoli Liu, Jianqin Yin, Huaping Liu et al.

Predicting future human motion plays a significant role in human-machine interactions for various real-life applications. A unified formulation and multi-order modeling are two critical perspectives for analyzing and representing human motion. In contrast to prior works, we improve the multi-order modeling ability of human motion systems for more accurate predictions by building a deep state-space model (DeepSSM). The DeepSSM utilizes the advantages of both the state-space theory and the deep network. Specifically, we formulate the human motion system as the state-space model of a dynamic system and model the motion system by the state-space theory, offering a unified formulation for diverse human motion systems. Moreover, a novel deep network is designed to parameterize this system, which jointly models the state-state transition and state-observation transition processes. In this way, the state of a system is updated by the multi-order information of a time-varying human motion sequence. Multiple future poses are recursively predicted via the state-observation transition. To further improve the model ability of the system, a novel loss, WT-MPJPE (Weighted Temporal Mean Per Joint Position Error), is introduced to optimize the model. The proposed loss encourages the system to achieve more accurate predictions by increasing weights to the early time steps. The experiments on two benchmark datasets (i.e., Human3.6M and 3DPW) confirm that our method achieves state-of-the-art performance with improved accuracy of at least 2.2mm per joint. The code will be available at: \url{https://github.com/lily2lab/DeepSSM.git}.

Jiong Gong, Haihao Shen, Guoming Zhang et al.

High throughput and low latency inference of deep neural networks are critical for the deployment of deep learning applications. This paper presents the efficient inference techniques of IntelCaffe, the first Intel optimized deep learning framework that supports efficient 8-bit low precision inference and model optimization techniques of convolutional neural networks on Intel Xeon Scalable Processors. The 8-bit optimized model is automatically generated with a calibration process from FP32 model without the need of fine-tuning or retraining. We show that the inference throughput and latency with ResNet-50, Inception-v3 and SSD are improved by 1.38X-2.9X and 1.35X-3X respectively with neglectable accuracy loss from IntelCaffe FP32 baseline and by 56X-75X and 26X-37X from BVLC Caffe. All these techniques have been open-sourced on IntelCaffe GitHub1, and the artifact is provided to reproduce the result on Amazon AWS Cloud.

Lincong Feng, Muyu Wang, Maoyu Wang et al.

Generative models for 3D object synthesis have seen significant advancements with the incorporation of prior knowledge distilled from 2D diffusion models. Nevertheless, challenges persist in the form of multi-view geometric inconsistencies and slow generation speeds within the existing 3D synthesis frameworks. This can be attributed to two factors: firstly, the deficiency of abundant geometric a priori knowledge in optimization, and secondly, the entanglement issue between geometry and texture in conventional 3D generation methods.In response, we introduce MetaDreammer, a two-stage optimization approach that leverages rich 2D and 3D prior knowledge. In the first stage, our emphasis is on optimizing the geometric representation to ensure multi-view consistency and accuracy of 3D objects. In the second stage, we concentrate on fine-tuning the geometry and optimizing the texture, thereby achieving a more refined 3D object. Through leveraging 2D and 3D prior knowledge in two stages, respectively, we effectively mitigate the interdependence between geometry and texture. MetaDreamer establishes clear optimization objectives for each stage, resulting in significant time savings in the 3D generation process. Ultimately, MetaDreamer can generate high-quality 3D objects based on textual prompts within 20 minutes, and to the best of our knowledge, it is the most efficient text-to-3D generation method. Furthermore, we introduce image control into the process, enhancing the controllability of 3D generation. Extensive empirical evidence confirms that our method is not only highly efficient but also achieves a quality level that is at the forefront of current state-of-the-art 3D generation techniques.

Hui Wu, Yi Gan, Feng Yuan et al.

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with massive operations and perform inference in the auto-regressive mode, making it a challenging task to design a system with high efficiency. In this paper, we propose an efficient LLM inference solution with low latency and high throughput. Firstly, we simplify the LLM decoder layer by fusing data movement and element-wise operations to reduce the memory access frequency and lower system latency. We also propose a segment KV cache policy to keep key/value of the request and response tokens in separate physical memory for effective device memory management, helping enlarge the runtime batch size and improve system throughput. A customized Scaled-Dot-Product-Attention kernel is designed to match our fusion policy based on the segment KV cache solution. We implement our LLM inference solution on Intel GPU and publish it publicly. Compared with the standard HuggingFace implementation, the proposed solution achieves up to 7x lower token latency and 27x higher throughput for some popular LLMs on Intel GPU.

Qingshan Hou, Shuai Cheng, Peng Cao et al.

Representation learning offers a conduit to elucidate distinctive features within the latent space and interpret the deep models. However, the randomness of lesion distribution and the complexity of low-quality factors in medical images pose great challenges for models to extract key lesion features. Disease diagnosis methods guided by contrastive learning (CL) have shown significant advantages in lesion feature representation. Nevertheless, the effectiveness of CL is highly dependent on the quality of the positive and negative sample pairs. In this work, we propose a clinical-oriented multi-level CL framework that aims to enhance the model's capacity to extract lesion features and discriminate between lesion and low-quality factors, thereby enabling more accurate disease diagnosis from low-quality medical images. Specifically, we first construct multi-level positive and negative pairs to enhance the model's comprehensive recognition capability of lesion features by integrating information from different levels and qualities of medical images. Moreover, to improve the quality of the learned lesion embeddings, we introduce a dynamic hard sample mining method based on self-paced learning. The proposed CL framework is validated on two public medical image datasets, EyeQ and Chest X-ray, demonstrating superior performance compared to other state-of-the-art disease diagnostic methods.

Qingshan Hou, Meng Wang, Peng Cao et al.

Recent advancements in ophthalmology foundation models such as RetFound have demonstrated remarkable diagnostic capabilities but require massive datasets for effective pre-training, creating significant barriers for development and deployment. To address this critical challenge, we propose FundusGAN, a novel hierarchical feature-aware generative framework specifically designed for high-fidelity fundus image synthesis. Our approach leverages a Feature Pyramid Network within its encoder to comprehensively extract multi-scale information, capturing both large anatomical structures and subtle pathological features. The framework incorporates a modified StyleGAN-based generator with dilated convolutions and strategic upsampling adjustments to preserve critical retinal structures while enhancing pathological detail representation. Comprehensive evaluations on the DDR, DRIVE, and IDRiD datasets demonstrate that FundusGAN consistently outperforms state-of-the-art methods across multiple metrics (SSIM: 0.8863, FID: 54.2, KID: 0.0436 on DDR). Furthermore, disease classification experiments reveal that augmenting training data with FundusGAN-generated images significantly improves diagnostic accuracy across multiple CNN architectures (up to 6.49\% improvement with ResNet50). These results establish FundusGAN as a valuable foundation model component that effectively addresses data scarcity challenges in ophthalmological AI research, enabling more robust and generalizable diagnostic systems while reducing dependency on large-scale clinical data collection.

Yujian Liu, Shidang Xu, Jing Guo et al.

Generating talking avatar driven by audio remains a significant challenge. Existing methods typically require high computational costs and often lack sufficient facial detail and realism, making them unsuitable for applications that demand high real-time performance and visual quality. Additionally, while some methods can synchronize lip movement, they still face issues with consistency between facial expressions and upper body movement, particularly during silent periods. In this paper, we introduce SyncAnimation, the first NeRF-based method that achieves audio-driven, stable, and real-time generation of speaking avatar by combining generalized audio-to-pose matching and audio-to-expression synchronization. By integrating AudioPose Syncer and AudioEmotion Syncer, SyncAnimation achieves high-precision poses and expression generation, progressively producing audio-synchronized upper body, head, and lip shapes. Furthermore, the High-Synchronization Human Renderer ensures seamless integration of the head and upper body, and achieves audio-sync lip. The project page can be found at https://syncanimation.github.io

Xuan Feng, Tianlong Gu, Xiaoli Liu et al.

Unnatural text correction aims to automatically detect and correct spelling errors or adversarial perturbation errors in sentences. Existing methods typically rely on fine-tuning or adversarial training to correct errors, which have achieved significant success. However, these methods exhibit poor generalization performance due to the difference in data distribution between training data and real-world scenarios, known as the exposure bias problem. In this paper, we propose a self-correct adversarial training framework for \textbf{L}earn\textbf{I}ng from \textbf{MI}s\textbf{T}akes (\textbf{LIMIT}), which is a task- and model-independent framework to correct unnatural errors or mistakes. Specifically, we fully utilize errors generated by the model that are actively exposed during the inference phase, i.e., predictions that are inconsistent with the target. This training method not only simulates potential errors in real application scenarios, but also mitigates the exposure bias of the traditional training process. Meanwhile, we design a novel decoding intervention strategy to maintain semantic consistency. Extensive experimental results on Chinese unnatural text error correction datasets show that our proposed method can correct multiple forms of errors and outperforms the state-of-the-art text correction methods. In addition, extensive results on Chinese and English datasets validate that LIMIT can serve as a plug-and-play defense module and can extend to new models and datasets without further training.

Yujian Liu, Yuechuan Lin, Dongxu Shen et al.

Whole-slide image (WSI) analysis remains challenging due to the gigapixel scale and sparsely distributed diagnostic regions. Multiple Instance Learning (MIL) mitigates this by modeling the WSI as bags of patches for slide-level prediction. However, most MIL approaches emphasize aggregator design while overlooking the impact of the feature extractor of the feature extraction stage, which is often pretrained on natural images. This leads to domain gap and suboptimal representations. Self-supervised learning (SSL) has shown promise in bridging domain gap via pretext tasks, but it still primarily builds upon generic backbones, thus requiring WSIs to be split into small patches. This inevitably splits histological structures and generates both redundant and interdependent patches, which in turn degrades aggregator performance and drastically increases training costs. To address this challenge, we propose a Cascaded Dual-Scale Reconstruction (CDSR) framework, demonstrating that only an average of 9 high-resolution patches per WSI are sufficient for robust slide-level representation. CDSR employs a two-stage selective sampling strategy that identifies the most informative representative regions from both model-based and semantic perspectives. These patches are then fed into a Local-to-Global Network, which reconstructs spatially coherent high-resolution WSI representations by integrating fine-grained local detail with global contextual information. Unlike existing dense-sampling or SSL pipelines, CDSR is optimized for efficiency and morphological fidelity. Experiments on Camelyon16, TCGA-NSCLC, and TCGA-RCC demonstrate that CDSR achieves improvements of 6.3% in accuracy and 5.5% in area under ROC curve on downstream classification tasks with only 7,070 (4.5% of total) high-resolution patches per dataset on average, outperforming state-of-the-art methods trained on over 10,000,000 patches.

Zheng Zhou, Zhe Li, Bo Yu et al.

The automatic reconstruction of 3D computer-aided design (CAD) models from CAD sketches has recently gained significant attention in the computer vision community. Most existing methods, however, rely on vector CAD sketches and 3D ground truth for supervision, which are often difficult to be obtained in industrial applications and are sensitive to noise inputs. We propose viewing CAD reconstruction as a specific instance of sparse-view 3D reconstruction to overcome these limitations. While this reformulation offers a promising perspective, existing 3D reconstruction methods typically require natural images and corresponding camera poses as inputs, which introduces two major significant challenges: (1) modality discrepancy between CAD sketches and natural images, and (2) difficulty of accurate camera pose estimation for CAD sketches. To solve these issues, we first transform the CAD sketches into representations resembling natural images and extract corresponding masks. Next, we manually calculate the camera poses for the orthographic views to ensure accurate alignment within the 3D coordinate system. Finally, we employ a customized sparse-view 3D reconstruction method to achieve high-quality reconstructions from aligned orthographic views. By leveraging raster CAD sketches for self-supervision, our approach eliminates the reliance on vector CAD sketches and 3D ground truth. Experiments on the Sub-Fusion360 dataset demonstrate that our proposed method significantly outperforms previous approaches in CAD reconstruction performance and exhibits strong robustness to noisy inputs.

Kuo Xu, Maoyu Wang, Muyu Wang et al.

The recent advancements in 2D generation technology have sparked a widespread discussion on using 2D priors for 3D shape and texture content generation. However, these methods often overlook the subsequent user operations, such as texture aliasing and blurring that occur when the user acquires the 3D model and simplifies its structure. Traditional graphics methods partially alleviate this issue, but recent texture synthesis technologies fail to ensure consistency with the original model's appearance and cannot achieve high-fidelity restoration. Moreover, background noise frequently arises in high-resolution texture synthesis, limiting the practical application of these generation technologies.In this work, we propose a high-resolution and high-fidelity texture restoration technique that uses the rough texture as the initial input to enhance the consistency between the synthetic texture and the initial texture, thereby overcoming the issues of aliasing and blurring caused by the user's structure simplification operations. Additionally, we introduce a background noise smoothing technique based on a self-supervised scheme to address the noise problem in current high-resolution texture synthesis schemes. Our approach enables high-resolution texture synthesis, paving the way for high-definition and high-detail texture synthesis technology. Experiments demonstrate that our scheme outperforms currently known schemes in high-fidelity texture recovery under high-resolution conditions.

Yujian Liu, Linlang Cao, Chuang Chen et al.

Existing 3D head avatar reconstruction methods adopt a two-stage process, relying on tracked FLAME meshes derived from facial landmarks, followed by Gaussian-based rendering. However, misalignment between the estimated mesh and target images often leads to suboptimal rendering quality and loss of fine visual details. In this paper, we present MoGaFace, a novel 3D head avatar modeling framework that continuously refines facial geometry and texture attributes throughout the Gaussian rendering process. To address the misalignment between estimated FLAME meshes and target images, we introduce the Momentum-Guided Consistent Geometry module, which incorporates a momentum-updated expression bank and an expression-aware correction mechanism to ensure temporal and multi-view consistency. Additionally, we propose Latent Texture Attention, which encodes compact multi-view features into head-aware representations, enabling geometry-aware texture refinement via integration into Gaussians. Extensive experiments show that MoGaFace achieves high-fidelity head avatar reconstruction and significantly improves novel-view synthesis quality, even under inaccurate mesh initialization and unconstrained real-world settings.

Renjie Li, Wenjie Wei, Qi Xin et al.

Large language models (LLMs) are rapidly pushing the limits of contemporary computing hardware. For example, training GPT-3 has been estimated to consume around 1300 MWh of electricity, and projections suggest future models may require city-scale (gigawatt) power budgets. These demands motivate exploration of computing paradigms beyond conventional von Neumann architectures. This review surveys emerging photonic hardware optimized for next-generation generative AI computing. We discuss integrated photonic neural network architectures (e.g., Mach-Zehnder interferometer meshes, lasers, wavelength-multiplexed microring resonators) that perform ultrafast matrix operations. We also examine promising alternative neuromorphic devices, including spiking neural network circuits and hybrid spintronic-photonic synapses, which combine memory and processing. The integration of two-dimensional materials (graphene, TMDCs) into silicon photonic platforms is reviewed for tunable modulators and on-chip synaptic elements. Transformer-based LLM architectures (self-attention and feed-forward layers) are analyzed in this context, identifying strategies and challenges for mapping dynamic matrix multiplications onto these novel hardware substrates. We then dissect the mechanisms of mainstream LLMs, such as ChatGPT, DeepSeek, and LLaMA, highlighting their architectural similarities and differences. We synthesize state-of-the-art components, algorithms, and integration methods, highlighting key advances and open issues in scaling such systems to mega-sized LLM models. We find that photonic computing systems could potentially surpass electronic processors by orders of magnitude in throughput and energy efficiency, but require breakthroughs in memory, especially for long-context windows and long token sequences, and in storage of ultra-large datasets.

Jacky Cao, Kit-Yung Lam, Lik-Hang Lee et al.

Mobile Augmented Reality (MAR) integrates computer-generated virtual objects with physical environments for mobile devices. MAR systems enable users to interact with MAR devices, such as smartphones and head-worn wearables, and performs seamless transitions from the physical world to a mixed world with digital entities. These MAR systems support user experiences by using MAR devices to provide universal accessibility to digital contents. Over the past 20 years, a number of MAR systems have been developed, however, the studies and design of MAR frameworks have not yet been systematically reviewed from the perspective of user-centric design. This article presents the first effort of surveying existing MAR frameworks (count: 37) and further discusses the latest studies on MAR through a top-down approach: 1) MAR applications; 2) MAR visualisation techniques adaptive to user mobility and contexts; 3) systematic evaluation of MAR frameworks including supported platforms and corresponding features such as tracking, feature extraction plus sensing capabilities; and 4) underlying machine learning approaches supporting intelligent operations within MAR systems. Finally, we summarise the development of emerging research fields, current state-of-the-art, and discuss the important open challenges and possible theoretical and technical directions. This survey aims to benefit both researchers and MAR system developers alike.

Xiaoli Liu, Yang Xu, Jiali Li et al.

Precise control over dimension of nanocrystals is critical to tune the properties for various applications. However, the traditional control through experimental optimization is slow, tedious and time consuming. Herein a robust deep neural network-based regression algorithm has been developed for precise prediction of length, width, and aspect ratios of semiconductor nanorods (NRs). Given there is limited experimental data available (28 samples), a Synthetic Minority Oversampling Technique for regression (SMOTE-REG) has been employed for the first time for data generation. Deep neural network is further applied to develop regression model which demonstrated the well performed prediction on both the original and generated data with a similar distribution. The prediction model is further validated with additional experimental data, showing accurate prediction results. Additionally, Local Interpretable Model-Agnostic Explanations (LIME) is used to interpret the weight for each variable, which corresponds to its importance towards the target dimension, which is approved to be well correlated well with experimental observations.

Xiaoli Liu, Jianqin Yin

Predicting future human motion is critical for intelligent robots to interact with humans in the real world, and human motion has the nature of multi-granularity. However, most of the existing work either implicitly modeled multi-granularity information via fixed modes or focused on modeling a single granularity, making it hard to well capture this nature for accurate predictions. In contrast, we propose a novel end-to-end network, Semi-Decoupled Multi-grained Trajectory Learning network (SDMTL), to predict future poses, which not only flexibly captures rich multi-grained trajectory information but also aggregates multi-granularity information for predictions. Specifically, we first introduce a Brain-inspired Semi-decoupled Motion-sensitive Encoding module (BSME), effectively capturing spatiotemporal features in a semi-decoupled manner. Then, we capture the temporal dynamics of motion trajectory at multi-granularity, including fine granularity and coarse granularity. We learn multi-grained trajectory information using BSMEs hierarchically and further capture the information of temporal evolutional directions at each granularity by gathering the outputs of BSMEs at each granularity and applying temporal convolutions along the motion trajectory. Next, the captured motion dynamics can be further enhanced by aggregating the information of multi-granularity with a weighted summation scheme. Finally, experimental results on two benchmarks, including Human3.6M and CMU-Mocap, show that our method achieves state-of-the-art performance, demonstrating the effectiveness of our proposed method. The code will be available if the paper is accepted.

Wanling Gao, Fei Tang, Jianfeng Zhan et al.

Modern real-world application scenarios like Internet services consist of a diversity of AI and non-AI modules with huge code sizes and long and complicated execution paths, which raises serious benchmarking or evaluating challenges. Using AI components or micro benchmarks alone can lead to error-prone conclusions. This paper presents a methodology to attack the above challenge. We formalize a real-world application scenario as a Directed Acyclic Graph-based model and propose the rules to distill it into a permutation of essential AI and non-AI tasks, which we call a scenario benchmark. Together with seventeen industry partners, we extract nine typical scenario benchmarks. We design and implement an extensible, configurable, and flexible benchmark framework. We implement two Internet service AI scenario benchmarks based on the framework as proxies to two real-world application scenarios. We consider scenario, component, and micro benchmarks as three indispensable parts for evaluating. Our evaluation shows the advantage of our methodology against using component or micro AI benchmarks alone. The specifications, source code, testbed, and results are publicly available from \url{https://www.benchcouncil.org/aibench/scenario/}.

Xiaoli Liu, Pan Hu, Zhi Mao et al.

Background: Elderly patients with MODS have high risk of death and poor prognosis. The performance of current scoring systems assessing the severity of MODS and its mortality remains unsatisfactory. This study aims to develop an interpretable and generalizable model for early mortality prediction in elderly patients with MODS. Methods: The MIMIC-III, eICU-CRD and PLAGH-S databases were employed for model generation and evaluation. We used the eXtreme Gradient Boosting model with the SHapley Additive exPlanations method to conduct early and interpretable predictions of patients' hospital outcome. Three types of data source combinations and five typical evaluation indexes were adopted to develop a generalizable model. Findings: The interpretable model, with optimal performance developed by using MIMIC-III and eICU-CRD datasets, was separately validated in MIMIC-III, eICU-CRD and PLAGH-S datasets (no overlapping with training set). The performances of the model in predicting hospital mortality as validated by the three datasets were: AUC of 0.858, sensitivity of 0.834 and specificity of 0.705; AUC of 0.849, sensitivity of 0.763 and specificity of 0.784; and AUC of 0.838, sensitivity of 0.882 and specificity of 0.691, respectively. Comparisons of AUC between this model and baseline models with MIMIC-III dataset validation showed superior performances of this model; In addition, comparisons in AUC between this model and commonly used clinical scores showed significantly better performance of this model. Interpretation: The interpretable machine learning model developed in this study using fused datasets with large sample sizes was robust and generalizable. This model outperformed the baseline models and several clinical scores for early prediction of mortality in elderly ICU patients. The interpretative nature of this model provided clinicians with the ranking of mortality risk features.

Francesco Concas, Julien Mineraud, Eemil Lagerspetz et al.

The significance of air pollution and the problems associated with it are fueling deployments of air quality monitoring stations worldwide. The most common approach for air quality monitoring is to rely on environmental monitoring stations, which unfortunately are very expensive both to acquire and to maintain. Hence environmental monitoring stations are typically sparsely deployed, resulting in limited spatial resolution for measurements. Recently, low-cost air quality sensors have emerged as an alternative that can improve the granularity of monitoring. The use of low-cost air quality sensors, however, presents several challenges: they suffer from cross-sensitivities between different ambient pollutants; they can be affected by external factors, such as traffic, weather changes, and human behavior; and their accuracy degrades over time. Periodic re-calibration can improve the accuracy of low-cost sensors, particularly with machine-learning-based calibration, which has shown great promise due to its capability to calibrate sensors in-field. In this article, we survey the rapidly growing research landscape of low-cost sensor technologies for air quality monitoring and their calibration using machine learning techniques. We also identify open research challenges and present directions for future research.

Xiaoli Liu, Jianqin Yin, Jin Liu et al.

Human motion prediction is an increasingly interesting topic in computer vision and robotics. In this paper, we propose a new 2D CNN based network, TrajectoryNet, to predict future poses in the trajectory space. Compared with most existing methods, our model focuses on modeling the motion dynamics with coupled spatio-temporal features, local-global spatial features and global temporal co-occurrence features of the previous pose sequence. Specifically, the coupled spatio-temporal features describe the spatial and temporal structure information hidden in the natural human motion sequence, which can be mined by covering the space and time dimensions of the input pose sequence with the convolutional filters. The local-global spatial features that encode different correlations of different joints of the human body (e.g. strong correlations between joints of one limb, weak correlations between joints of different limbs) are captured hierarchically by enlarging the receptive field layer by layer and residual connections from the lower layers to the deeper layers in our proposed convolutional network. And the global temporal co-occurrence features represent the co-occurrence relationship that different subsequences in a complex motion sequence are appeared simultaneously, which can be obtained automatically with our proposed TrajectoryNet by reorganizing the temporal information as the depth dimension of the input tensor. Finally, future poses are approximated based on the captured motion dynamics features. Extensive experiments show that our method achieves state-of-the-art performance on three challenging benchmarks (e.g. Human3.6M, G3D, and FNTU), which demonstrates the effectiveness of our proposed method. The code will be available if the paper is accepted.

Xiaoli Liu, Jianqin Yin, Huaping Liu et al.

Pose prediction is to predict future poses given a window of previous poses. In this paper, we propose a new problem that predicts poses using 3D joint coordinate sequences. Different from the traditional pose prediction based on Mocap frames, this problem is convenient to use in real applications due to its simple sensors to capture data. We also present a new framework, PISEP^2 (Pseudo Image Sequence Evolution based 3D Pose Prediction), to address this new problem. Specifically, a skeletal representation is proposed by transforming the joint coordinate sequence into an image sequence, which can model the different correlations of different joints. With this image based skeletal representation, we model the pose prediction as the evolution of image sequence. Moreover, a novel inference network is proposed to predict all future poses in one step by decoupling the decoders in a non-recursive manner. Compared with the recursive sequence to sequence model, we can improve the computational efficiency and avoid error accumulation significantly. Extensive experiments are carried out on two benchmark datasets (e.g. G3D and FNTU). The proposed method achieves the state-of-the-art performance on both datasets, which demonstrates the effectiveness of our proposed method.

Andre Goncalves, Xiaoli Liu, Arindam Banerjee

Alternating Direction Method of Multipliers (ADMM) has become a widely used optimization method for convex problems, particularly in the context of data mining in which large optimization problems are often encountered. ADMM has several desirable properties, including the ability to decompose large problems into smaller tractable sub-problems and ease of parallelization, that are essential in these scenarios. The most common form of ADMM is the two-block, in which two sets of primal variables are updated alternatingly. Recent years have seen advances in multi-block ADMM, which update more than two blocks of primal variables sequentially. In this paper, we study the empirical question: {\em Is two-block ADMM always comparable with sequential multi-block ADMM solving an equivalent problem?} In the context of optimization problems arising in multi-task learning, through a comprehensive set of experiments we surprisingly show that multi-block ADMM consistently outperformed two-block ADMM on optimization performance, and as a consequence on prediction performance, across all datasets and for the entire range of dual step sizes. Our results have an important practical implication: rather than simply using the popular two-block ADMM, one may considerably benefit from experimenting with multi-block ADMM applied to an equivalent problem.