Jiayi Zhao

Jingsheng Li, Tianxiang Xue, Jiayi Zhao et al.

The complexity of clouds, particularly in terms of texture detail at high resolutions, has not been well explored by most existing cloud detection networks. This paper introduces the High-Resolution Cloud Detection Network (HR-cloud-Net), which utilizes a hierarchical high-resolution integration approach. HR-cloud-Net integrates a high-resolution representation module, layer-wise cascaded feature fusion module, and multi-resolution pyramid pooling module to effectively capture complex cloud features. This architecture preserves detailed cloud texture information while facilitating feature exchange across different resolutions, thereby enhancing overall performance in cloud detection. Additionally, a novel approach is introduced wherein a student view, trained on noisy augmented images, is supervised by a teacher view processing normal images. This setup enables the student to learn from cleaner supervisions provided by the teacher, leading to improved performance. Extensive evaluations on three optical satellite image cloud detection datasets validate the superior performance of HR-cloud-Net compared to existing methods.The source code is available at \url{https://github.com/kunzhan/HR-cloud-Net}.

Zhaopei Huang, Yanfeng Jia, Jiayi Zhao et al.

Developing compassionate interactive systems requires agents to not only understand user emotions but also provide diverse, substantive support. While recent works explore empathetic dialogue generation, they remain limited in response form and content, struggling to satisfy diverse needs across users and contexts. To address this, we explore empowering agents with external tools to execute diverse actions. Grounded in the psychological concept of "social support", this paradigm delivers substantive, human-like companionship. Specifically, we first design a dozen user-centric tools simulating various multimedia applications, which can cover different types of social support behaviors in human-agent interaction scenarios. We then construct ComPASS-Bench, the first personalized social support benchmark for LLM-based agents, via multi-step automated synthesis and manual refinement. Based on ComPASS-Bench, we further synthesize tool use records to fine-tune the Qwen3-8B model, yielding a task-specific ComPASS-Qwen. Comprehensive evaluations across two settings reveal that while the evaluated LLMs can generate valid tool-calling requests with high success rates, significant gaps remain in final response quality. Moreover, tool-augmented responses achieve better overall performance than directly producing conversational empathy. Notably, our trained ComPASS-Qwen demonstrates substantial improvements over its base model, achieving comparable performance to several large-scale models. Our code and data are available at https://github.com/hzp3517/ComPASS.

Denizalp Goktas, Jiayi Zhao, Amy Greenwald

The behavior of no-regret learning algorithms is well understood in two-player min-max (i.e, zero-sum) games. In this paper, we investigate the behavior of no-regret learning in min-max games with dependent strategy sets, where the strategy of the first player constrains the behavior of the second. Such games are best understood as sequential, i.e., min-max Stackelberg, games. We consider two settings, one in which only the first player chooses their actions using a no-regret algorithm while the second player best responds, and one in which both players use no-regret algorithms. For the former case, we show that no-regret dynamics converge to a Stackelberg equilibrium. For the latter case, we introduce a new type of regret, which we call Lagrangian regret, and show that if both players minimize their Lagrangian regrets, then play converges to a Stackelberg equilibrium. We then observe that online mirror descent (OMD) dynamics in these two settings correspond respectively to a known nested (i.e., sequential) gradient descent-ascent (GDA) algorithm and a new simultaneous GDA-like algorithm, thereby establishing convergence of these algorithms to Stackelberg equilibrium. Finally, we analyze the robustness of OMD dynamics to perturbations by investigating online min-max Stackelberg games. We prove that OMD dynamics are robust for a large class of online min-max games with independent strategy sets. In the dependent case, we demonstrate the robustness of OMD dynamics experimentally by simulating them in online Fisher markets, a canonical example of a min-max Stackelberg game with dependent strategy sets.

Sean Grullon, Vaughn Spurrier, Jiayi Zhao et al.

Although melanoma occurs more rarely than several other skin cancers, patients' long term survival rate is extremely low if the diagnosis is missed. Diagnosis is complicated by a high discordance rate among pathologists when distinguishing between melanoma and benign melanocytic lesions. A tool that provides potential concordance information to healthcare providers could help inform diagnostic, prognostic, and therapeutic decision-making for challenging melanoma cases. We present a melanoma concordance regression deep learning model capable of predicting the concordance rate of invasive melanoma or melanoma in-situ from digitized Whole Slide Images (WSIs). The salient features corresponding to melanoma concordance were learned in a self-supervised manner with the contrastive learning method, SimCLR. We trained a SimCLR feature extractor with 83,356 WSI tiles randomly sampled from 10,895 specimens originating from four distinct pathology labs. We trained a separate melanoma concordance regression model on 990 specimens with available concordance ground truth annotations from three pathology labs and tested the model on 211 specimens. We achieved a Root Mean Squared Error (RMSE) of 0.28 +/- 0.01 on the test set. We also investigated the performance of using the predicted concordance rate as a malignancy classifier, and achieved a precision and recall of 0.85 +/- 0.05 and 0.61 +/- 0.06, respectively, on the test set. These results are an important first step for building an artificial intelligence (AI) system capable of predicting the results of consulting a panel of experts and delivering a score based on the degree to which the experts would agree on a particular diagnosis. Such a system could be used to suggest additional testing or other action such as ordering additional stains or genetic tests.

Jiayi Zhao, Alison Wun-lam Yeung, Ali Muhammad et al.

Under high-intensity rail operations, rail tracks endure considerable stresses resulting in various defects such as corrugation and spellings. Failure to effectively detect defects and provide maintenance in time would compromise service reliability and public safety. While advanced models have been developed in recent years, efficiently identifying small-scale rail defects has not yet been studied, especially for categories such as Dirt or Squat on rail surface. To address this challenge, this study utilizes Swin Transformer (SwinT) as baseline and incorporates the Convolutional Block Attention Module (CBAM) for enhancement. Our proposed method integrates CBAM successively within the swin transformer blocks, resulting in significant performance improvement in rail defect detection, particularly for categories with small instance sizes. The proposed framework is named CBAM-Enhanced Swin Transformer in Block Level (CBAM-SwinT-BL). Experiment and ablation study have proven the effectiveness of the framework. The proposed framework has a notable improvement in the accuracy of small size defects, such as dirt and dent categories in RIII dataset, with mAP-50 increasing by +23.0% and +38.3% respectively, and the squat category in MUET dataset also reaches +13.2% higher than the original model. Compares to the original SwinT, CBAM-SwinT-BL increase overall precision around +5% in the MUET dataset and +7% in the RIII dataset, reaching 69.1% and 88.1% respectively. Meanwhile, the additional module CBAM merely extend the model training speed by an average of +0.04s/iteration, which is acceptable compared to the significant improvement in system performance.

Jiayi Zhao, Fei Teng, Kai Luo et al.

The perception capability of robotic systems relies on the richness of the dataset. Although Segment Anything Model 2 (SAM2), trained on large datasets, demonstrates strong perception potential in perception tasks, its inherent training paradigm prevents it from being suitable for RGB-T tasks. To address these challenges, we propose SHIFNet, a novel SAM2-driven Hybrid Interaction Paradigm that unlocks the potential of SAM2 with linguistic guidance for efficient RGB-Thermal perception. Our framework consists of two key components: (1) Semantic-Aware Cross-modal Fusion (SACF) module that dynamically balances modality contributions through text-guided affinity learning, overcoming SAM2's inherent RGB bias; (2) Heterogeneous Prompting Decoder (HPD) that enhances global semantic information through a semantic enhancement module and then combined with category embeddings to amplify cross-modal semantic consistency. With 32.27M trainable parameters, SHIFNet achieves state-of-the-art segmentation performance on public benchmarks, reaching 89.8% on PST900 and 67.8% on FMB, respectively. The framework facilitates the adaptation of pre-trained large models to RGB-T segmentation tasks, effectively mitigating the high costs associated with data collection while endowing robotic systems with comprehensive perception capabilities. The source code will be made publicly available at https://github.com/iAsakiT3T/SHIFNet.

Sihan Wang, Jiayi Zhao

Activation steering methods modify intermediate representations of language models to control output behavior, but universally assume the activation space is Euclidean. We show this assumption fails drastically: the local geometry induced by the model's own output behavior -- the Fisher information metric of the softmax layer, pulled back through the Jacobian of subsequent layers -- deviates from the Euclidean metric by over 97% in relative spectral norm on GPT-2, with an effective dimensionality of only 2--17% of the ambient space. From this pullback Fisher metric, we derive a closed-form steering equation that identifies the minimum-distortion direction for any target concept, yielding a closed-form optimal direction at each point that can be applied iteratively without manifold fitting or data-driven geometry estimation. We call the resulting framework FishBack. The metric admits a layer-wise recursive decomposition, which reveals that existing methods -- CAA, ActAdd, ITI, and others -- each implicitly adopt a particular approximate metric, and that their performance gaps are quantitatively predicted by a single spectral diagnostic: the ratio of their implicit metric's cost to the Fisher-optimal cost. On GPT-2, iterative pullback steering consistently outperforms all Euclidean baselines across three verb-morphology concepts and four layers, with off-target KL reductions of $1.3\times$--$2.5\times$ relative to Euclidean gradient ascent and $1.5\times$ relative to CAA at matched concept probability.

Yuemei Xu, Ling Hu, Jiayi Zhao et al.

Based on the foundation of Large Language Models (LLMs), Multilingual LLMs (MLLMs) have been developed to address the challenges faced in multilingual natural language processing, hoping to achieve knowledge transfer from high-resource languages to low-resource languages. However, significant limitations and challenges still exist, such as language imbalance, multilingual alignment, and inherent bias. In this paper, we aim to provide a comprehensive analysis of MLLMs, delving deeply into discussions surrounding these critical issues. First of all, we start by presenting an overview of MLLMs, covering their evolutions, key techniques, and multilingual capacities. Secondly, we explore the multilingual training corpora of MLLMs and the multilingual datasets oriented for downstream tasks that are crucial to enhance the cross-lingual capability of MLLMs. Thirdly, we survey the state-of-the-art studies of multilingual representations and investigate whether the current MLLMs can learn a universal language representation. Fourthly, we discuss bias on MLLMs, including its categories, evaluation metrics, and debiasing techniques. Finally, we discuss existing challenges and point out promising research directions of MLLMs.

Jiayi Zhao

Augmented Lagrangian and optimistic primal--dual methods stabilize equality-constrained optimization through seemingly different mechanisms: the former adds constraint-dependent primal curvature, while the latter adds dual memory. Recent work has shown that these mechanisms are equivalent for scalar parameters. We extend this equivalence to matrix-valued correction. We prove an additivity principle: for symmetric matrix parameters, the ideal primal trajectory depends only on the summed correction matrix, not on how it is split between augmented and optimistic channels. This exposes a design freedom: algebraically equivalent decompositions can have different finite-step feasibility because augmented correction affects primal curvature, whereas optimistic correction affects the scale of the dual memory correction. We formulate the resulting step-size-limited design problem and derive a closed-form hybrid rule that selects a matrix correction, splits it between the two channels, and chooses primal and dual steps using local spectral weights. Experiments on nonlinear equality-constrained problems with controlled constraint-Jacobian conditioning show that the hybrid design improves over pure augmented and pure optimistic endpoints, closely tracks a grid-search hybrid oracle, and is competitive with first-order primal--dual baselines under mild-to-moderate ill-conditioning. The experiments also identify the expected limitation: exact cancellation requires increasingly large matrix corrections as the constraint Jacobian becomes ill-conditioned.

Jiayi Zhao, Changlu Chen, Jingsheng Li et al.

Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages unlabeled remote sensing imagery through view-consistency learning combined with scene-mixing augmentations. An observation behind CloudMatch is that cloud patterns exhibit structural diversity and contextual variability across different scenes and within the same scene category. Our key insight is that enforcing prediction consistency across diversely augmented views, incorporating both inter-scene and intra-scene mixing, enables the model to capture the structural diversity and contextual richness of cloud patterns. Specifically, CloudMatch generates one weakly augmented view along with two complementary strongly augmented views for each unlabeled image: one integrates inter-scene patches to simulate contextual variety, while the other employs intra-scene mixing to preserve semantic coherence. This approach guides pseudolabel generation and enhances generalization. Extensive experiments show that CloudMatch achieves good performance, demonstrating its capability to utilize unlabeled data efficiently and advance semi-supervised cloud detection.

Yuang Jia, Jinlong Wang, Jiayi Zhao et al.

This paper presents an effective solution for view extrapolation in autonomous driving scenarios. Recent approaches focus on generating shifted novel view images from given viewpoints using diffusion models. However, these methods heavily rely on priors such as LiDAR point clouds, 3D bounding boxes, and lane annotations, which demand expensive sensors or labor-intensive labeling, limiting applicability in real-world deployment. In this work, with only images and optional camera poses, we first estimate a global static point cloud and per-frame dynamic point clouds, fusing them into a unified representation. We then employ a deformable 4D Gaussian framework to reconstruct the scene. The initially trained 4D Gaussian model renders degraded and pseudo-images to train a video diffusion model. Subsequently, progressively shifted Gaussian renderings are iteratively refined by the diffusion model,and the enhanced results are incorporated back as training data for 4DGS. This process continues until extrapolation reaches the target viewpoints. Compared with baselines, our method produces higher-quality images at novel extrapolated viewpoints.

Songjiang Lai, Tsun-Hin Cheung, Jiayi Zhao et al.

Rolling bearings play a crucial role in industrial machinery, directly influencing equipment performance, durability, and safety. However, harsh operating conditions, such as high speeds and temperatures, often lead to bearing malfunctions, resulting in downtime, economic losses, and safety hazards. This paper proposes the Residual Attention Single-Head Vision Transformer Network (RA-SHViT-Net) for fault diagnosis in rolling bearings. Vibration signals are transformed from the time to frequency domain using the Fast Fourier Transform (FFT) before being processed by RA-SHViT-Net. The model employs the Single-Head Vision Transformer (SHViT) to capture local and global features, balancing computational efficiency and predictive accuracy. To enhance feature extraction, the Adaptive Hybrid Attention Block (AHAB) integrates channel and spatial attention mechanisms. The network architecture includes Depthwise Convolution, Single-Head Self-Attention, Residual Feed-Forward Networks (Res-FFN), and AHAB modules, ensuring robust feature representation and mitigating gradient vanishing issues. Evaluation on the Case Western Reserve University and Paderborn University datasets demonstrates the RA-SHViT-Net's superior accuracy and robustness in complex, noisy environments. Ablation studies further validate the contributions of individual components, establishing RA-SHViT-Net as an effective tool for early fault detection and classification, promoting efficient maintenance strategies in industrial settings. Keywords: rolling bearings, fault diagnosis, Vision Transformer, attention mechanism, noisy environments, Fast Fourier Transform (FFT)

Shenghao Ren, Yi Lu, Jiayi Huang et al.

Existing human Motion Capture (MoCap) methods mostly focus on the visual similarity while neglecting the physical plausibility. As a result, downstream tasks such as driving virtual human in 3D scene or humanoid robots in real world suffer from issues such as timing drift and jitter, spatial problems like sliding and penetration, and poor global trajectory accuracy. In this paper, we revisit human MoCap from the perspective of interaction between human body and physical world by exploring the role of pressure. Firstly, we construct a large-scale human Motion capture dataset with Pressure, RGB and Optical sensors (named MotionPRO), which comprises 70 volunteers performing 400 types of motion, encompassing a total of 12.4M pose frames. Secondly, we examine both the necessity and effectiveness of the pressure signal through two challenging tasks: (1) pose and trajectory estimation based solely on pressure: We propose a network that incorporates a small kernel decoder and a long-short-term attention module, and proof that pressure could provide accurate global trajectory and plausible lower body pose. (2) pose and trajectory estimation by fusing pressure and RGB: We impose constraints on orthographic similarity along the camera axis and whole-body contact along the vertical axis to enhance the cross-attention strategy to fuse pressure and RGB feature maps. Experiments demonstrate that fusing pressure with RGB features not only significantly improves performance in terms of objective metrics, but also plausibly drives virtual humans (SMPL) in 3D scene. Furthermore, we demonstrate that incorporating physical perception enables humanoid robots to perform more precise and stable actions, which is highly beneficial for the development of embodied artificial intelligence. Project page is available at: https://nju-cite-mocaphumanoid.github.io/MotionPRO/

Nan Gao, Yihua Bao, Dongdong Weng et al.

Co-speech gesture generation enhances human-computer interaction realism through speech-synchronized gesture synthesis. However, generating semantically meaningful gestures remains a challenging problem. We propose SARGes, a novel framework that leverages large language models (LLMs) to parse speech content and generate reliable semantic gesture labels, which subsequently guide the synthesis of meaningful co-speech gestures.First, we constructed a comprehensive co-speech gesture ethogram and developed an LLM-based intent chain reasoning mechanism that systematically parses and decomposes gesture semantics into structured inference steps following ethogram criteria, effectively guiding LLMs to generate context-aware gesture labels. Subsequently, we constructed an intent chain-annotated text-to-gesture label dataset and trained a lightweight gesture label generation model, which then guides the generation of credible and semantically coherent co-speech gestures. Experimental results demonstrate that SARGes achieves highly semantically-aligned gesture labeling (50.2% accuracy) with efficient single-pass inference (0.4 seconds). The proposed method provides an interpretable intent reasoning pathway for semantic gesture synthesis.

Jiayi Zhao, Dongdong Weng, Qiuxin Du et al.

Human motion generation involves creating natural sequences of human body poses, widely used in gaming, virtual reality, and human-computer interaction. It aims to produce lifelike virtual characters with realistic movements, enhancing virtual agents and immersive experiences. While previous work has focused on motion generation based on signals like movement, music, text, or scene background, the complexity of human motion and its relationships with these signals often results in unsatisfactory outputs. Manifold learning offers a solution by reducing data dimensionality and capturing subspaces of effective motion. In this review, we present a comprehensive overview of manifold applications in human motion generation, one of the first in this domain. We explore methods for extracting manifolds from unstructured data, their application in motion generation, and discuss their advantages and future directions. This survey aims to provide a broad perspective on the field and stimulate new approaches to ongoing challenges.

Tianxiang Xue, Jiayi Zhao, Jingsheng Li et al.

Remote sensing images are frequently obscured by cloud cover, posing significant challenges to data integrity and reliability. Effective cloud detection requires addressing both short-range spatial redundancies and long-range atmospheric similarities among cloud patches. Convolutional neural networks are effective at capturing local spatial dependencies, while Mamba has strong capabilities in modeling long-range dependencies. To fully leverage both local spatial relations and long-range dependencies, we propose CD-Mamba, a hybrid model that integrates convolution and Mamba's state-space modeling into a unified cloud detection network. CD-Mamba is designed to comprehensively capture pixelwise textural details and long term patchwise dependencies for cloud detection. This design enables CD-Mamba to manage both pixel-wise interactions and extensive patch-wise dependencies simultaneously, improving detection accuracy across diverse spatial scales. Extensive experiments validate the effectiveness of CD-Mamba and demonstrate its superior performance over existing methods.

Yixiao Chen, Bin Liang, Hanzhi Guo et al.

Integrating inverse rendering with multi-view photometric stereo (MVPS) yields more accurate 3D reconstructions than the inverse rendering approaches that rely on fixed environment illumination. However, efficient inverse rendering with MVPS remains challenging. To fill this gap, we introduce the Gaussian Splatting for Multi-view Photometric Stereo (PS-GS), which efficiently and jointly estimates the geometry, materials, and lighting of the object that is illuminated by diverse directional lights (multi-light). Our method first reconstructs a standard 2D Gaussian splatting model as the initial geometry. Based on the initialization model, it then proceeds with the deferred inverse rendering by the full rendering equation containing a lighting-computing multi-layer perceptron. During the whole optimization, we regularize the rendered normal maps by the uncalibrated photometric stereo estimated normals. We also propose the 2D Gaussian ray-tracing for single directional light to refine the incident lighting. The regularizations and the use of multi-view and multi-light images mitigate the ill-posed problem of inverse rendering. After optimization, the reconstructed object can be used for novel-view synthesis, relighting, and material and shape editing. Experiments on both synthetic and real datasets demonstrate that our method outperforms prior works in terms of reconstruction accuracy and computational efficiency.

Ruimin Feng, Jiayi Zhao, He Wang et al.

Quantitative susceptibility mapping (QSM) has demonstrated great potential in quantifying tissue susceptibility in various brain diseases. However, the intrinsic ill-posed inverse problem relating the tissue phase to the underlying susceptibility distribution affects the accuracy for quantifying tissue susceptibility. Recently, deep learning has shown promising results to improve accuracy by reducing the streaking artifacts. However, there exists a mismatch between the observed phase and the theoretical forward phase estimated by the susceptibility label. In this study, we proposed a model-based deep learning architecture that followed the STI (susceptibility tensor imaging) physical model, referred to as MoDL-QSM. Specifically, MoDL-QSM accounts for the relationship between STI-derived phase contrast induced by the susceptibility tensor terms (ki13,ki23,ki33) and the acquired single-orientation phase. The convolution neural networks are embedded into the physical model to learn a regularization term containing prior information. ki33 and phase induced by ki13 and ki23 terms were used as the labels for network training. Quantitative evaluation metrics (RSME, SSIM, and HFEN) were compared with recently developed deep learning QSM methods. The results showed that MoDL-QSM achieved superior performance, demonstrating its potential for future applications.

Haiyang Liu, Yichen Wang, Jiayi Zhao et al.

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear. Since it is impractical to collect labeled data for all categories, how to conduct zero-shot learning in semantic segmentation establishes an important problem. Although the attribute embedding of categories can promote effective knowledge transfer across different categories, the prediction of segmentation network reveals obvious bias to seen categories. In this paper, we propose an easy-to-implement transductive approach to alleviate the prediction bias in zero-shot semantic segmentation. Our method assumes that both the source images with full pixel-level labels and unlabeled target images are available during training. To be specific, the source images are used to learn the relationship between visual images and semantic embeddings, while the target images are used to alleviate the prediction bias towards seen categories. We conduct comprehensive experiments on diverse split s of the PASCAL dataset. The experimental results clearly demonstrate the effectiveness of our method.