Jin Li

Jin Li, Yaoming Wang, Xiaopeng Zhang et al.

Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require high-resolution input, the complexity of ViTs increases significantly. Notably, dense prediction tasks, such as semantic segmentation or object detection, emphasize more on the contours or shapes of objects, while the texture inside objects is less informative. Motivated by this observation, we propose to apply adaptive resolution for different regions in the image according to their importance. Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence. Once the representative tokens are determined, we proceed to merge other tokens into their closest representative token. Consequently, semantic similar tokens are merged together to form low-resolution regions, while semantic irrelevant tokens are preserved independently as high-resolution regions. This strategy effectively reduces the number of tokens, allowing subsequent layers to handle a reduced token sequence and achieve acceleration. We evaluate our proposed method on three different datasets and observe promising performance. For example, the "Segmenter ViT-L" model can be accelerated by 48% FPS without fine-tuning, while maintaining the performance. Additionally, our method can be applied to accelerate fine-tuning as well. Experimental results demonstrate that we can save 52% training time while accelerating 2.46 times FPS with only a 0.09% performance drop. The code is available at https://github.com/caddyless/ailurus/tree/main.

Jiacheng Li, Tong Zhao, Jin Li et al.

Sequential recommendation aims to model dynamic user behavior from historical interactions. Self-attentive methods have proven effective at capturing short-term dynamics and long-term preferences. Despite their success, these approaches still struggle to model sparse data, on which they struggle to learn high-quality item representations. We propose to model user dynamics from shopping intents and interacted items simultaneously. The learned intents are coarse-grained and work as prior knowledge for item recommendation. To this end, we present a coarse-to-fine self-attention framework, namely CaFe, which explicitly learns coarse-grained and fine-grained sequential dynamics. Specifically, CaFe first learns intents from coarse-grained sequences which are dense and hence provide high-quality user intent representations. Then, CaFe fuses intent representations into item encoder outputs to obtain improved item representations. Finally, we infer recommended items based on representations of items and corresponding intents. Experiments on sparse datasets show that CaFe outperforms state-of-the-art self-attentive recommenders by 44.03% NDCG@5 on average.

SII-GAIR, Sand. ai, Ethan Chern et al.

We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio using a single-stream Transformer that processes text, video, and audio within a unified token sequence via self-attention only. This single-stream design avoids the complexity of multi-stream or cross-attention architectures while remaining easy to optimize with standard training and inference infrastructure. The model is particularly strong in human-centric scenarios, producing expressive facial performance, natural speech-expression coordination, realistic body motion, and precise audio-video synchronization. It supports multilingual spoken generation across Chinese (Mandarin and Cantonese), English, Japanese, Korean, German, and French. For efficient inference, we combine the single-stream backbone with model distillation, latent-space super-resolution, and a Turbo VAE decoder, enabling generation of a 5-second 256p video in 2 seconds on a single H100 GPU. In automatic evaluation, daVinci-MagiHuman achieves the highest visual quality and text alignment among leading open models, along with the lowest word error rate (14.60%) for speech intelligibility. In pairwise human evaluation, it achieves win rates of 80.0% against Ovi 1.1 and 60.9% against LTX 2.3 over 2000 comparisons. We open-source the complete model stack, including the base model, the distilled model, the super-resolution model, and the inference codebase.

Trong Nghia Hoang, Anoop Deoras, Tong Zhao et al.

This paper studies the item-to-item recommendation problem in recommender systems from a new perspective of metric learning via implicit feedback. We develop and investigate a personalizable deep metric model that captures both the internal contents of items and how they were interacted with by users. There are two key challenges in learning such model. First, there is no explicit similarity annotation, which deviates from the assumption of most metric learning methods. Second, these approaches ignore the fact that items are often represented by multiple sources of meta data and different users use different combinations of these sources to form their own notion of similarity. To address these challenges, we develop a new metric representation embedded as kernel parameters of a probabilistic model. This helps express the correlation between items that a user has interacted with, which can be used to predict user interaction with new items. Our approach hinges on the intuition that similar items induce similar interactions from the same user, thus fitting a metric-parameterized model to predict an implicit feedback signal could indirectly guide it towards finding the most suitable metric for each user. To this end, we also analyze how and when the proposed method is effective from a theoretical lens. Its empirical effectiveness is also demonstrated on several real-world datasets.

Dongsheng Jiang, Yuchen Liu, Songlin Liu et al.

Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications and the availability of diverse instruction tuning data, existing approaches often rely on CLIP or its variants as the visual branch, and merely extract features from the deep layers. However, these methods lack a comprehensive analysis of the visual encoders in MLLMs. In this paper, we conduct an extensive investigation into the effectiveness of different vision encoders within MLLMs. Our findings reveal that the shallow layer features of CLIP offer particular advantages for fine-grained tasks such as grounding and region understanding. Surprisingly, the vision-only model DINO, which is not pretrained with text-image alignment, demonstrates promising performance as a visual branch within MLLMs. By simply equipping it with an MLP layer for alignment, DINO surpasses CLIP in fine-grained related perception tasks. Building upon these observations, we propose a simple yet effective feature merging strategy, named COMM, that integrates CLIP and DINO with Multi-level features Merging, to enhance the visual capabilities of MLLMs. We evaluate COMM through comprehensive experiments on a wide range of benchmarks, including image captioning, visual question answering, visual grounding, and object hallucination. Experimental results demonstrate the superior performance of COMM compared to existing methods, showcasing its enhanced visual capabilities within MLLMs.

Yuchen Zhuang, Xin Shen, Yan Zhao et al. · amazon-science, tsinghua

Sequential recommendation requires understanding the dynamic patterns of users' behaviors, contexts, and preferences from their historical interactions. Most existing works focus on modeling user-item interactions only from the item level, ignoring that they are driven by latent shopping intentions (e.g., ballpoint pens, miniatures, etc). The detection of the underlying shopping intentions of users based on their historical interactions is a crucial aspect for e-commerce platforms, such as Amazon, to enhance the convenience and efficiency of their customers' shopping experiences. Despite its significance, the area of main shopping intention detection remains under-investigated in the academic literature. To fill this gap, we propose a graph-regularized stochastic Transformer method, G-STO. By considering intentions as sets of products and user preferences as compositions of intentions, we model both of them as stochastic Gaussian embeddings in the latent representation space. Instead of training the stochastic representations from scratch, we develop a global intention relational graph as prior knowledge for regularization, allowing relevant shopping intentions to be distributionally close. Finally, we feed the newly regularized stochastic embeddings into Transformer-based models to encode sequential information from the intention transitions. We evaluate our main shopping intention identification model on three different real-world datasets, where G-STO achieves significantly superior performances to the baselines by 18.08% in Hit@1, 7.01% in Hit@10, and 6.11% in NDCG@10 on average.

Ghadeer Ghosheh, Jin Li, Tingting Zhu

Electronic Health Records (EHRs) are a valuable asset to facilitate clinical research and point of care applications; however, many challenges such as data privacy concerns impede its optimal utilization. Deep generative models, particularly, Generative Adversarial Networks (GANs) show great promise in generating synthetic EHR data by learning underlying data distributions while achieving excellent performance and addressing these challenges. This work aims to review the major developments in various applications of GANs for EHRs and provides an overview of the proposed methodologies. For this purpose, we combine perspectives from healthcare applications and machine learning techniques in terms of source datasets and the fidelity and privacy evaluation of the generated synthetic datasets. We also compile a list of the metrics and datasets used by the reviewed works, which can be utilized as benchmarks for future research in the field. We conclude by discussing challenges in GANs for EHRs development and proposing recommended practices. We hope that this work motivates novel research development directions in the intersection of healthcare and machine learning.

Tan H. Nguyen, Dinkar Juyal, Jin Li et al.

Differences in staining and imaging procedures can cause significant color variations in histopathology images, leading to poor generalization when deploying deep-learning models trained from a different data source. Various color augmentation methods have been proposed to generate synthetic images during training to make models more robust, eliminating the need for stain normalization during test time. Many color augmentation methods leverage domain labels to generate synthetic images. This approach causes three significant challenges to scaling such a model. Firstly, incorporating data from a new domain into deep-learning models trained on existing domain labels is not straightforward. Secondly, dependency on domain labels prevents the use of pathology images without domain labels to improve model performance. Finally, implementation of these methods becomes complicated when multiple domain labels (e.g., patient identification, medical center, etc) are associated with a single image. We introduce ContriMix, a novel domain label free stain color augmentation method based on DRIT++, a style-transfer method. Contrimix leverages sample stain color variation within a training minibatch and random mixing to extract content and attribute information from pathology images. This information can be used by a trained ContriMix model to create synthetic images to improve the performance of existing classifiers. ContriMix outperforms competing methods on the Camelyon17-WILDS dataset. Its performance is consistent across different slides in the test set while being robust to the color variation from rare substances in pathology images. We make our code and trained ContriMix models available for research use. The code for ContriMix can be found at https://gitlab.com/huutan86/contrimix

Bowen Shi, Xiaopeng Zhang, Yaoming Wang et al.

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised pre-training excel at capturing longer-range global patterns and enabling better feature discrimination, while MIM can introduce more local and diverse attention across all transformer layers. In this paper, we explore how to obtain a model that combines their strengths. We start by examining previous feature distillation and mask feature reconstruction methods and identify their limitations. We find that their increasing diversity mainly derives from the asymmetric designs, but these designs may in turn compromise the discrimination ability. In order to better obtain both discrimination and diversity, we propose a simple but effective Hybrid Distillation strategy, which utilizes both the supervised/CL teacher and the MIM teacher to jointly guide the student model. Hybrid Distill imitates the token relations of the MIM teacher to alleviate attention collapse, as well as distills the feature maps of the supervised/CL teacher to enable discrimination. Furthermore, a progressive redundant token masking strategy is also utilized to reduce the distilling costs and avoid falling into local optima. Experiment results prove that Hybrid Distill can achieve superior performance on different benchmarks.

Jin Hao, Jiaxiang Liu, Jin Li et al.

A critical step in virtual dental treatment planning is to accurately delineate all tooth-bone structures from CBCT with high fidelity and accurate anatomical information. Previous studies have established several methods for CBCT segmentation using deep learning. However, the inherent resolution discrepancy of CBCT and the loss of occlusal and dentition information largely limited its clinical applicability. Here, we present a Deep Dental Multimodal Analysis (DDMA) framework consisting of a CBCT segmentation model, an intraoral scan (IOS) segmentation model (the most accurate digital dental model), and a fusion model to generate 3D fused crown-root-bone structures with high fidelity and accurate occlusal and dentition information. Our model was trained with a large-scale dataset with 503 CBCT and 28,559 IOS meshes manually annotated by experienced human experts. For CBCT segmentation, we use a five-fold cross validation test, each with 50 CBCT, and our model achieves an average Dice coefficient and IoU of 93.99% and 88.68%, respectively, significantly outperforming the baselines. For IOS segmentations, our model achieves an mIoU of 93.07% and 95.70% on the maxillary and mandible on a test set of 200 IOS meshes, which are 1.77% and 3.52% higher than the state-of-art method. Our DDMA framework takes about 20 to 25 minutes to generate the fused 3D mesh model following the sequential processing order, compared to over 5 hours by human experts. Notably, our framework has been incorporated into a software by a clear aligner manufacturer, and real-world clinical cases demonstrate that our model can visualize crown-root-bone structures during the entire orthodontic treatment and can predict risks like dehiscence and fenestration. These findings demonstrate the potential of multi-modal deep learning to improve the quality of digital dental models and help dentists make better clinical decisions.

Kamya Hari, Taha Binhuraib, Jin Li et al.

Encoding models provide a powerful framework for linking continuous stimulus features to neural activity; however, traditional voxelwise approaches are limited by measurement noise, inter-subject variability, and redundancy arising from spatially correlated voxels encoding overlapping neural signals. Here, we propose an independent component (IC)-based encoding framework that dissociates stimulus-driven and noise-driven signals in fMRI data. We decompose continuous fMRI data from naturalistic story listening into ICs using one subset of the data, and train encoding models on independent data to predict IC time series from large language model representations of linguistic input. Across subjects, a subset of ICs exhibited consistently high predictivity. These ICs were spatially and temporally consistent across subjects and included cognitive networks known to respond during story listening (auditory and language). Auditory component time series were strongly correlated with acoustic stimulus features, highlighting the interpretability of identified component time series. Components identified as noise or motion-related artifacts by ICA-AROMA showed uniformly poor predictive performance, confirming that highly predicted components reflect genuine stimulus-related neural signals rather than confounds. Overall, IC-based encoding models enable analyses at the level of functional networks, accommodating the variability in network locations across individuals and providing interpretable results that are easy to compare across subjects.

Dongwei Ren, Xinya Shu, Yu Li et al.

For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typically rely on training data collected by specialized imaging equipment, with the assumption that these pairs or triplets are perfectly aligned. However, in practical scenarios involving the collection of real-world data, direct acquisition of training triplets is infeasible, and training pairs inevitably encounter spatial misalignment issues. In this work, we introduce a reblurring-guided learning framework for single image defocus deblurring, enabling the learning of a deblurring network even with misaligned training pairs. By reconstructing spatially variant isotropic blur kernels, our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image, thereby addressing the misalignment issue while effectively extracting sharp textures from the all-in-focus sharp image. Moreover, spatially variant blur can be derived from the reblurring module, and serve as pseudo supervision for defocus blur map during training, interestingly transforming training pairs into training triplets. To leverage this pseudo supervision, we propose a lightweight defocus blur estimator coupled with a fusion block, which enhances deblurring performance through seamless integration with state-of-the-art deblurring networks. Additionally, we have collected a new dataset for single image defocus deblurring (SDD) with typical misalignments, which not only validates our proposed method but also serves as a benchmark for future research.

Song Li, Jiandong Zhou, Chong MO et al.

Graph convolutional networks (GCNs) is a class of artificial neural networks for processing data that can be represented as graphs. Since financial transactions can naturally be constructed as graphs, GCNs are widely applied in the financial industry, especially for financial fraud detection. In this paper, we focus on fraud detection on cryptocurrency truct networks. In the literature, most works focus on static networks. Whereas in this study, we consider the evolving nature of cryptocurrency networks, and use local structural as well as the balance theory to guide the training process. More specifically, we compute motif matrices to capture the local topological information, then use them in the GCN aggregation process. The generated embedding at each snapshot is a weighted average of embeddings within a time window, where the weights are learnable parameters. Since the trust networks is signed on each edge, balance theory is used to guide the training process. Experimental results on bitcoin-alpha and bitcoin-otc datasets show that the proposed model outperforms those in the literature.

Jin Li, Deepta Rajan, Chintan Shah et al.

Histopathology images are gigapixel-sized and include features and information at different resolutions. Collecting annotations in histopathology requires highly specialized pathologists, making it expensive and time-consuming. Self-training can alleviate annotation constraints by learning from both labeled and unlabeled data, reducing the amount of annotations required from pathologists. We study the design of teacher-student self-training systems for Non-alcoholic Steatohepatitis (NASH) using clinical histopathology datasets with limited annotations. We evaluate the models on in-distribution and out-of-distribution test data under clinical data shifts. We demonstrate that through self-training, the best student model statistically outperforms the teacher with a $3\%$ absolute difference on the macro F1 score. The best student model also approaches the performance of a fully supervised model trained with twice as many annotations.

Yun Piao, Hongbo Min, Hang Su et al.

The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making Human-in-the-Loop (HITL) supervision essential for mission-critical applications. In this paper, we present AgentBay, a novel sandbox service designed from the ground up for hybrid interaction. AgentBay provides secure, isolated execution environments spanning Windows, Linux, Android, Web Browsers, and Code interpreters. Its core contribution is a unified session accessible via a hybrid control interface: An AI agent can interact programmatically via mainstream interfaces (MCP, Open Source SDK), while a human operator can, at any moment, seamlessly take over full manual control. This seamless intervention is enabled by Adaptive Streaming Protocol (ASP). Unlike traditional VNC/RDP, ASP is specifically engineered for this hybrid use case, delivering an ultra-low-latency, smoother user experience that remains resilient even in weak network environments. It achieves this by dynamically blending command-based and video-based streaming, adapting its encoding strategy based on network conditions and the current controller (AI or human). Our evaluation demonstrates strong results in security, performance, and task completion rates. In a benchmark of complex tasks, the AgentBay (Agent + Human) model achieved more than 48% success rate improvement. Furthermore, our ASP protocol reduces bandwidth consumption by up to 50% compared to standard RDP, and in end-to-end latency with around 5% reduction, especially under poor network conditions. We posit that AgentBay provides a foundational primitive for building the next generation of reliable, human-supervised autonomous systems.

Xuanchen Li, Chenrui Cui, Tianrui Wang et al.

Speech Large Language Models (SpeechLLMs) have achieved breakthroughs in multilingual speech-to-text translation (S2TT). However, existing approaches often overlook semantic commonalities across source languages, leading to biased translation performance. In this work, we propose \textbf{POTSA} (Parallel Optimal Transport for Speech Alignment), a new framework based on cross-lingual parallel speech pairs and Optimal Transport (OT), designed to bridge high- and low-resource translation gaps. First, we introduce a Bias Compensation module to coarsely align initial speech representations across languages. Second, we impose token-level OT constraints on a Q-Former using parallel speech pairs to establish fine-grained consistency of representations. Then, we apply a layer scheduling strategy to focus OT constraints on the most semantically beneficial layers. Experiments on the FLEURS dataset show that our method achieves SOTA performance, with +0.93 BLEU on average over five common languages and +5.05 BLEU on zero-shot languages, using only 10 hours of parallel speech per source language.

Bowen Shi, Peisen Zhao, Zichen Wang et al.

Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual tasks. However, existing approaches primarily focus on training models to match global image representations with textual descriptions, thereby overlooking the critical alignment between local regions and corresponding text tokens. This paper extends CLIP with multi-granularity alignment. Notably, we deliberately construct a new dataset comprising pseudo annotations at various levels of granularities, encompassing image-level, region-level as well as pixel-level captions and tags. Accordingly, we develop a Unified Multi-Granularity learning framework, termed UMG-CLIP, which simultaneously empowers the model with versatile perception abilities across different levels of detail. With parameter efficient tuning, UMG-CLIP surpasses current widely used CLIP variants and achieves state-of-the-art performance on diverse image understanding benchmarks, including open-world recognition, retrieval, semantic segmentation, and panoptic segmentation tasks. We believe that UMG-CLIP represents a valuable advancement in vision-language foundation models. The code is available at https://github.com/lygsbw/UMG-CLIP.

Yanyan Liu, Changcheng Pan, Minglin Bie et al.

Visual-based target tracking is easily influenced by multiple factors, such as background clutter, targets fast-moving, illumination variation, object shape change, occlusion, etc. These factors influence the tracking accuracy of a target tracking task. To address this issue, an efficient real-time target tracking method based on a low-dimension adaptive feature fusion is proposed to allow us the simultaneous implementation of the high-accuracy and real-time target tracking. First, the adaptive fusion of a histogram of oriented gradient (HOG) feature and color feature is utilized to improve the tracking accuracy. Second, a convolution dimension reduction method applies to the fusion between the HOG feature and color feature to reduce the over-fitting caused by their high-dimension fusions. Third, an average correlation energy estimation method is used to extract the relative confidence adaptive coefficients to ensure tracking accuracy. We experimentally confirm the proposed method on an OTB100 data set. Compared with nine popular target tracking algorithms, the proposed algorithm gains the highest tracking accuracy and success tracking rate. Compared with the traditional Sum of Template and Pixel-wise LEarners (STAPLE) algorithm, the proposed algorithm can obtain a higher success rate and accuracy, improving by 0.023 and 0.019, respectively. The experimental results also demonstrate that the proposed algorithm can reach the real-time target tracking with 50 fps. The proposed method paves a more promising way for real-time target tracking tasks under a complex environment, such as appearance deformation, illumination change, motion blur, background, similarity, scale change, and occlusion.

Li Zhu, Jiawei Jiang, Lin Lu et al.

Multimodal magnetic resonance imaging (MRI) can reveal different patterns of human tissue and is crucial for clinical diagnosis. However, limited by cost, noise and manual labeling, obtaining diverse and reliable multimodal MR images remains a challenge. For the same lesion, different MRI manifestations have great differences in background information, coarse positioning and fine structure. In order to obtain better generation and segmentation performance, a coordination-spatial attention generation adversarial network (CASP-GAN) based on the cycle-consistent generative adversarial network (CycleGAN) is proposed. The performance of the generator is optimized by introducing the Coordinate Attention (CA) module and the Spatial Attention (SA) module. The two modules can make full use of the captured location information, accurately locating the interested region, and enhancing the generator model network structure. The ability to extract the structure information and the detailed information of the original medical image can help generate the desired image with higher quality. There exist some problems in the original CycleGAN that the training time is long, the parameter amount is too large, and it is difficult to converge. In response to this problem, we introduce the Coordinate Attention (CA) module to replace the Res Block to reduce the number of parameters, and cooperate with the spatial information extraction network above to strengthen the information extraction ability. On the basis of CASP-GAN, an attentional generative cross-modality segmentation (AGCMS) method is further proposed. This method inputs the modalities generated by CASP-GAN and the real modalities into the segmentation network for brain tumor segmentation. Experimental results show that CASP-GAN outperforms CycleGAN and some state-of-the-art methods in PSNR, SSMI and RMSE in most tasks.

Jin Li, Ziqiang He, Anwei Luo et al.

Imperceptible adversarial attacks aim to fool DNNs by adding imperceptible perturbation to the input data. Previous methods typically improve the imperceptibility of attacks by integrating common attack paradigms with specifically designed perception-based losses or the capabilities of generative models. In this paper, we propose Adversarial Attacks in Diffusion (AdvAD), a novel modeling framework distinct from existing attack paradigms. AdvAD innovatively conceptualizes attacking as a non-parametric diffusion process by theoretically exploring basic modeling approach rather than using the denoising or generation abilities of regular diffusion models requiring neural networks. At each step, much subtler yet effective adversarial guidance is crafted using only the attacked model without any additional network, which gradually leads the end of diffusion process from the original image to a desired imperceptible adversarial example. Grounded in a solid theoretical foundation of the proposed non-parametric diffusion process, AdvAD achieves high attack efficacy and imperceptibility with intrinsically lower overall perturbation strength. Additionally, an enhanced version AdvAD-X is proposed to evaluate the extreme of our novel framework under an ideal scenario. Extensive experiments demonstrate the effectiveness of the proposed AdvAD and AdvAD-X. Compared with state-of-the-art imperceptible attacks, AdvAD achieves an average of 99.9$\%$ (+17.3$\%$) ASR with 1.34 (-0.97) $l_2$ distance, 49.74 (+4.76) PSNR and 0.9971 (+0.0043) SSIM against four prevalent DNNs with three different architectures on the ImageNet-compatible dataset. Code is available at https://github.com/XianguiKang/AdvAD.

Jin Li, Kleanthis Malialis, Christos G. Panayiotou et al.

In today's digital world, the generation of vast amounts of streaming data in various domains has become ubiquitous. However, many of these data are unlabeled, making it challenging to identify events, particularly anomalies. This task becomes even more formidable in nonstationary environments where model performance can deteriorate over time due to concept drift. To address these challenges, this paper presents a novel method, VAE++ESDD, which employs incremental learning and two-level ensembling: an ensemble of Variational AutoEncoder(VAEs) for anomaly prediction, along with an ensemble of concept drift detectors. Each drift detector utilizes a statistical-based concept drift mechanism. To evaluate the effectiveness of VAE++ESDD, we conduct a comprehensive experimental study using real-world and synthetic datasets characterized by severely or extremely low anomalous rates and various drift characteristics. Our study reveals that the proposed method significantly outperforms both strong baselines and state-of-the-art methods.

Zezhong Ding, Jin Li, Xugang Wang et al.

Relational graph learning models relational databases as graphs and has demonstrated superior performance on a wide range of relational predictive tasks. However, existing methods struggle to capture long-range dependencies due to information decay in their message-passing mechanisms, and recent relational graph transformers remain limited in jointly modeling structural, semantic, and temporal information. In this paper, we propose GelGT, a Gaussian relational graph transformer that explicitly addresses these challenges. GelGT introduces a structure-semantic collaborative sampling strategy to preserve structural connectivity while filtering irrelevant semantic information, and incorporates a Gaussian graph attention mechanism with a learnable Gaussian bias on the sampled subgraphs to dynamically encode temporal dependencies. Extensive experiments on various real-world datasets demonstrate that GelGT achieves state-of-the-art downstream task performance, with up to a 13.8% improvement in predictive performance.

Dongjing Shan, Yamei Luo, Jiqing Xuan et al.

Early detection of myometrial invasion is critical for the staging and life-saving management of endometrial carcinoma (EC), a prevalent global malignancy. Transvaginal ultrasound serves as the primary, accessible screening modality in resource-constrained primary care settings; however, its diagnostic reliability is severely hindered by low tissue contrast, high operator dependence, and a pronounced scarcity of positive pathological samples. Existing artificial intelligence solutions struggle to overcome this severe class imbalance and the subtle imaging features of invasion, particularly under the strict computational limits of primary care clinics. Here we present an automated, highly efficient two-stage deep learning framework that resolves both data and computational bottlenecks in EC screening. To mitigate pathological data scarcity, we develop a structure-guided cross-modal generation network that synthesizes diverse, high-fidelity ultrasound images from unpaired magnetic resonance imaging (MRI) data, strictly preserving clinically essential anatomical junctions. Furthermore, we introduce a lightweight screening network utilizing gradient distillation, which transfers discriminative knowledge from a high-capacity teacher model to dynamically guide sparse attention towards task-critical regions. Evaluated on a large, multicenter cohort of 7,951 participants, our model achieves a sensitivity of 99.5\%, a specificity of 97.2\%, and an area under the curve of 0.987 at a minimal computational cost (0.289 GFLOPs), substantially outperforming the average diagnostic accuracy of expert sonographers. Our approach demonstrates that combining cross-modal synthetic augmentation with knowledge-driven efficient modeling can democratize expert-level, real-time cancer screening for resource-constrained primary care settings.

Zijie Meng, Jin Hao, Xiwei Dai et al.

Diagnosing and managing oral diseases necessitate advanced visual interpretation across diverse imaging modalities and integrated information synthesis. While current AI models excel at isolated tasks, they often fall short in addressing the complex, multimodal requirements of comprehensive clinical dental practice. Here we introduce DentVLM, a multimodal vision-language model engineered for expert-level oral disease diagnosis. DentVLM was developed using a comprehensive, large-scale, bilingual dataset of 110,447 images and 2.46 million visual question-answering (VQA) pairs. The model is capable of interpreting seven 2D oral imaging modalities across 36 diagnostic tasks, significantly outperforming leading proprietary and open-source models by 19.6% higher accuracy for oral diseases and 27.9% for malocclusions. In a clinical study involving 25 dentists, evaluating 1,946 patients and encompassing 3,105 QA pairs, DentVLM surpassed the diagnostic performance of 13 junior dentists on 21 of 36 tasks and exceeded that of 12 senior dentists on 12 of 36 tasks. When integrated into a collaborative workflow, DentVLM elevated junior dentists' performance to senior levels and reduced diagnostic time for all practitioners by 15-22%. Furthermore, DentVLM exhibited promising performance across three practical utility scenarios, including home-based dental health management, hospital-based intelligent diagnosis and multi-agent collaborative interaction. These findings establish DentVLM as a robust clinical decision support tool, poised to enhance primary dental care, mitigate provider-patient imbalances, and democratize access to specialized medical expertise within the field of dentistry.

Zhouwei Zhai, Min Yang, Jin Li

Faceted search acts as a critical bridge for navigating massive ecommerce catalogs, yet traditional systems rely on static rule-based extraction or statistical ranking, struggling with emerging vocabulary, semantic gaps, and a disconnect between facet selection and underlying retrieval. In this paper, we introduce GenFacet, an industrial-grade, end-to-end generative framework deployed at JD.com. GenFacet reframes faceted search as two coupled generative tasks within a unified Large Language Model: Context-Aware Facet Generation, which dynamically synthesizes trend-responsive navigation options, and Intent-Driven Query Rewriting, which translates user interactions into precise search queries to close the retrieval loop. To bridge the gap between generative capabilities and search utility, we propose a novel multi-task training pipeline combining teacher-student distillation with GRPO. This aligns the model with complex user preferences by directly optimizing for downstream search satisfaction. Validated on China's largest selfoperated e-commerce platform via rigorous offline evaluations and online A/B tests, GenFacet demonstrated substantial improvements. Specifically, online results reveal a relative increase of 42.0% in facet Click-Through Rate (CTR) and 2.0% in User Conversion Rate (UCVR). These outcomes provide strong evidence of the benefits of generative methods for improving query understanding and user engagement in large-scale information retrieval systems.

Shuai Shao, Yuhao Sun, Xing Chen et al.

Large-scale sparse multi-objective optimization problems (LSMOPs) are prevalent in real-world applications, where optimal solutions typically contain only a few nonzero variables, such as in adversarial attacks, critical node detection, and sparse signal reconstruction. Since the function evaluation of LSMOPs often relies on large-scale datasets involving a large number of decision variables, the search space becomes extremely high-dimensional. The coexistence of sparsity and high dimensionality greatly intensifies the conflict between exploration and exploitation, making it difficult for existing multi-objective evolutionary algorithms (MOEAs) to identify the critical nonzero decision variables within limited function evaluations. To address this challenge, this paper proposes an evolutionary algorithm with probabilistic annealing for large-scale sparse multi-objective optimization. The algorithm is driven by two probability vectors with distinct entropy characteristics: a convergence-oriented probability vector with relatively low entropy ensures stable exploitation, whereas an annealed probability vector with gradually decreasing entropy enables an adaptive transition from global exploration to local refinement. By integrating these complementary search dynamics, the proposed algorithm achieves a dynamic equilibrium between exploration and exploitation. Experimental results on benchmark problems and real-world applications demonstrate that the proposed algorithm outperforms state-of-the-art evolutionary algorithms in terms of both convergence and diversity.

Hengshuai Yao, Xing Chen, Ahmed Murtadha et al.

We introduce Focus, a method that learns which token pairs matter rather than approximating all of them. Learnable centroids assign tokens to groups; distant attention is restricted to same-group pairs while local attention operates at full resolution. Because all model weights stay frozen, Focus is purely additive: centroid-only training (as few as 148K parameters) improves domain perplexity with zero degradation on downstream benchmarks--from 124M to 70B parameters, across five attention architectures. No existing efficient attention method achieves this in the retrofit setting. At 124M, Focus surpasses full attention (30.3 vs 31.4 PPL); trained from scratch at 7B scale (2B tokens), Focus again beats full attention (13.82 vs 13.89 PPL). At inference, restricting each token to its top-k highest-scoring groups discretizes the soft routing into a hard sparsity pattern, yielding 2x speedup while beating the pretrained baseline (41.3 vs 42.8 PPL); decomposing this pattern into two standard FlashAttention calls reaches 8.6x wall-clock speedup at 1M tokens with no custom kernels. Unlike LoRA, centroid routing preserves alignment: instruction-tuned models retain TruthfulQA scores after adaptation, while LoRA degrades at every learning rate and rank. Sinkhorn normalization enforces balanced groups as a hard constraint, and the resulting groups discover interpretable linguistic categories without supervision.

Jin Li, Zezhong Ding, Xike Xie

Knowledge graphs (KGs) are vital for enabling knowledge reasoning across various domains. Recent KG reasoning methods that integrate both global and local information have achieved promising results. However, existing methods often suffer from score over-smoothing, which blurs the distinction between correct and incorrect answers and hinders reasoning effectiveness. To address this, we propose DuetGraph, a coarse-to-fine KG reasoning mechanism with dual-pathway global-local fusion. DuetGraph tackles over-smoothing by segregating -- rather than stacking -- the processing of local (via message passing) and global (via attention) information into two distinct pathways, preventing mutual interference and preserving representational discrimination. In addition, DuetGraph introduces a coarse-to-fine optimization, which partitions entities into high- and low-score subsets. This strategy narrows the candidate space and sharpens the score gap between the two subsets, which alleviates over-smoothing and enhances inference quality. Extensive experiments on various datasets demonstrate that DuetGraph achieves state-of-the-art (SOTA) performance, with up to an 8.7% improvement in reasoning quality and a 1.8$\times$ acceleration in training efficiency. Our code is available at https://github.com/USTC-DataDarknessLab/DuetGraph.git.

Qiang Chen, Tianyang Han, Jin Li et al.

Can AI effectively perform complex econometric analysis traditionally requiring human expertise? This paper evaluates AI agents' capability to master econometrics, focusing on empirical analysis performance. We develop an ``Econometrics AI Agent'' built on the open-source MetaGPT framework. This agent exhibits outstanding performance in: (1) planning econometric tasks strategically, (2) generating and executing code, (3) employing error-based reflection for improved robustness, and (4) allowing iterative refinement through multi-round conversations. We construct two datasets from academic coursework materials and published research papers to evaluate performance against real-world challenges. Comparative testing shows our domain-specialized AI agent significantly outperforms both benchmark large language models (LLMs) and general-purpose AI agents. This work establishes a testbed for exploring AI's impact on social science research and enables cost-effective integration of domain expertise, making advanced econometric methods accessible to users with minimal coding skills. Furthermore, our AI agent enhances research reproducibility and offers promising pedagogical applications for econometrics teaching.

Feng Lv, Guoqing Li, Jin Li et al.

Despite domain-adaptive object detectors based on CNN and transformers have made significant progress in cross-domain detection tasks, it is regrettable that domain adaptation for real-time transformer-based detectors has not yet been explored. Directly applying existing domain adaptation algorithms has proven to be suboptimal. In this paper, we propose RT-DATR, a simple and efficient real-time domain adaptive detection transformer. Building on RT-DETR as our base detector, we first introduce a local object-level feature alignment module to significantly enhance the feature representation of domain invariance during object transfer. Additionally, we introduce a scene semantic feature alignment module designed to boost cross-domain detection performance by aligning scene semantic features. Finally, we introduced a domain query and decoupled it from the object query to further align the instance feature distribution within the decoder layer, reduce the domain gap, and maintain discriminative ability. Experimental results on various cross-domian benchmarks demonstrate that our method outperforms current state-of-the-art approaches. Code is available at https://github.com/Jeremy-lf/RT-DATR.

Wanquan Feng, Jin Li, Hongrui Cai et al.

In this paper, we propose Neural Points, a novel point cloud representation and apply it to the arbitrary-factored upsampling task. Different from traditional point cloud representation where each point only represents a position or a local plane in the 3D space, each point in Neural Points represents a local continuous geometric shape via neural fields. Therefore, Neural Points contain more shape information and thus have a stronger representation ability. Neural Points is trained with surface containing rich geometric details, such that the trained model has enough expression ability for various shapes. Specifically, we extract deep local features on the points and construct neural fields through the local isomorphism between the 2D parametric domain and the 3D local patch. In the final, local neural fields are integrated together to form the global surface. Experimental results show that Neural Points has powerful representation ability and demonstrate excellent robustness and generalization ability. With Neural Points, we can resample point cloud with arbitrary resolutions, and it outperforms the state-of-the-art point cloud upsampling methods. Code is available at https://github.com/WanquanF/NeuralPoints.

Zhong Ji, Jin Li, Qiang Wang et al.

General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We reveal that the relation and feature deviations are crucial problems for catastrophic forgetting, in which relation deviation refers to the deficiency of the relationship among all classes in knowledge distillation, and feature deviation refers to indiscriminative feature representations. To this end, we propose a Complementary Calibration (CoCa) framework by mining the complementary model's outputs and features to alleviate the two deviations in the process of GCL. Specifically, we propose a new collaborative distillation approach for addressing the relation deviation. It distills model's outputs by utilizing ensemble dark knowledge of new model's outputs and reserved outputs, which maintains the performance of old tasks as well as balancing the relationship among all classes. Furthermore, we explore a collaborative self-supervision idea to leverage pretext tasks and supervised contrastive learning for addressing the feature deviation problem by learning complete and discriminative features for all classes. Extensive experiments on four popular datasets show that our CoCa framework achieves superior performance against state-of-the-art methods. Code is available at https://github.com/lijincm/CoCa.

Nikolay Ivanov, Jianzhi Lou, Ting Chen et al.

Ethereum holds multiple billions of U.S. dollars in the form of Ether cryptocurrency and ERC-20 tokens, with millions of deployed smart contracts algorithmically operating these funds. Unsurprisingly, the security of Ethereum smart contracts has been under rigorous scrutiny. In recent years, numerous defense tools have been developed to detect different types of smart contract code vulnerabilities. When opportunities for exploiting code vulnerabilities diminish, the attackers start resorting to social engineering attacks, which aim to influence humans -- often the weakest link in the system. The only known class of social engineering attacks in Ethereum are honeypots, which plant hidden traps for attackers attempting to exploit existing vulnerabilities, thereby targeting only a small population of potential victims. In this work, we explore the possibility and existence of new social engineering attacks beyond smart contract honeypots. We present two novel classes of Ethereum social engineering attacks - Address Manipulation and Homograph - and develop six zero-day social engineering attacks. To show how the attacks can be used in popular programming patterns, we conduct a case study of five popular smart contracts with combined market capitalization exceeding $29 billion, and integrate our attack patterns in their source codes without altering their existing functionality. Moreover, we show that these attacks remain dormant during the test phase but activate their malicious logic only at the final production deployment. We further analyze 85,656 open-source smart contracts, and discover that 1,027 of them can be used for the proposed social engineering attacks. We conduct a professional opinion survey with experts from seven smart contract auditing firms, corroborating that the exposed social engineering attacks bring a major threat to the smart contract systems.

Fu-Zhao Ou, Yuan-Gen Wang, Jin Li et al.

No-reference image quality assessment (NR-IQA) has received increasing attention in the IQA community since reference image is not always available. Real-world images generally suffer from various types of distortion. Unfortunately, existing NR-IQA methods do not work with all types of distortion. It is a challenging task to develop universal NR-IQA that has the ability of evaluating all types of distorted images. In this paper, we propose a universal NR-IQA method based on controllable list-wise ranking (CLRIQA). First, to extend the authentically distorted image dataset, we present an imaging-heuristic approach, in which the over-underexposure is formulated as an inverse of Weber-Fechner law, and fusion strategy and probabilistic compression are adopted, to generate the degraded real-world images. These degraded images are label-free yet associated with quality ranking information. We then design a controllable list-wise ranking function by limiting rank range and introducing an adaptive margin to tune rank interval. Finally, the extended dataset and controllable list-wise ranking function are used to pre-train a CNN. Moreover, in order to obtain an accurate prediction model, we take advantage of the original dataset to further fine-tune the pre-trained network. Experiments evaluated on four benchmark datasets (i.e. LIVE, CSIQ, TID2013, and LIVE-C) show that the proposed CLRIQA improves the state of the art by over 9% in terms of overall performance. The code and model are publicly available at https://github.com/GZHU-Image-Lab/CLRIQA.

Ziang Yan, Jian Liang, Weishen Pan et al.

Object detection when provided image-level labels instead of instance-level labels (i.e., bounding boxes) during training is an important problem in computer vision, since large scale image datasets with instance-level labels are extremely costly to obtain. In this paper, we address this challenging problem by developing an Expectation-Maximization (EM) based object detection method using deep convolutional neural networks (CNNs). Our method is applicable to both the weakly-supervised and semi-supervised settings. Extensive experiments on PASCAL VOC 2007 benchmark show that (1) in the weakly supervised setting, our method provides significant detection performance improvement over current state-of-the-art methods, (2) having access to a small number of strongly (instance-level) annotated images, our method can almost match the performace of the fully supervised Fast RCNN. We share our source code at https://github.com/ZiangYan/EM-WSD.

Jin Li, Tao Chen, Shuai Jiang et al.

Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536 \times 1536$). The dataset is constructed using DINOv3-based hierarchical clustering for semantically balanced sampling and Gemini-powered dense captioning, ensuring a uniform distribution across 20 fine-grained garment categories. To support reliable evaluation, we propose a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism. The protocol integrates VLM-based semantic reasoning with a novel Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion, enabling the separation of boundary alignment errors from internal texture artifacts. Experimental results show strong agreement with human judgments (Kendall's $τ$ of 0.833 vs. 0.611 for SSIM), establishing a robust benchmark for VTON evaluation.

Yanke Yu, Jin Li, Ying Sun et al.

Understanding the internal functional organization of Large Language Models (LLMs) is crucial for improving their trustworthiness and performance. However, how LLMs organize different functions into modules remains highly unexplored. To bridge this gap, we formulate a functional module discovery problem and propose an Unsupervised LLM Cross-layer MOdule Discovery (ULCMOD) framework that simultaneously disentangles the large set of neurons in the entire LLM into modules while discovering the topics of input samples related to these modules. Our framework introduces a novel objective function and an efficient Iterative Decoupling (IterD) algorithm. Extensive experiments show that our method discovers high-quality, disentangled modules that capture more meaningful semantic information and achieve superior performance in various downstream tasks. Moreover, our qualitative analysis reveals that the discovered modules show semantic coherence, correspond to interpretable specializations, and a clear spatial and hierarchical organization within the LLM. Our work provides a novel tool for interpreting the functional modules of LLMs, filling a critical blank in LLM's interpretability research.

Jinning Zhang, Jie Song, Wenhui Tu et al.

In medicine, large language models (LLMs) increasingly rely on retrieval-augmented generation (RAG) to ground outputs in up-to-date external evidence. However, current RAG approaches focus primarily on performance improvements while overlooking evidence-based medicine (EBM) principles. This study addresses two key gaps: (1) the lack of PICO alignment between queries and retrieved evidence, and (2) the absence of evidence hierarchy considerations during reranking. We present a generalizable strategy for adapting EBM to graph-based RAG, integrating the PICO framework into knowledge graph construction and retrieval, and proposing a Bayesian-inspired reranking algorithm to calibrate ranking scores by evidence grade without introducing predefined weights. We validated this framework in sports rehabilitation, a literature-rich domain currently lacking RAG systems and benchmarks. We released a knowledge graph (357,844 nodes and 371,226 edges) and a reusable benchmark of 1,637 QA pairs. The system achieved 0.830 nugget coverage, 0.819 answer faithfulness, 0.882 semantic similarity, and 0.788 PICOT match accuracy. In a 5-point Likert evaluation, five expert clinicians rated the system 4.66-4.84 across factual accuracy, faithfulness, relevance, safety, and PICO alignment. These findings demonstrate that the proposed EBM adaptation strategy improves retrieval and answer quality and is transferable to other clinical domains. The released resources also help address the scarcity of RAG datasets in sports rehabilitation.

Jin Li, Kleanthis Malialis, Marios Polycarpou

In today's connected world, the generation of massive streaming data across diverse domains has become commonplace. In the presence of concept drift, class imbalance, label scarcity, and new class emergence, they jointly degrade representation stability, bias learning toward outdated distributions, and reduce the resilience and reliability of detection in dynamic environments. This paper proposes SCIL (Streaming Class-Incremental Learning) to address these challenges. The SCIL framework integrates an autoencoder (AE) with a multi-layer perceptron for multi-class prediction, uses a dual-loss strategy (classification and reconstruction) for prediction and new class detection, employs corrected pseudo-labels for online training, manages classes with queues, and applies oversampling to handle imbalance. The rationale behind the method's structure is elucidated through ablation studies and a comprehensive experimental evaluation is performed using both real-world and synthetic datasets that feature class imbalance, incremental classes, and concept drifts. Our results demonstrate that SCIL outperforms strong baselines and state-of-the-art methods. Based on our commitment to Open Science, we make our code and datasets available to the community.

Jinhao Li, Yuhao Sun, Zhiyuan Ma et al.

Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement learning remains challenging. Population-based, gradient-free optimization circumvents backpropagation through non-differentiable spike dynamics by estimating gradients. However, with finite populations, high variance of these estimates can induce harmful and overly aggressive update steps. Inspired by trust-region methods in reinforcement learning that constrain policy updates in distribution space, we propose \textbf{Signal-Adaptive Trust Regions (SATR)}, a distributional update rule that constrains relative change by bounding KL divergence normalized by an estimated signal energy. SATR automatically expands the trust region under strong signals and contracts it when updates are noise-dominated. We instantiate SATR for Bernoulli connectivity distributions, which have shown strong empirical performance for RSNN optimization. Across a suite of high-dimensional continuous-control benchmarks, SATR improves stability under limited populations and reaches competitive returns against strong baselines including PPO-LSTM. In addition, to make SATR practical at scale, we introduce a bitset implementation for binary spiking and binary weights, substantially reducing wall-clock training time and enabling fast RSNN policy search.

Guan Wang, Jin Li, Yuhao Sun et al.

Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle task decomposition, extensive data requirements, and high latency. Inspired by the hierarchical and multi-timescale processing in the human brain, we propose the Hierarchical Reasoning Model (HRM), a novel recurrent architecture that attains significant computational depth while maintaining both training stability and efficiency. HRM executes sequential reasoning tasks in a single forward pass without explicit supervision of the intermediate process, through two interdependent recurrent modules: a high-level module responsible for slow, abstract planning, and a low-level module handling rapid, detailed computations. With only 27 million parameters, HRM achieves exceptional performance on complex reasoning tasks using only 1000 training samples. The model operates without pre-training or CoT data, yet achieves nearly perfect performance on challenging tasks including complex Sudoku puzzles and optimal path finding in large mazes. Furthermore, HRM outperforms much larger models with significantly longer context windows on the Abstraction and Reasoning Corpus (ARC), a key benchmark for measuring artificial general intelligence capabilities. These results underscore HRM's potential as a transformative advancement toward universal computation and general-purpose reasoning systems.

Zhouwei Zhai, Mengxiang Chen, Haoyun Xia et al.

Modern e-commerce search engines, largely rooted in passive retrieval-and-ranking models, frequently fail to support complex decision-making, leaving users overwhelmed by cognitive friction. In this paper, we introduce CogSearch, a novel cognitive-oriented multi-agent framework that reimagines e-commerce search as a proactive decision support system. By synergizing four specialized agents, CogSearch mimics human cognitive workflows: it decomposes intricate user intents, fuses heterogeneous knowledge across internal and external sources, and delivers highly actionable insights. Our offline benchmarks validate CogSearch's excellence in consultative and complex search scenarios. Extensive online A/B testing on JD.com demonstrates the system's transformative impact: it reduced decision costs by 5% and achieved a 0.41% increase in overall UCVR, with a remarkable 30% surge in conversion for decision-heavy queries. CogSearch represents a fundamental shift in information retrieval, moving beyond traditional relevance-centric paradigms toward a future of holistic, collaborative decision intelligence.

Guikun Chen, Jin Li, Wenguan Wang

Current approaches for open-vocabulary scene graph generation (OVSGG) use vision-language models such as CLIP and follow a standard zero-shot pipeline -- computing similarity between the query image and the text embeddings for each category (i.e., text classifiers). In this work, we argue that the text classifiers adopted by existing OVSGG methods, i.e., category-/part-level prompts, are scene-agnostic as they remain unchanged across contexts. Using such fixed text classifiers not only struggles to model visual relations with high variance, but also falls short in adapting to distinct contexts. To plug these intrinsic shortcomings, we devise SDSGG, a scene-specific description based OVSGG framework where the weights of text classifiers are adaptively adjusted according to the visual content. In particular, to generate comprehensive and diverse descriptions oriented to the scene, an LLM is asked to play different roles (e.g., biologist and engineer) to analyze and discuss the descriptive features of a given scene from different views. Unlike previous efforts simply treating the generated descriptions as mutually equivalent text classifiers, SDSGG is equipped with an advanced renormalization mechanism to adjust the influence of each text classifier based on its relevance to the presented scene (this is what the term "specific" means). Furthermore, to capture the complicated interplay between subjects and objects, we propose a new lightweight module called mutual visual adapter. It refines CLIP's ability to recognize relations by learning an interaction-aware semantic space. Extensive experiments on prevalent benchmarks show that SDSGG outperforms top-leading methods by a clear margin.

Mengxiang Chen, Zhouwei Zhai, Jin Li

Modern e-commerce search is evolving to resolve complex user intents. While Large Language Models (LLMs) offer strong reasoning, existing LLM-based paradigms face a fundamental blindness-latency dilemma: query rewriting is agnostic to retrieval capabilities and real-time inventory, yielding invalid plans; conversely, deep search agents rely on iterative tool calls and reflection, incurring seconds of latency incompatible with industrial sub-second budgets. To resolve this conflict, we propose Environment-Aware Search Planning (EASP), reformulating search planning as a dynamic reasoning process grounded in environmental reality. EASP introduces a Probe-then-Plan mechanism: a lightweight Retrieval Probe exposes the retrieval snapshot, enabling the Planner to diagnose execution gaps and generate grounded search plans. The methodology comprises three stages: (1) Offline Data Synthesis: A Teacher Agent synthesizes diverse, execution-validated plans by diagnosing the probed environment. (2) Planner Training and Alignment: The Planner is initialized via Supervised Fine-Tuning (SFT) to internalize diagnostic capabilities, then aligned with business outcomes (conversion rate) via Reinforcement Learning (RL). (3) Adaptive Online Serving: A complexity-aware routing mechanism selectively activates planning for complex queries, ensuring optimal resource allocation. Extensive offline evaluations and online A/B testing on JD.com demonstrate that EASP significantly improves relevant recall and achieves substantial lifts in UCVR and GMV. EASP has been successfully deployed in JD.com's AI-Search system.

Keyu Wang, Jin Li, Shu Yang et al.

Large Language Models (LLMs) often exhibit sycophantic behavior, agreeing with user-stated opinions even when those contradict factual knowledge. While prior work has documented this tendency, the internal mechanisms that enable such behavior remain poorly understood. In this paper, we provide a mechanistic account of how sycophancy arises within LLMs. We first systematically study how user opinions induce sycophancy across different model families. We find that simple opinion statements reliably induce sycophancy, whereas user expertise framing has a negligible impact. Through logit-lens analysis and causal activation patching, we identify a two-stage emergence of sycophancy: (1) a late-layer output preference shift and (2) deeper representational divergence. We also verify that user authority fails to influence behavior because models do not encode it internally. In addition, we examine how grammatical perspective affects sycophantic behavior, finding that first-person prompts (``I believe...'') consistently induce higher sycophancy rates than third-person framings (``They believe...'') by creating stronger representational perturbations in deeper layers. These findings highlight that sycophancy is not a surface-level artifact but emerges from a structural override of learned knowledge in deeper layers, with implications for alignment and truthful AI systems.

Zhangkai Wu, Xuhui Fan, Jin Li et al.

The recently proposed Bayesian Flow Networks~(BFNs) show great potential in modeling parameter spaces, offering a unified strategy for handling continuous, discretized, and discrete data. However, BFNs cannot learn high-level semantic representation from the parameter space since {common encoders, which encode data into one static representation, cannot capture semantic changes in parameters.} This motivates a new direction: learning semantic representations hidden in the parameter spaces to characterize mixed-typed noisy data. {Accordingly, we propose a representation learning framework named ParamReL, which operates in the parameter space to obtain parameter-wise latent semantics that exhibit progressive structures. Specifically, ParamReL proposes a \emph{self-}encoder to learn latent semantics directly from parameters, rather than from observations. The encoder is then integrated into BFNs, enabling representation learning with various formats of observations. Mutual information terms further promote the disentanglement of latent semantics and capture meaningful semantics simultaneously.} We illustrate {conditional generation and reconstruction} in ParamReL via expanding BFNs, and extensive {quantitative} experimental results demonstrate the {superior effectiveness} of ParamReL in learning parameter representation.

Jing Zeng, Qi Ye, Tianle Liu et al.

Implicit neural representations and 3D Gaussian splatting (3DGS) have shown great potential for scene reconstruction. Recent studies have expanded their applications in autonomous reconstruction through task assignment methods. However, these methods are mainly limited to single robot, and rapid reconstruction of large-scale scenes remains challenging. Additionally, task-driven planning based on surface uncertainty is prone to being trapped in local optima. To this end, we propose the first 3DGS-based centralized multi-robot autonomous 3D reconstruction framework. To further reduce time cost of task generation and improve reconstruction quality, we integrate online open-vocabulary semantic segmentation with surface uncertainty of 3DGS, focusing view sampling on regions with high instance uncertainty. Finally, we develop a multi-robot collaboration strategy with mode and task assignments improving reconstruction quality while ensuring planning efficiency. Our method demonstrates the highest reconstruction quality among all planning methods and superior planning efficiency compared to existing multi-robot methods. We deploy our method on multiple robots, and results show that it can effectively plan view paths and reconstruct scenes with high quality.

Kleanthis Malialis, Jin Li, Christos G. Panayiotou et al.

Data stream mining aims at extracting meaningful knowledge from continually evolving data streams, addressing the challenges posed by nonstationary environments, particularly, concept drift which refers to a change in the underlying data distribution over time. Graph structures offer a powerful modelling tool to represent complex systems, such as, critical infrastructure systems and social networks. Learning from graph streams becomes a necessity to understand the dynamics of graph structures and to facilitate informed decision-making. This work introduces a novel method for graph stream classification which operates under the general setting where a data generating process produces graphs with varying nodes and edges over time. The method uses incremental learning for continual model adaptation, selecting representative graphs (prototypes) for each class, and creating graph embeddings. Additionally, it incorporates a loss-based concept drift detection mechanism to recalculate graph prototypes when drift is detected.

Huali Ren, Anli Yan, Xiaojun Ren et al.

Deep neural networks (DNNs) are extensively employed in a wide range of application scenarios. Generally, training a commercially viable neural network requires significant amounts of data and computing resources, and it is easy for unauthorized users to use the networks illegally. Therefore, network ownership verification has become one of the most crucial steps in safeguarding digital assets. To verify the ownership of networks, the existing network fingerprinting approaches perform poorly in the aspects of efficiency, stealthiness, and discriminability. To address these issues, we propose a network fingerprinting approach, named as GanFinger, to construct the network fingerprints based on the network behavior, which is characterized by network outputs of pairs of original examples and conferrable adversarial examples. Specifically, GanFinger leverages Generative Adversarial Networks (GANs) to effectively generate conferrable adversarial examples with imperceptible perturbations. These examples can exhibit identical outputs on copyrighted and pirated networks while producing different results on irrelevant networks. Moreover, to enhance the accuracy of fingerprint ownership verification, the network similarity is computed based on the accuracy-robustness distance of fingerprint examples'outputs. To evaluate the performance of GanFinger, we construct a comprehensive benchmark consisting of 186 networks with five network structures and four popular network post-processing techniques. The benchmark experiments demonstrate that GanFinger significantly outperforms the state-of-the-arts in efficiency, stealthiness, and discriminability. It achieves a remarkable 6.57 times faster in fingerprint generation and boosts the ARUC value by 0.175, resulting in a relative improvement of about 26%.

Jin Li, Qirong Zhang, Shuling Xu et al.

Despite Graph neural networks' significant performance gain over many classic techniques in various graph-related downstream tasks, their successes are restricted in shallow models due to over-smoothness and the difficulties of optimizations among many other issues. In this paper, to alleviate the over-smoothing issue, we propose a soft graph normalization method to preserve the diversities of node embeddings and prevent indiscrimination due to possible over-closeness. Combined with residual connections, we analyze the reason why the method can effectively capture the knowledge in both input graph structures and node features even with deep networks. Additionally, inspired by Curriculum Learning that learns easy examples before the hard ones, we propose a novel label-smoothing-based learning framework to enhance the optimization of deep GNNs, which iteratively smooths labels in an auxiliary graph and constructs many gradual non-smooth tasks for extracting increasingly complex knowledge and gradually discriminating nodes from coarse to fine. The method arguably reduces the risk of overfitting and generalizes better results. Finally, extensive experiments are carried out to demonstrate the effectiveness and potential of the proposed model and learning framework through comparison with twelve existing baselines including the state-of-the-art methods on twelve real-world node classification benchmarks.