Industrial generative recommendation systems operating over discrete Semantic IDs (SIDs) are largely behavior-driven, and thus struggle to proactively activate latent demand before explicit user signals emerge, leading to intent cold-start. To address this, we propose RIGER (Reasoning-grounded Intent injection for GE nerative Recommendation), a deployable two-stage framework that integrates offline large language model (LLM) reasoning into an online generative recommender under strict latency constraints. Offline, to ensure scalable deployment, we distill the latent-intent inference capability of a strong LLM into a lightweight forecasting model using an automated data curation pipeline---leveraging judge-guided prompt calibration and future-query-guided rejection filtering. Online, to bridge the representation mismatch between free-form textual intents and the discrete SID token space, predicted intents are converted into SID-native tokens through a behavior-grounded mapping and injected into the deployed decoder-only retrieval backbone. We further fine-tune the model with beam-aware GRPO, introducing a hierarchical intent-alignment exploration reward in SID space while preserving exploitation behavior through KL regularization. Offline evaluations demonstrate a substantial increase in intent-aligned density and diversity with only a marginal reduction in hindsight recall, indicating that RIGER effectively enhances proactive intent exploration while preserving its capability to exploit historical behaviors. In a large-scale e-commerce display advertising system, RIGER improves clicks by 1.6% and advertiser spend by 1.3%.

The ranking stage serves as the central optimization and allocation hub in advertising systems, governing economic value distribution through eCPM and orchestrating the user-centric blending of organic and advertising content. Prevailing ranking models often rely on fragmented modules and hand-crafted features, limiting their ability to interpret complex user intent. This challenge is further amplified in location-based services such as food delivery, where user decisions are shaped by dynamic spatial, temporal, and individual contexts. To address these limitations, we propose a novel generative framework that reframes ranking as a context comprehension task, modeling heterogeneous signals in a unified architecture. Our architecture consists of two core components: the Generative Contextual Encoder (GCE) and the Generative Contextual Fusion (GCF). The GCE comprises three specialized modules: a Personalized Context Enhancer (PCE) for user-specific modeling, a Collective Context Enhancer (CCE) for group-level patterns, and a Dynamic Context Enhancer (DCE) for real-time situational adaptation. The GCF module then seamlessly integrates these contextual representations through low-rank adaptation. Extensive experiments confirm that our method achieves significant gains in critical business metrics, including click-through rate and platform revenue. We have successfully deployed our method on a large-scale food delivery advertising platform, demonstrating its substantial practical impact. This work pioneers a new perspective on generative recommendation and highlights its practical potential in industrial advertising systems.

Recent major milestones have successfully reconstructed natural language from non-invasive brain signals (e.g.functional Magnetic Resonance Imaging (fMRI) and Electroencephalogram (EEG)) across subjects.However, we find current dataset splitting strategies for cross-subject brain-to-text decoding are wrong.Specifically, we first demonstrate that all current splitting methods suffer from data leakage problem, which refers to the leakage of validation and test data into training set, resulting in significant overfitting and overestimation of decoding models.In this study, we develop a right cross-subject data splitting criterion without data leakage for decoding fMRI and EEG signal to text.Some SOTA brain-to-text decoding models are re-evaluated correctly with the proposed criterion for further research.

Abstract— Robotic needle positioning tasks in neurosurgery often face challenges due to insufficient perception of planar guidance images during surgery. In this work, we propose an Augmented Reality (AR) interface to help perform the robotic needle positioning tasks by learning from demonstration (LfD). Enhanced immersion in the workflow is achieved by displaying surgical scenes and calculated navigation information. The framework utilizes mixed interactive interfaces in virtual and real environments, enhancing demonstration efficiency and quality. A head-mounted display and an optical tracking system are utilized to perform the visualization and needle tracking. Gaussian Mixture Model (GMM) and Gaussian Mixture Regression (GMR) are employed to learn a robust and smooth trajectory policy from demonstrations. Experiments on robot reproduction of the needle positioning task achieved a final positioning error of 0.6 mm and an average trajectory error of 1.07 mm. Comparative user studies with haptic device-based teleoperation exhibit a low completion time of 62.76 s and reduced workload of the proposed system.

Accurate click-through rate (CTR) prediction is critical for online advertising, relying on regular features like browsing history and demographics and post-event features such as exposed position and detailed page behaviors. However, post-event features, unavailable during inference, often face training-inference inconsistency and low coverage issues, especially post-click features like dwell time that are available only for clicked items. To address these challenges, we propose Causal Optimal Transport (COT), a novel framework that (1) generates pseudo post-click features via semi-supervised pseudo-labeling (2) causally generates accurate feature distributions using a Causal Distribution Shaper (CDS), and (3) refines generated features through optimal transport to minimize distributional divergence, facilitating further knowledge transfer. Experiments on real-world data confirm COT's superiority and practical efficacy in enhancing CTR prediction via improved user interest modeling and bias mitigation. Theoretical guarantees underpin the framework's robustness.

Needle interventions are crucial in neurosurgery, requiring high precision and stability. This paper presents a 5-DoF head-mounted hydraulic needle robot designed for accurate and targeted needle insertion and neuroimaging in the deep brain. The robot is compact and lightweight by utilizing a hydraulic pipe transmission to connect the needle driver and actuator. The syringe pistons serve as the actuator and executor, enabling synchronized motion, minimal hysteresis, and high-accuracy insertion. The hydraulic transmission system exhibits hysteresis of less than 0.8 mm, with bidirectional insertion accuracy of approximately 0.05 mm. The resulting needle driver features a compact structure measuring 48 mm × 25 mm × 9 mm, accompanied by a 70-mm-long needle guide. The needle driver is mainly 3D printed, while the hydraulic transmission ensures full compatibility with magnetic resonance imaging (MRI) by isolating all electromagnetic parts from the executor. This compact and lightweight robot-assisted needle intervention system significantly enhances the safety, accuracy, and effectiveness of deep-brain neuroimaging. The feasibility of precise positioning and insertion is further demonstrated by deploying an optical coherence tomography (OCT) microneedle in a rat brain.

Recently, deep learning surrogates and neural operators have shown promise in solving partial differential equations (PDEs). However, they often require a large amount of training data and are limited to bounded domains. In this work, we present a novel physics-informed neural operator method to solve parameterized boundary value problems without labeled data. By reformulating the PDEs into boundary integral equations (BIEs), we can train the operator network solely on the boundary of the domain. This approach reduces the number of required sample points from O(Nd) to O(Nd-1), where d is the domain's dimension, leading to a significant acceleration of the training process. Additionally, our method can handle unbounded problems, which are unattainable for existing physics-informed neural networks (PINNs) and neural operators. Our numerical experiments show the effectiveness of parameterized complex geometries and unbounded problems.

Online recommenders have attained growing interest and created great revenue for businesses. Given numerous users and items, incremental update becomes a mainstream paradigm for learning large-scale models in industrial scenarios, where only newly arrived data within a sliding window is fed into the model, meeting the strict requirements of quick response. However, this strategy would be prone to overfitting to newly arrived data. When there exists a significant drift of data distribution, the long-term information would be discarded, which harms the recommendation performance. Conventional methods address this issue through native model-based continual learning methods, without analyzing the data characteristics for online recommenders. To address the aforementioned issue, we propose an incremental update framework for online recommenders with Data-Driven Prior (DDP), which is composed of Feature Prior (FP) and Model Prior (MP). The FP performs the click estimation for each specific value to enhance the stability of the training process. The MP incorporates previous model output into the current update while strictly following the Bayes rules, resulting in a theoretically provable prior for the robust update. In this way, both the FP and MP are well integrated into the unified framework, which is model-agnostic and can accommodate various advanced interaction models. Extensive experiments on two publicly available datasets as well as an industrial dataset demonstrate the superior performance of the proposed framework. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

The exposure sequence is being actively studied for user interest modeling in Click-Through Rate (CTR) prediction. However, the existing methods for exposure sequence modeling bring extensive computational burden and neglect noise problems, resulting in an excessively latency and the limited performance in online recommenders. In this paper, we propose to address the high latency and noise problems via Gating-adapted wavelet multiresolution analysis (Gama), which can effectively denoise the extremely long exposure sequence and adaptively capture the implied multi-dimension user interest with linear computational complexity. This is the first attempt to integrate non-parametric multiresolution analysis technique into deep neural network to model user exposure sequence. Extensive experiments on large scale benchmark dataset and real production dataset confirm the effectiveness of Gama for exposure sequence modeling, especially in cold-start scenarios. Benefited from its low latency and high effecitveness, Gama has been deployed in our real large-scale industrial recommender, successfully serving over hundreds of millions users.

We propose a general Variational Embedding Learning Framework (VELF) for alleviating the severe cold-start problem in CTR prediction. VELF addresses the cold start problem via alleviating over-fits caused by data-sparsity in two ways: learning probabilistic embedding, and incorporating trainable and regularized priors which utilize the rich side information of cold start users and advertisements (Ads). The two techniques are naturally integrated into a variational inference framework, forming an end-to-end training process. Abundant empirical tests on benchmark datasets well demonstrate the advantages of our proposed VELF. Besides, extended experiments confirmed that our parameterized and regularized priors provide more generalization capability than traditional fixed priors.

In this article, we develop a hybrid physics-informed neural network (hybrid PINN) for partial differential equations (PDEs). We borrow the idea from the convolutional neural network (CNN) and finite volume methods. Unlike the physics-informed neural network (PINN) and its variations, the method proposed in this article uses an approximation of the differential operator to solve the PDEs instead of automatic differentiation (AD). The approximation is given by a local fitting method, which is the main contribution of this article. As a result, our method has been proved to have a convergent rate. This will also avoid the issue that the neural network gives a bad prediction, which sometimes happened in PINN. To the author's best knowledge, this is the first work that the machine learning PDE's solver has a convergent rate, such as in numerical methods. The numerical experiments verify the correctness and efficiency of our algorithm. We also show that our method can be applied in inverse problems and surface PDEs, although without proof.

Learning effective interactions between multi-modal features is at the heart of visual question answering (VQA). A common defect of the existing VQA approaches is that they only consider a very limited amount of inter-modality interactions, which may be not enough to model latent complex image-question relations that are necessary for accurately answering questions. Besides, most methods neglect the modeling of the intra-modality interactions that is also important to VQA. In this work, we propose a novel DenIII framework for modeling dense inter- and intra-modality interactions. It densely connects all pairwise layers of the network via the proposed Inter- and Intra-modality Attention Connectors, capturing fine-grained interplay across all hierarchical levels. The Inter-modality Attention Connector efficiently connects the multi-modality features at any two layers with bidirectional attention, capturing the inter-modality interactions. While the Intra-modality Attention Connector connects the features of the same modality with unidirectional attention, and models the intra-modality interactions. Extensive ablation studies and visualizations validate the effectiveness of our method, and DenIII achieves state-of-the-art or competitive performance on three publicly available datasets.

Embedding mechanism plays an important role in Click-Through-Rate (CTR) prediction. Essentially, it tries to learn a new feature space with some learned latent properties as the basis, and maps the high dimensional and categorical raw data to dense, rich and expressive representations, i.e., the embedding features. Current researches usually focus on learning the interactions through operations on the whole embedding features without considering the relations among the learned latent properties. In this paper, we find it has clear positive effects on CTR prediction to model such relations and propose a novel Dimension Relation Module (DRM) to capture them through dimension recalibration. We show that DRM can improve the performance of existing models consistently and the improvements are more obvious when the embedding dimension is higher. We further boost Field-wise and Element-wise embedding methods with our DRM and name this new model FED network. Extensive experiments demonstrate that FED is very powerful in CTR prediction task and achieves new state-of-the-art results on Criteo, Avazu and JD.com datasets.

Targeting system is an essential part of computational advertising. It allows advertisers to select and reach their targeted users. Due to various advertising goals and the demand for making budget plans, advertisers have a strong will to configure the final targeting results, or they can become very cautious in spending money on advertising campaigns. Meanwhile, to guarantee the advertising performance, the targeted users should also be relevant to the ads of the advertisers. Recent targeting methods are mainly based on tags produced by the Data Management Platform (DMP) which is easy for the advertisers to configure the targeting results. However, in such methods, the relevance between the targeted users and ads is not technically evaluated and cannot be guaranteed. The biggest challenge is that it is hard for a machine learning model to both model the relevance and take account of the advertiser’s configuration demands. In this paper, we propose a novel relevance-driven and configurable targeting framework called Smart Targeting to solve the problem. Specifically, different from Tag-wise Targeting, we first use a relevance model to retrieve the most relevant users for the ads. To further enable the advertisers to configure the final results, we develop a Delay Intervention Mechanism to leverage the power of DMP. As far as we know, this is the first attempt of combining relevance modeling and advertiser intervention into a unified targeting system. We implement and evaluate our framework on JD.com platform with over 300 million users and the results show that it can bring significant improvements to the core indicators such as CTR and eCPM. The long term monitoring also demonstrates that Smart Targeting gradually becomes the most popular targeting tool after its release.

In this paper, we address the scene segmentation task by capturing rich contextual dependencies based on the self-attention mechanism. Unlike previous works that capture contexts by multi-scale features fusion, we propose a Dual Attention Networks (DANet) to adaptively integrate local features with their global dependencies. Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively. The position attention module selectively aggregates the features at each position by a weighted sum of the features at all positions. Similar features would be related to each other regardless of their distances. Meanwhile, the channel attention module selectively emphasizes interdependent channel maps by integrating associated features among all channel maps. We sum the outputs of the two attention modules to further improve feature representation which contributes to more precise segmentation results. We achieve new state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset. In particular, a Mean IoU score of 81.5% on Cityscapes test set is achieved without using coarse data.

Visual Question Answering (VQA) involves complex relations of two modalities, including the relations between words and between image regions. Thus, encoding these relations is important to accurate VQA. In this paper, we propose two modules to encode the two types of relations respectively. The language relation encoding module is proposed to encode multi-scale relations between words via a novel masked self-attention. The visual relation encoding module is proposed to encode the relations between image regions. It computes the response at a position as a weighted sum of the features at other positions in the feature maps. Extensive experiments demonstrate the effectiveness of each modules. Our model achieves state-of-the-art performance on the VQA 1.0 dataset.

Learning effective interactions between multi-modal features is at the heart of visual question answering (VQA). A common defect of the existing VQA approaches is that they only consider a very limited amount of interactions, which may be not enough to model latent complex image-question relations that are necessary for accurately answering questions. Therefore, in this paper, we propose a novel DCAF (Densely Connected Attention Flow) framework for modeling dense interactions. It densely connects all pairwise layers of the network via Attention Connectors, capturing fine-grained interplay between image and question across all hierarchical levels. The proposed Attention Connector efficiently connects the multi-modal features at any two layers with symmetric co-attention, and produces interaction-aware attention features. Experimental results on three publicly available datasets show that the proposed method achieves state-of-the-art performance.

Bilinear models are very powerful in multimodal fusion tasks like Visual Question Answering. The predominant bilinear methods can all be seen as a kind of tensor-based decomposition operation that contains a key kernel called “core tensor.” Current approaches usually focus on reducing the computation complexity by applying low-rank constraint on the core tensor. In this article, we propose a novel bilinear architecture called Block Term Decomposition Pooling (BTDP), which not only maintains the advantages of previous bilinear methods but also conducts sparse bilinear interactions between modalities. Our method is based on Block Term Decompositions theory of tensor, which will result in a sparse and learnable block-diagonal core tensor for multimodal fusion. We prove that using such a block-diagonal core tensor is equivalent to conducting many “tiny” bilinear operations in different feature spaces. Thus, introducing sparsity into the bilinear operation can significantly increase the performance of feature fusion and improve VQA models. What is more, our BTDP is very flexible in design. We develop several variants of BTDP and discuss the effects of the diagonal blocks of core tensor. Extensive experiments on two challenging VQA-v1 and VQA-v2 datasets show that our BTDP method outperforms current bilinear models, achieving state-of-the-art performance.

Using dropout in Visual Question Answering (VQA) is a common practice to prevent overfitting. However, in multi-path networks, the current way to use dropout may cause two problems: the co-adaptations of neurons and the explosion of output variance. In this paper, we propose the coherent dropout and the siamese dropouy to solve the two problems, respectively. Specifically, in coherent dropout, all relevant dropout layers in multiple paths are forced to work coherently to maximize the ability of preventing neuron co-adaptations. We show that the coherent dropout is simple in implementation but very effective to overcome overfitting. As for the explosion of output variance, we develop a siamese dropout mechanism to explicitly minimize the difference between the two output vectors produced from the same input data during training phase. Such mechanism can reduce the gap between training and inference phases and make the VQA model more robust. Extensive experiments are conducted to verify the effectiveness of coherent dropout and siamese dropout. And the results also show that our methods can bring additional improvements on the state-of-the-art VQA models.

Content-based image retrieval (CBIR) is one of the most important applications of computer vision. In recent years, there have been many important advances in the development of CBIR systems, especially Convolutional Neural Networks (CNNs) and other deep-learning techniques. On the other hand, current CNN-based CBIR systems suffer from high computational complexity of CNNs. This problem becomes more severe as mobile applications become more and more popular. The current practice is to deploy the entire CBIR systems on the server side while the client side only serves as an image provider. This architecture can increase the computational burden on the server side, which needs to process thousands of requests per second. Moreover, sending images have the potential of personal information leakage. As the need of mobile search expands, concerns about privacy are growing. In this article, we propose a fast image search framework, named DeepSearch, which makes complex image search based on CNNs feasible on mobile phones. To implement the huge computation of CNN models, we present a tensor Block Term Decomposition (BTD) approach as well as a nonlinear response reconstruction method to accelerate the CNNs involving in object detection and feature extraction. The extensive experiments on the ImageNet dataset and Alibaba Large-scale Image Search Challenge dataset show that the proposed accelerating approach BTD can significantly speed up the CNN models and further makes CNN-based image search practical on common smart phones.

Recent years, with the development of e-commerce and population of mobile phones, image-based commodity retrieval has attracted much attention. This paper proposed a deep framework for commodity image retrieval(CMIR) from the view that they are same designed commodities. Our framework can catch as many design details as possible by exploring object detection and ranking sensitive feature learning, while the former is performed based on Faster R-CNN, and the later is learned with a multi-task Siamese Network. Besides, we refine the processing speed of the framework to make it a live system. Our framework is implemented on an android application based on Client/Server structure model whose server response time is about 150 ms per query.

MOTIVATION: Because of the unique biological features, a bioinformatic platform for the integrated genetic and physical map of maize is required for storing, integrating, accessing and visualizing the underlying data. RESULTS: The goal of the Maize Mapping Project is to develop a fully integrated genetic and physical map for maize. To display this integrated map, we have developed iMap. iMap has three main components: a relational database (iMapDB), a map graphic browser (iMap Viewer) and a search utility (iMap Search). iMapDB is populated with current genetic and physical map data, describing relationships among genetic loci, molecular markers and bacterial artificial chromosome (BAC) contigs. The database also contains integrated information produced by applying a set of anchoring rules to assign BAC contigs to specific locations on the genetic map. The iMap Viewer and iMap Search functions are combined in the user interface to allow viewing and retrieving many types of genetic and physical map data. The iMap Viewer features side-by-side chromosome-based displays of the genetic map and associated BAC contigs. For each genetic locus, information about marker type or contig can be viewed via pop-up windows that feature links to external data resources. Searches can be conducted for genetic locus, probe or sequence accession number; search results include relevant map positions, anchored BAC contigs and links to the graphical display of relevant chromosomes. iMap can be accessed at http://www.maizemap.org AVAILABILITY: The iMap utility package is available for non-commercial use upon request from the authors.

Abstract Summary: cMap, a www comparative genetic map graphical utility, has a search capability and provides comparison of two genetic maps within or between species with dynamic links to data resources and text lists of the shared loci, running in a relational database environment. Currently, maps from three species (maize ‘Zea mays L.’, rice‘ Oryza sativa L.’, and sorghum ‘Sorghum bicolor L.’), representing over 13 800 distinct loci, are available for comparison at http://www.agron.missouri.edu/cMapDB/cMap.html Availability: cMap source code is available without cost on request for non-commercial use. Contact: [email protected] * To whom correspondence should be addressed. † Current address: Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611, USA

MOTIVATION: The development of an integrated genetic and physical map for the maize genome involves the generation of an enormous amount of data. Managing this data requires a system to aid in genotype scoring for different types of markers coming from both local and remote users. In addition, researchers need an efficient way to interact with genetic mapping software and with data files from automated DNA sequencing. They also need ways to manage primer data for mapping and sequencing and provide views of the integrated physical and genetic map and views of genetic map comparisons. RESULTS: The MMP-LIMS system has been used successfully in a high-throughput mapping environment. The genotypes from 957 SSR, 1023 RFLP, 189 SNP, and 177 InDel markers have been entered and verified via MMP-LIMS. The system is flexible, and can be easily modified to manage data for other species. The software is freely available. AVAILABILITY: To receive a copy of the iMap or cMap software, please fill out the form on our website. The other MMP-LIMS software is freely available at http://www.maizemap.org/bioinformatics.htm.