Author name cluster

Yang He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

17 papers

2 author rows

AAAI Conference 2026 System Paper

GenMatLab: A Generative Platform for Inverse Materials Design

Hangwei Qian
Yang He
Yaxin Shi
Ivor Tsang

In this demo, we present GenMatLab, a user-friendly web platform that makes latest AI techniques accessible for inverse materials design. The platform integrates data analysis and generative modeling into an easy-to-use interface, enabling researchers, material domain experts, and practitioners to explore and apply AI techniques without requiring advanced coding expertise. At its core are generative AI models that support interactive operations, allowing users to conduct inverse design and investigate generated candidates in an intuitive and exploratory way. By lowering technical barriers, GenMatLab empowers a broader community to leverage cutting-edge AI methods for accelerating materials discovery.

PDF Details DOI

AAAI Conference 2026 Conference Paper

LLM Safety in Judicial AI: A Stress Test of Social Media Influence on Real-World Judgments

Yixuan Xie
Yang He
Xiaoyu Yang
Xu Gai
Pan Hui

Integrating Large Language Models (LLMs) into judicial decision-making demands rigorous safety examination against non-legal influences. This paper presents a novel stress test where we evaluate LLM-generated labor dispute outcomes by introducing social media sentiment as an external pressure, critically comparing them against 10,000 real-world court judgments from China Judgments Online (CJOL). Our findings reveal significant LLM safety vulnerabilities: models exhibit inherent deviations from real rulings, and public opinion substantially amplifies these discrepancies, leading to unstable and often inflated compensation predictions. Furthermore, these safety risks are compounded across low-skilled occupational categories and emotionally charged topics. This study uncovers critical threats to judicial integrity and public trust, underscoring the urgent need for robust safeguards against non-legal influences in AI legal systems.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents

Yiming Du
Bingbing Wang
Yang He
Bin Liang
Baojun Wang
Zhongyang Li
Lin Gui
Jeff Z. Pan

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods prioritise semantic similarity over task intent, degrading multi-session coherence. We propose MemGuide, a two-stage intent-driven memory selection framework: (1) Intent‑Aligned Retrieval retrieves goal-consistent QA‑formatted memory units; (2) Missing‑Slot Guided Filtering reranks units by slot-completion gain via a chain‑of‑thought reasoner and fine‑tuned LLaMA‑8B filter. We also introduce the MS-TOD, the first multi-session TOD benchmark with 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets. Evaluations on MS-TOD show that MemGuide boosts task success rate by 11% (88%→99%) and reduces dialogue length by 2.84 turns, and matches single‑session performance.

PDF Details DOI

EAAI Journal 2025 Journal Article

Predicting potential microbe-disease associations based on heterogeneous graph attention network and deep sparse autoencoder

Bo Wang
Wenlong Zhao
Xiaoxin Du
Jianfei Zhang
Chunyu Zhang
Liping Wang
Yang He

Identifying potential associations between microbes and diseases is crucial for explaining disease pathogenesis and designing targeted therapeutic strategies. Basic biological experiments for microbe-disease association (MDA) prediction are costly, time-consuming, and labor-intensive, whereas computational methods can effectively complement traditional biological experiments. We propose a computational framework called graph attention convolutional deep sparse autoencoder microbe-disease association (GCDSAEMDA) to predict unknown MDAs. First, we calculate the semantic similarity and Gaussian interaction profile (GIP) similarity of diseases, as well as the functional similarity and GIP similarity of microbes, and integrate these similarity matrices to construct a heterogeneous graph. Next, a multi-head dynamic graph attention mechanism is employed to extract low-order features of microbe and disease nodes in the heterogeneous graph, while multiple convolutional neural networks with different kernels aggregate and concatenate these low-order features to form new high-order representations. Third, we apply a cosine distance-based k-means clustering to select reliable negative samples and use a deep sparse autoencoder to extract high-order features of microbe-disease pairs. Finally, an ensemble Light Gradient Boosting Machine (LightGBM) algorithm is used to predict potential MDAs. GCDSAEMDA was compared to four state-of-the-art MDA models on the Human Microbe-Disease Association Database (HMDAD) and Disbiome databases and validated through five-fold cross-validation on diseases, microbes, and microbe-disease pairs. Results indicate that GCDSAEMDA outperforms the other four models in MDA prediction. Additionally, case studies demonstrate the robust predictive capability of GCDSAEMDA. The source code and datasets for GCDSAEMDA are available at https: //github. com/chenyunmolu/GCDSAEMDA.

Details DOI

NeurIPS Conference 2025 Conference Paper

SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs

Jinhong Deng
Wen Li
Joey Tianyi Zhou
Yang He

Multimodal Large Language Models (MLLMs) typically process a large number of visual tokens, leading to considerable computational overhead, even though many of these tokens are redundant. Existing visual token pruning methods primarily focus on selecting the most salient tokens based on attention scores, resulting in the semantic incompleteness of the selected tokens. In this paper, we propose a novel visual token pruning strategy, called S aliency- C overage O riented token P runing for E fficient MLLMs (SCOPE), to jointly model both the saliency and coverage of the selected visual tokens to better preserve semantic completeness. Specifically, we introduce a set-coverage for a given set of selected tokens, computed based on the token relationships. We then define a token-coverage gain for each unselected token, quantifying how much additional coverage would be obtained by including it. By integrating the saliency score into the token-coverage gain, we propose our SCOPE score and iteratively select the token with the highest SCOPE score. We conduct extensive experiments on multiple vision-language understanding benchmarks using the LLaVA-1. 5 and LLaVA-Next models. Experimental results demonstrate that our method consistently outperforms prior approaches.

PDF Details

AIIM Journal 2025 Journal Article

VAE-GANMDA: A microbe-drug association prediction model integrating variational autoencoders and generative adversarial networks

Bo Wang
Yang He
Xiaoxin Du
Lei Zhu
Junqi Wang
Tongxuan Wang

Traditional biological experimental methods typically require weeks or even months of experimentation, and the cost of each experiment can reach hundreds or even thousands of dollars, which is quite expensive and time-consuming. To address this, a model called VAE-GANMDA, which integrates variational autoencoders (VAE) and generative adversarial networks (GAN) for predicting microbe-drug associations, has been proposed. Firstly, a heterogeneous network of microbes and drugs is established to enrich the association information. Secondly, by fusing VAE and GAN, the model learns the manifold distribution of data through association features, obtaining nonlinear manifold features. Furthermore, the VAE generation module is improved by integrating the Convolutional Block Attention Module (CBAM) and Gaussian kernel function, enhancing the smooth perception of manifold features, thus endowing VAE with stronger feature extraction capabilities. Then, singular value decomposition (SVD) technique is employed to extract linear features of the data. Finally, by combining linear and nonlinear features, the k-means++ algorithm is used to select balanced and high-quality negative samples for training the MLP classifier. Through performance evaluation, the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC) of VAE-GANMDA reach 0. 9724 and 0. 9635 respectively, outperforming classical machine learning methods and the majority of deep learning methods. Case studies demonstrate that VAE-GANMDA accurately predicts candidate drugs related to SARS-CoV-2 and candidate microbes related to ciprofloxacin.

Details DOI

NeurIPS Conference 2024 Conference Paper

Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?

Lingao Xiao
Yang He

In ImageNet-condensation, the storage for auxiliary soft labels exceeds that of the condensed dataset by over 30 times. However, are large-scale soft labels necessary for large-scale dataset distillation? In this paper, we first discover that the high within-class similarity in condensed datasets necessitates the use of large-scale soft labels. This high within-class similarity can be attributed to the fact that previous methods use samples from different classes to construct a single batch for batch normalization (BN) matching. To reduce the within-class similarity, we introduce class-wise supervision during the image synthesizing process by batching the samples within classes, instead of across classes. As a result, we can increase within-class diversity and reduce the size of required soft labels. A key benefit of improved image diversity is that soft label compression can be achieved through simple random pruning, eliminating the need for complex rule-based strategies. Experiments validate our discoveries. For example, when condensing ImageNet-1K to 200 images per class, our approach compresses the required soft labels from 113 GB to 2. 8 GB (40$\times$ compression) with a 2. 6\% performance gain. Code is available at: https: //github. com/he-y/soft-label-pruning-for-dataset-distillation

PDF Details DOI

JBHI Journal 2024 Journal Article

Craniomaxillofacial Bone Segmentation and Landmark Detection Using Semantic Segmentation Networks and an Unbiased Heatmap

Runshi Zhang
Bimeng Jie
Yang He
Liang Zhu
Zefeng Xie
Zhan Liu
Hao Mo
Junchen Wang

Craniomaxillofacial (CMF) surgery always relies on accurate preoperative planning to assist surgeons, and automatically generating bone structures and digitizing landmarks for CMF preoperative planning is crucial. Since the soft and hard tissues of the CMF regions possess complicated attachment, segmenting the CMF bones and detecting the CMF landmarks are challenging problems. In this study, we proposed a semantic segmentation network to segment the maxilla, mandible, zygoma, zygomatic arch, and frontal bones. Then, we obtained the minimum bounding box around the CMF bones. After cropping, we used the top-down heatmap landmark detection network, similar to the segmentation module, to identify 18 CMF landmarks from the cropping patch. In addition, an unbiased heatmap encoding method was proposed to generate actual landmark coordinates in the heatmap. To overcome quantization effects in the heatmap-based landmark detection networks, the distribution-prior coordinate representation of medical landmarks (DCRML) was proposed to utilize the prior distribution of the encoding heatmap, approximating the accurate landmark coordinates in heatmap decoding by Taylor's theorem. The encoding and decoding method can easily contribute to other existing landmark detection frameworks based on heatmaps; consequently, these approaches can readily benefit without changing model structure. We used prior segmentation knowledge to enhance the semantic information around the landmarks, increasing landmark detection accuracy. The proposed framework was evaluated by 100 healthy persons and 86 patients from multicenter cooperation. The mean Dice score of our proposed segmentation network achieved over 88 %; in particular, the mandible accuracy was approximately 95%. The mean error of landmarks was 1. 84 $\pm$ 1. 32 mm.

Details DOI

IROS Conference 2024 Conference Paper

Research of calibration method for fusion of LDS sensor and ToF low-cost sensor

Jiahui Zhu
Guitao Yu
Yang He
Kui Yang
Dongtai Liang

This paper proposes a method for calibrating the external parameters of the LDS sensor and ToF depth camera based on three cylinders. This method obtains the scanning data of the side surfaces of the three cylinders at different postures by changing the posture of the robot. For the single-line laser plane scanned by the LDS sensor, three elliptical contours are obtained by intersecting with the side surfaces of the three cylinders respectively. The Random Sample Consensus (RANSAC) algorithm is used to obtain the coordinates of the center points of the three elliptical contours and two random points on each elliptical contour. For the three-dimensional point cloud image of the cylinder scanned by the ToF depth camera, the RANSAC algorithm is used to fit the central axis of the three cylinders. The nonlinear optimization equation is established using the three center points obtained from the three elliptical contours and the distances from the two random points on each elliptical contour to their corresponding central axes. In this paper, we propose to use a fusion method of the Powell algorithm and the BFGS algorithm to solve the nonlinear optimization equations to obtain the transformation matrix between the LDS sensor and the ToF depth camera. Finally, simulation and actual test are carried out based on the proposed method, and the influence of the initial value of the calibration parameter on the calibration result is discussed. The accuracy of the calibration algorithm in this paper is verified through comparative experiments of the calibration algorithm. The results show that the calibration accuracy of the proposed method is better than that of the traditional planar calibration method, and it has the characteristics of simple operation and high calibration accuracy.

Details

ICRA Conference 2024 Conference Paper

Robotic Craniomaxillofacial Osteotomy System Using Acoustic 3D Registration

Jiayu Zhu
Runzhe Han
Mengning Yuan
Bimeng Jie
Shanshan Du
Yang He
Runshi Zhang
Junchen Wang

Osteotomy holds a pivotal position among the fundamental procedures in craniomaxillofacial (CMF) surgery. However, there are inherent challenges and risks associated with ensuring the recuperation of occlusion, safeguarding the facial nerves and blood vessels, as well as preserving facial aesthetics. In this study, a non-invasive image-to-patient registration method for navigation/robotic CMF surgery based on intraoperative freehand ultrasound (US) 3D reconstruction is proposed. Building upon this, a CMF osteotomy robotic system with compliant human-robot interaction and osteotomy trajectory planning was devised. In the freehand US 3D reconstruction and registration experiments, the registration errors for human volunteers and phantoms were consistently less than 1 mm. In robot osteotomy experiments based on the resulting registration, the average osteotomy error was below 1. 5 mm. The proposed US 3D reconstruction based registration method is non-invasive and radiation-free, and shows the promising accuracy which is suitable for CMF robotic or navigation systems.

Details

NeurIPS Conference 2023 Conference Paper

You Only Condense Once: Two Rules for Pruning Condensed Datasets

Yang He
Lingao Xiao
Joey Tianyi Zhou

Dataset condensation is a crucial tool for enhancing training efficiency by reducing the size of the training dataset, particularly in on-device scenarios. However, these scenarios have two significant challenges: 1) the varying computational resources available on the devices require a dataset size different from the pre-defined condensed dataset, and 2) the limited computational resources often preclude the possibility of conducting additional condensation processes. We introduce You Only Condense Once (YOCO) to overcome these limitations. On top of one condensed dataset, YOCO produces smaller condensed datasets with two embarrassingly simple dataset pruning rules: Low LBPE Score and Balanced Construction. YOCO offers two key advantages: 1) it can flexibly resize the dataset to fit varying computational constraints, and 2) it eliminates the need for extra condensation processes, which can be computationally prohibitive. Experiments validate our findings on networks including ConvNet, ResNet and DenseNet, and datasets including CIFAR-10, CIFAR-100 and ImageNet. For example, our YOCO surpassed various dataset condensation and dataset pruning methods on CIFAR-10 with ten Images Per Class (IPC), achieving 6. 98-8. 89% and 6. 31-23. 92% accuracy gains, respectively. The code is available at: https: //github. com/he-y/you-only-condense-once.

PDF Details

EAAI Journal 2021 Journal Article

A multiclass classification using one-versus-all approach with the differential partition sampling ensemble

Xin Gao
Yang He
Mi Zhang
Xinping Diao
Xiao Jing
Bing Ren
Weijia Ji

The One-versus-all(OVA) approach is one of the mainstream decomposition methods by which multiple binary classifiers are used to solve multiclass classification tasks. However, it exists the problems of serious class imbalance. This paper proposes a differential partition sampling ensemble method(DPSE) in the OVA framework. The number of majority samples and that of the minority samples in each binary training dataset are used as the upper and lower limits of the sampling interval respectively. Within this range, the construction process of the arithmetic sequence is simulated to generate the set containing multiple different sampling numbers with equal intervals. All samples are divided into safe examples, borderline examples, rare examples, and outliers according to the neighborhood information, then Random undersampling for safe samples(s-Random undersampling) and SMOTE for borderline examples and rare examples (br-SMOTE) are proposed based on the distribution characteristics of the classes. In each iteration, according to the number of differential sampling, the two methods are used to undersample or oversample the majority and minority in each binary training dataset to balance the number of positive and negative samples, which preserves the characteristic of the class structure as much as possible. Balanced training sets are used to train the binary classification model with multiple sub classifiers. The thorough experiments performed on 27 KEEL public multiclass datasets show that DPSE outperforms the typical methods in the OVA scheme, the One-versus-One scheme or direct way in classification performance.

Details DOI

IJCAI Conference 2021 Conference Paper

Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis

Yang He
Ning Yu
Margret Keuper
Mario Fritz

The rapid advances in deep generative models over the past years have led to highly realistic media, known as deepfakes, that are commonly indistinguishable from real to human eyes. These advances make assessing the authenticity of visual data increasingly difficult and pose a misinformation threat to the trustworthiness of visual content in general. Although recent work has shown strong detection accuracy of such deepfakes, the success largely relies on identifying frequency artifacts in the generated images, which will not yield a sustainable detection approach as generative models continue evolving and closing the gap to real images. In order to overcome this issue, we propose a novel fake detection that is designed to re-synthesize testing images and extract visual cues for detection. The re-synthesis procedure is flexible, allowing us to incorporate a series of visual tasks - we adopt super-resolution, denoising and colorization as the re-synthesis. We demonstrate the improved effectiveness, cross-GAN generalization, and robustness against perturbations of our approach in a variety of detection scenarios involving multiple generators over CelebA-HQ, FFHQ, and LSUN datasets. Source code is available at https: //github. com/SSAW14/BeyondtheSpectrum.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

An Attention-based Model for Conversion Rate Prediction with Delayed Feedback via Post-click Calibration

Yumin Su
Liang Zhang
Quanyu Dai
Bo Zhang
Jinyao Yan
Dan Wang
Yongjun Bao
Sulong Xu

Conversion rate (CVR) prediction is becoming increasingly important in the multi-billion dollar online display advertising industry. It has two major challenges: firstly, the scarce user history data is very complicated and non-linear; secondly, the time delay between the clicks and the corresponding conversions can be very large, e. g. , ranging from seconds to weeks. Existing models usually suffer from such scarce and delayed conversion behaviors. In this paper, we propose a novel deep learning framework to tackle the two challenges. Specifically, we extract the pre-trained embedding from impressions/clicks to assist in conversion models and propose an inner/self-attention mechanism to capture the fine-grained personalized product purchase interests from the sequential click data. Besides, to overcome the time-delay issue, we calibrate the delay model by learning dynamic hazard function with the abundant post-click data more in line with the real distribution. Empirical experiments with real-world user behavior data prove the effectiveness of the proposed method.

PDF Details DOI

AAAI Conference 2018 Short Paper

Enhancing RNN Based OCR by Transductive Transfer Learning From Text to Images

Yang He
Jingling Yuan
Lin Li

This paper presents a novel approach for optical character recognition (OCR) on acceleration and to avoid underfitting by text. Previously proposed OCR models typically take much time in the training phase and require large amount of labelled data to avoid underfitting. In contrast, our method does not require such condition. This is a challenging task related to transferring the character sequential relationship from text to OCR. We build a model based on transductive transfer learning to achieve domain adaptation from text to image. We thoroughly evaluate our approach on different datasets, including a general one and a relatively small one. We also compare the performance of our model with the general OCR model on different circumstances. We show that (1) our approach accelerates the training phase 20-30% on time cost; and (2) our approach can avoid underfitting while model is trained on a small dataset

PDF Details

IJCAI Conference 2018 Conference Paper

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

Yang He
Guoliang Kang
Xuanyi Dong
Yanwei Fu
Yi Yang

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pretrained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0. 2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https: //github. com/he-y/softfilter-pruning

PDF Details

AAAI Conference 2018 Conference Paper

Telepath: Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems

Yu Wang
Jixing Xu
Aohan Wu
Mantian Li
Yang He
Jinghe Hu
Weipeng Yan

Designing an e-commerce recommender system that serves hundreds of millions of active users is a daunting challenge. To our best knowledge, the complex brain activity mechanism behind human shopping activities is never considered in existing recommender systems. From a human vision perspective, we found two key factors that affect users’ behaviors: items’ attractiveness and their matching degrees with users’ interests. This paper proposes Telepath, a visionbased bionic recommender system model, which simulates human brain activities in decision making of shopping, thus understanding users from such perspective. The core of Telepath is a complex deep neural network with multiple subnetworks. In practice, the Telepath model has been launched to JD’s recommender system and advertising system and outperformed the former state-of-the-art method. For one of the major item recommendation blocks on the JD app, clickthrough rate (CTR), gross merchandise value (GMV) and orders have been increased 1. 59%, 8. 16% and 8. 71% respectively by Telepath. For several major ad publishers of JD demand-side platform, CTR, GMV and return on investment have been increased 6. 58%, 61. 72% and 65. 57% respectively by the first launch of Telepath, and further increased 2. 95%, 41. 75% and 41. 37% respectively by the second launch.

PDF Details