Author name cluster

Yingjie Wang

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.

16 papers

2 author rows

EAAI Journal 2026 Journal Article

Multi-dimensional logic anomaly inspection method for assembly components based on virtual domain contrastive pre-training

Yangfeng Wang
Changyang Yu
Yingjie Wang
Hui Shi
Wenyong Yu

Complex mechanical structures, such as engines, must undergo rigorous integrity inspection before leaving the factory. However, assembly logic anomaly inspection in industrial settings faces the challenges of high task complexity and high data acquisition costs, making traditional methods difficult to meet the requirements of efficiency and accuracy demanded by intelligent production lines. To address this issue, this study developed a multi-dimensional logic anomaly inspection method for assembly components based on virtual domain contrastive pre-Training. In this method, the virtual pre-training phase leverages the proposed Virtual Component MOCO (VC-MOCO) to integrate pre-trained weights with prior knowledge. During the downstream task transfer phase, multi-dimensional DEtection Transformer (DETR) facilitates dimensionality reduction, thereby enabling the attainment of superior results under reduced data requirements. Comparative experiments are conducted with various single dimension methods. The results show that the multi-dimensional DETR using the VC-MOCO pre-training achieved optimal performance with Average Precision (@0. 5: 0. 95) = 0. 918 and Recall (@0. 5: 0. 95) = 0. 944. This achievement demonstrates that the combination of customized pre-training based on virtual domains and multi-dimensional architectures can effectively enhance the data utilization efficiency and inspection performance of models. This research will be able to provide novel insights for industrial scenarios with data scarcity and high-performance demands, thereby accelerating the application of intelligent systems within industrial environments.

Details DOI

AAAI Conference 2026 Conference Paper

Towards Understanding In-Context Learning of Transformers Under Non-I.I.D. Scenarios

Qilu Shen
Yingjie Wang
Jinhai Xiang

Understanding the generalization behavior of in-context learning (ICL) in Transformers remains a fundamental challenge, as most existing theoretical analyses are based on the assumption that data are independently and identically distributed (i.i.d.), an assumption that often does not hold in practice. Motivated by the theoretical insight that ICL operates similarly to gradient-based optimization, we leverage the concept of gradient stability to establish generalization error bounds for ICL under a general non-i.i.d. setting. Our analysis shows that two factors play a central role in ICL generalization: the number of demonstrations in the prompt and their distributional alignment with the query. In particular, increasing the number of demonstrations and improving their alignment with the query distribution lead to better generalization, even without any parameter tuning. Under mild conditions, we further prove that the generalization error can achieve the optimal convergence rate of O(N^(-1/2)), where N is the number of demonstrations. Our empirical evaluations validate the effectiveness of our theoretical findings.

PDF Details DOI

ICLR Conference 2025 Conference Paper

A Statistical Approach for Controlled Training Data Detection

Zirui Hu
Yingjie Wang
Zheng Zhang
Hong Chen
Dacheng Tao

Detecting training data for large language models (LLMs) is receiving growing attention, especially in applications requiring high reliability. While numerous efforts have been made to address this issue, they typically focus on accuracy without ensuring controllable results. To fill this gap, we propose **K**nockoff Inference-based **T**raining data **D**etector (KTD), a novel method that achieves rigorous false discovery rate (FDR) control in training data detection. Specifically, KTD generates synthetic knockoff samples that seamlessly replace original data points without compromising contextual integrity. A novel knockoff statistic, which incorporates multiple knockoff draws, is then calculated to ensure FDR control while maintaining high power. Our theoretical analysis demonstrates KTD's asymptotic optimality in terms of FDR control and power. Empirical experiments on real-world datasets such as WikiMIA, XSum and Real Time BBC News further validate KTD's superior performance compared to existing methods.

Details

ICLR Conference 2025 Conference Paper

A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops

Shi Fu
Yingjie Wang
Yuzhu Chen
Xinmei Tian 0001
Dacheng Tao

High-quality data is essential for training large generative models, yet the vast reservoir of real data available online has become nearly depleted. Consequently, models increasingly generate their own data for further training, forming Self-consuming Training Loops (STLs). However, the empirical results have been strikingly inconsistent: some models degrade or even collapse, while others successfully avoid these failures, leaving a significant gap in theoretical understanding to explain this discrepancy. This paper introduces the intriguing notion of *recursive stability* and presents the first theoretical generalization analysis, revealing how both model architecture and the proportion between real and synthetic data influence the success of STLs. We further extend this analysis to transformers in in-context learning, showing that even a constant-sized proportion of real data ensures convergence, while also providing insights into optimal synthetic data sizing.

Details

NeurIPS Conference 2025 Conference Paper

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning

Kongcheng Zhang
QI YAO
Shunyu Liu
Yingjie Wang
Baisheng Lai
Jieping Ye
Mingli Song
Dacheng Tao

Recent advances of Reinforcement Learning (RL) have highlighted its potential in complex reasoning tasks, yet effective training often relies on external supervision, which limits the broader applicability. In this work, we propose a novel self-rewarding reinforcement learning framework to enhance Large Language Model (LLM) reasoning by leveraging the consistency of intermediate reasoning states across different reasoning trajectories. Our key insight is that correct responses often exhibit consistent trajectory patterns in terms of model likelihood: their intermediate reasoning states tend to converge toward their own final answers ( high consistency ) with minimal deviation toward other candidates ( low volatility ). Inspired by this observation, we introduce CoVo, an intrinsic reward mechanism that integrates Co nsistency and Vo latility via a robust vector-space aggregation strategy, complemented by a curiosity bonus to promote diverse exploration. CoVo enables LLMs to perform RL in a self-rewarding manner, offering a scalable pathway for learning to reason without external supervision. Extensive experiments on diverse reasoning benchmarks show that CoVo achieves performance comparable to or even surpassing supervised RL. Our code is available at https: //github. com/sastpg/CoVo.

PDF Details

AAAI Conference 2025 Conference Paper

Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent

Jun Chen
Hong Chen
Bin Gu
Guodong Liu
Yingjie Wang
Weifu Li

In recent years, there have been a growing number of works studying the generalization properties of stochastic gradient descent (SGD) from the perspective of algorithmic stability. However, few of them devote to simultaneously studying the generalization and optimization for the non-convex setting, especially pairwise SGD with heavy-tailed gradient noise. This paper considers the impact of the heavy-tailed gradient noise obeying sub-Weibull distribution on the stability-based learning guarantees for non-convex pairwise SGD by investigating its generalization and optimization jointly. Specifically, based on two novel pairwise uniform model stability tools, we firstly bound the generalization error of pairwise SGD in the general non-convex setting after bridging the quantitative relationships between stability and generalization error. Then, we further consider the practical heavy-tailed sub-Weibull gradient noise condition to establish a refined generalization bound without the bounded gradient condition. Finally, sharper error bounds for generalization and optimization are built by introducing the gradient dominance condition. Comparing these results reveals that sub-Weibull gradient noise brings some positive dependencies on the heavy-tailed strength for generalization and optimization. Furthermore, we extend our analysis to the corresponding pairwise minibatch SGD and derive the first stability-based near-optimal generalization and optimization bounds which are consistent with many empirical observations.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Huanjin Yao
Jiaxing Huang
Wenhao Wu
Jingyi Zhang
Yibo Wang
Shunyu Liu
Yingjie Wang
YuXin Song

In this work, we aim to develop an MLLM that understands and solves questions by learning to create each intermediate step of the reasoning involved till the final answer. To this end, we propose Collective Monte Carlo Tree Search (CoMCTS), a new learning-to-reason method for MLLMs, which introduces the concept of collective learning into ``tree search'' for effective and efficient reasoning-path searching and learning. The core idea of CoMCTS is to leverage collective knowledge from multiple models to collaboratively conjecture, search and identify effective reasoning paths toward correct answers via four iterative operations including Expansion, Simulation and Error Positioning, Backpropagation, and Selection. Using CoMCTS, we construct Mulberry-260k, a multimodal dataset with a tree of rich, explicit and well-defined reasoning nodes for each question. With Mulberry-260k, we perform collective SFT to train our model, Mulberry, a series of MLLMs with o1-like step-by-step Reasoning and Reflection capabilities. Extensive experiments demonstrate the superiority of our proposed methods on various benchmarks. Code is available at https: //github. com/HJYao00/Mulberry.

PDF Details

JBHI Journal 2025 Journal Article

Multi-Modal Encrypted Retrieval Method with Semantic Feature Fusion towards Internet of Medical Things

Puning Zhang
Yingjie Wang
Jing Wang
Zhen Zhang

There exists a tremendous amount of multimodal data in the Internet of Medical Things (IoMT), retrieval technology can extract target data on demand from the extensive multimodal medical data space, which is crucial for aiding diagnosis and medical informatization. However, existing methods only focus on single-modal data such as medical texts, without considering the privacy protection and retrieval needs of users' multimodal data. Furthermore, these existing methods only match keywords and fail to effectively mine the semantic features of multimodal data, thereby limiting the performance of retrieval systems. To address these issues, this paper proposes a multimodal encrypted retrieval method for the IoMT based on semantic feature fusion and designs a multimodal semantic feature extraction model based on searchable encryption technology to enable encrypted retrieval of multimodal data. Specifically, an edge-cloud collaboration concept is introduced to underpin a secure semantic search architecture tailored for multimodal data, which ensures low-latency encrypted retrieval while safeguarding user privacy. Besides, a semantic-aware multimodal feature extraction method is designed, enhancing the capability of mining semantic features and replacing the traditional keyword retrieval mode with semantic feature retrieval. Moreover, a multimodal data encrypted retrieval method is proposed, employing a block idea and parallel search tree structure, which achieves rapid retrieval of semantic similarity with low-cost and privacy-preserving. Simulation results demonstrate that the proposed method significantly outperforms the latest research regarding precision, search delay, and storage overhead.

Details DOI

ICML Conference 2025 Conference Paper

Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG

Wenbin Wang
Yongcheng Jing
Liang Ding 0006
Yingjie Wang
Li Shen 0008
Yong Luo 0002
Bo Du 0001
Dacheng Tao

High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To drive progress beyond the limits of heuristic methods, this paper advances HR perception capabilities of MLLMs by harnessing cutting-edge long-context techniques such as retrieval-augmented generation (RAG). Towards this end, this paper presents the first study exploring the use of RAG to address HR perception challenges. Specifically, we propose Retrieval-Augmented Perception (RAP), a training-free framework that retrieves and fuses relevant image crops while preserving spatial context using the proposed Spatial-Awareness Layout. To accommodate different tasks, the proposed Retrieved-Exploration Search (RE-Search) dynamically selects the optimal number of crops based on model confidence and retrieval scores. Experimental results on HR benchmarks demonstrate the significant effectiveness of RAP, with LLaVA-v1. 5-13B achieving a 43% improvement on $V^*$ Bench and 19% on HR-Bench. Code is available at https: //github. com/DreamMr/RAP.

Details

NeurIPS Conference 2025 Conference Paper

Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training

Shi Fu
Yingjie Wang
Yuzhu Chen
Li Shen
Dacheng Tao

Large generative models are increasingly trained on synthetic data from earlier generations, raising concerns about model collapse, a progressive performance decline consistently observed in empirical studies. However, theoretical understanding of recursive training dynamics and their failure modes remains limited. In this work, we theoretically show that recursive training inherently leads to exponential error growth unless mitigated by sufficient real data. Addressing the growing scarcity of real data, we introduce a self-verification mechanism enabling models to filter their outputs based on internal confidence scores without external validation. Through rigorous analysis, we derive finite-sample error bounds demonstrating that self-verification alone can prevent collapse, even in fully synthetic training regimes. Our theoretical framework extends to large language models (LLMs), characterizing the conditions under which recursive training can maintain stability without performance degradation.

PDF Details

IJCAI Conference 2024 Conference Paper

Counterfactual User Sequence Synthesis Augmented with Continuous Time Dynamic Preference Modeling for Sequential POI Recommendation

Lianyong Qi
Yuwen Liu
Weiming Liu
Shichao Pei
Xiaolong Xu
Xuyun Zhang
Yingjie Wang
Wanchun Dou

With the proliferation of Location-based Social Networks (LBSNs), user check-in data at Points-of-Interest (POIs) has surged, offering rich insights into user preferences. However, sequential POI recommendation systems always face two pivotal challenges. A challenge lies in the difficulty of modeling time in a discrete space, which fails to accurately capture the dynamic nature of user preferences. Another challenge is the inherent sparsity and noise in continuous POI recommendation, which hinder the recommendation process. To address these challenges, we propose counterfactual user sequence synthesis with continuous time dynamic preference modeling (CussCtpm). CussCtpm innovatively combines Gated Recurrent Unit (GRU) with neural Ordinary Differential Equations (ODEs) to model user preferences in a continuous time framework. CussCtpm captures user preferences at both the POI-level and interest-level, identifying deterministic and non-deterministic preference concepts. Particularly at the interest-level, we employ GRU and neural ODEs to model users' dynamic preferences in continuous space, aiming to capture finer-grained shifts in user preferences over time. Furthermore, CussCtpm utilizes counterfactual data augmentation to generate counterfactual positive and negative user sequences. Our extensive experiments on two widely-used public datasets demonstrate that CussCtpm outperforms several advanced baseline models.

PDF Details DOI

IROS Conference 2024 Conference Paper

CRPlace: Camera-Radar Fusion with BEV Representation for Place Recognition

Shaowei Fu
Yifan Duan
Yao Li 0016
Chengzhen Meng
Yingjie Wang
Jianmin Ji
Yanyong Zhang

The integration of complementary characteristics from camera and radar data has emerged as an effective approach in 3D object detection. However, such fusion-based methods remain unexplored for place recognition, an equally important task for autonomous systems. Given that place recognition relies on the similarity between a query scene and the corresponding candidate scene, the stationary background of a scene is expected to play a crucial role in the task. As such, current well-designed camera-radar fusion methods for 3D object detection can hardly take effect in place recognition because they mainly focus on dynamic foreground objects. In this paper, a background-attentive camera-radar fusion-based method, named CRPlace, is proposed to generate background-attentive global descriptors from multi-view images and radar point clouds for accurate place recognition. To extract stationary background features effectively, we design an adaptive module that generates the background-attentive mask by utilizing the camera BEV feature and radar dynamic points. With the guidance of a background mask, we devise a bidirectional cross-attention-based spatial fusion strategy to facilitate comprehensive spatial interaction between the background information of the camera BEV feature and the radar BEV feature. As the first camera-radar fusion-based place recognition network, CRPlace has been evaluated thoroughly on the nuScenes dataset. The results show that our algorithm outperforms a variety of baseline methods across a comprehensive set of metrics (recall@1 reaches 91. 2%).

Details

NeurIPS Conference 2023 Conference Paper

CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection

Yingjie Wang
Jiajun Deng
Yuenan Hou
Yao Li
Yu Zhang
Jianmin Ji
Wanli Ouyang
Yanyong Zhang

Currently, LiDAR-based 3D detectors are broadly categorized into two groups, namely, BEV-based detectors and cluster-based detectors. BEV-based detectors capture the contextual information from the Bird's Eye View (BEV) and fill their center voxels via feature diffusion with a stack of convolution layers, which, however, weakens the capability of presenting an object with the center point. On the other hand, cluster-based detectors exploit the voting mechanism and aggregate the foreground points into object-centric clusters for further prediction. In this paper, we explore how to effectively combine these two complementary representations into a unified framework. Specifically, we propose a new 3D object detection framework, referred to as CluB, which incorporates an auxiliary cluster-based branch into the BEV-based detector by enriching the object representation at both feature and query levels. Technically, CluB is comprised of two steps. First, we construct a cluster feature diffusion module to establish the association between cluster features and BEV features in a subtle and adaptive fashion. Based on that, an imitation loss is introduced to distill object-centric knowledge from the cluster features to the BEV features. Second, we design a cluster query generation module to leverage the voting centers directly from the cluster branch, thus enriching the diversity of object queries. Meanwhile, a direction loss is employed to encourage a more accurate voting center for each cluster. Extensive experiments are conducted on Waymo and nuScenes datasets, and our CluB achieves state-of-the-art performance on both benchmarks.

PDF Details

AAAI Conference 2022 Conference Paper

Error-Based Knockoffs Inference for Controlled Feature Selection

Xuebin Zhao
Hong Chen
Yingjie Wang
Weifu Li
Tieliang Gong
Yulong Wang
Feng Zheng

Recently, the scheme of model-X knockoffs was proposed as a promising solution to address controlled feature selection under high-dimensional finite-sample settings. However, the procedure of model-X knockoffs depends heavily on the coefficient-based feature importance and only concerns the control of false discovery rate (FDR). To further improve its adaptivity and flexibility, in this paper, we propose an error-based knockoff inference method by integrating the knockoff features, the error-based feature importance statistics, and the stepdown procedure together. The proposed inference procedure does not require specifying a regression model and can handle feature selection with theoretical guarantees on controlling false discovery proportion (FDP), FDR, or k-familywise error rate (k-FWER). Empirical evaluations demonstrate the competitive performance of our approach on both simulated and real data.

PDF Details

AAAI Conference 2021 Conference Paper

Distributed Ranking with Communications: Approximation Analysis and Applications

Hong Chen
Yingjie Wang
Yulong Wang
Feng Zheng

Learning theory of distributed algorithms has recently attracted enormous attention in the machine learning community. However, most of existing works focus on learning problem with pointwise loss and does not consider the communication among local processors. In this paper, we propose a new distributed pairwise ranking with communication (called DLSRank-C) based on the Newton-Raphson iteration, and establish its learning rate analysis in probability. Theoretical and empirical assessments demonstrate the effectiveness of DLSRank-C under mild conditions.

PDF Details

NeurIPS Conference 2020 Conference Paper

Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery

Yingjie Wang
Hong Chen
Feng Zheng
Chen Xu
Tieliang Gong
Yanhong Chen

Additive models have attracted much attention for high-dimensional regression estimation and variable selection. However, the existing models are usually limited to the single-task learning framework under the mean squared error (MSE) criterion, where the utilization of variable structure depends heavily on priori knowledge among variables. For high-dimensional observations in real environment, e. g. , Coronal Mass Ejections (CMEs) data, the learning performance of previous methods may be degraded seriously due to the complex non-Gaussian noise and the insufficiency of prior knowledge on variable structure. To tackle this problem, we propose a new class of additive models, called Multi-task Additive Models (MAM), by integrating the mode-induced metric, the structure-based regularizer, and additive hypothesis spaces into a bilevel optimization framework. Our approach does not require any priori knowledge of variable structure and suits for high-dimensional data with complex noise, e. g. , skewed noise, heavy-tailed noise, and outliers. A smooth iterative optimization algorithm with convergence guarantees is provided to implement MAM efficiently. Experiments on simulations and the CMEs analysis demonstrate the competitive performance of our approach for robust estimation and automatic structure discovery.

PDF Details