Author name cluster

Ning Yang

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.

11 papers

2 author rows

AAAI Conference 2026 Conference Paper

CrossCheck-Bench: Diagnosing Compositional Failures in Multimodal Conflict Resolution

Baoliang Tian
Yuxuan Si
Jilong Wang
LingYao Li
Zhongyuan Bao
Zineng Zhou
Tao Wang
Sixu Li

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual cues often conflict, requiring models to perform structured reasoning beyond surface-level alignment. We introduce CrossCheck-Bench, a diagnostic benchmark for evaluating contradiction detection in multimodal inputs. The benchmark adopts a hierarchical task framework covering three levels of reasoning complexity and defines seven atomic capabilities essential for resolving cross-modal inconsistencies. CrossCheck-Bench includes 15k question-answer pairs sourced from real-world artifacts with synthetically injected contradictions. The dataset is constructed through a multi-stage annotation pipeline involving more than 450 expert hours to ensure semantic validity and calibrated difficulty across perception, integration, and reasoning. We evaluate 13 state-of-the-art vision-language models and observe a consistent performance drop as tasks shift from perceptual matching to logical contradiction detection. Most models perform well on isolated entity recognition but fail when multiple clues must be synthesized for conflict reasoning. Capability-level analysis further reveals uneven skill acquisition, especially in tasks requiring multi-step inference or rule-based validation. Additional probing shows that conventional prompting strategies such as Chain-of-Thought and Set-of-Mark yield only marginal gains. By contrast, methods that interleave symbolic reasoning with grounded visual processing achieve more stable improvements. These results highlight a persistent bottleneck in multimodal reasoning and suggest new directions for building models capable of robust cross-modal verification.

PDF Details DOI

AAMAS Conference 2026 Conference Paper

Feasible Constraint Policy Optimization for Safe Reinforcement Learning

Luoyang Sun
Jiwen Jiang
Ning Yang
Rasul Tutunov
Haifeng Zhang
Jun Wang

Safe reinforcement learning (RL) ensures that policies satisfy explicit constraints in safety-critical applications. However, existing primal-dual methods suffer from training instability. Trust regionbased approaches often produce infeasible policies during training due to initialization and approximation errors. We introduce Feasible Constraint Policy Optimization (FCPO), which seamlessly combines penalty and trust region methods to address policy feasibility while ensuring stability and performance. FCPO efficiently decomposes optimization problems with the Alternating Direction Multiplier Method (ADMM), enabling efficient optimization through the utilization of first-order degree information. Comprehensive experiments showcase FCPO’s consistent superiority, outperforming the baselines in both performance and constraint satisfaction across the majority of tasks.

PDF

AAAI Conference 2026 Conference Paper

Proactive Constrained Policy Optimization with Preemptive Penalty

Ning Yang
Pengyu Wang
Guoqing Liu
Haifeng Zhang
Pin Lyu
Jun Wang

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific constraints like safety. Typically, constrained optimization problems are addressed by the Lagrangian method, a post-violation remedial approach that may result in oscillations and overshoots. Motivated by this, we propose a novel method named Proactive Constrained Policy Optimization (PCPO) that incorporates a preemptive penalty mechanism. This mechanism integrates barrier items into the objective function as the policy nears the boundary, imposing a cost. Meanwhile, we introduce a constraint-aware intrinsic reward to guide boundary-aware exploration, which is activated only when the policy approaches the constraint boundary. We establish theoretical upper and lower bounds for the duality gap and the performance of the PCPO update, shedding light on the method's convergence characteristics. Additionally, to enhance the optimization performance, we adopt a policy iteration approach. An interesting finding is that PCPO demonstrates significant stability in experiments. Experimental results indicate that the PCPO framework provides a robust solution for policy optimization under constraints, with important implications for future research and practical applications.

PDF Details DOI

AAAI Conference 2026 Conference Paper

TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning

Yuxuan Li
Yicheng Gao
Ning Yang
Stephen Xia

Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, these tasks often feature hidden “trap states”—irreversible failures that prevent task completion but do not provide explicit negative rewards to guide agents away from repeated errors. To address these issues, we propose Time-Weighted Contrastive Reward Learning (TW-CRL), an Inverse Reinforcement Learning (IRL) framework that leverages both successful and failed demonstrations. By incorporating temporal information, TW-CRL learns a dense reward function that identifies critical states associated with success or failure. This approach not only enables agents to avoid trap states but also encourages meaningful exploration beyond simple imitation of expert trajectories. Empirical evaluations on navigation tasks and robotic manipulation benchmarks demonstrate that TW-CRL surpasses state-of-the-art methods, achieving improved efficiency and robustness.

PDF Details DOI

EAAI Journal 2025 Journal Article

A unified multi-task model for leaf disease region detection and segmentation

Tian Zhang
Yanfeng Lu
Chenshuang Li
Rundong Hong
Hengqiang Su
Ce Yang
Ning Yang
Haiying Zhang

Crop diseases challenge agricultural production. Pinpointing disease spots, assessing infection areas, and gauging infection severity are crucial for effective disease control. However, lesion variations, blurred boundaries, and small, dense lesions make precise detection and segmentation difficult. This paper presents an end-to-end unified multi-task model based on Detection Transformer (DETR) for leaf disease region detection and segmentation. It integrates Convolutional Neural Networks (CNNs) and Transformer, uses the Contextual Transformer Network (CoTNet) for feature extraction, and incorporates innovative mechanisms like box-attention and reference window update. Additionally, we have devised a novel instance segmentation head. This head effectively addresses the misclassification issue between minute disease spots and leaf surfaces. Experiments show the model achieves Average Precision ( AP ). The Average Precision of Bounding Box ( AP box ) of 73. 9 %, the Average Precision of Mask ( AP mask ) of 68. 2 %, the Average Precision of Small-sized Bounding Box ( AP s box ) of 29. 0 %, and the Average Precision of Small-sized Mask ( AP s mask ) of 27. 1 % for four diseases, with detection recall reaching 76. 8 % and segmentation recall reaching 73. 4 %. Meanwhile. The model architecture demonstrates practical feasibility with 40. 1 million (m) parameters and 169 Giga Floating-point Operations Per Second (GFLOP) computational complexity. The accuracy of disease grading reaches 92. 07 %. In this study, a model based on Artificial Intelligence (AI) was implemented to address the challenges in leaf disease detection and segmentation. The proposed model, which integrates object detection and instance segmentation tasks, can be applied to accurately identify and grade leaf diseases, providing support for disease control strategies in agriculture.

Details DOI

JBHI Journal 2025 Journal Article

CorrMorph: Unsupervised Deformable Brain MRI Registration Based on Correlation Mining

Yuan Chang
Zheng Li
Ning Yang

Deformable image registration, as a fundamental prerequisite for many medical image analysis tasks, has received considerable attention. However, existing methods suffer from two key issues: 1) single-stream methods that stack moving and fixed images as input are prone to interference from spatial misalignment and style discrepancy, while dual-stream methods that use fully parallel encoders face challenges in learning correlations between images. 2) CNN-based methods are difficult to capture the complex spatial correspondences between images, while Transformer-based methods lack the ability to capture local context information. Therefore, we propose an unsupervised deformable brain MRI registration network, CorrMorph, which achieves reasonable and accurate registration by mining correlations. Specifically, we design a match-fusion strategy that allows the independent extraction of shallow features from the moving and fixed images while capturing their correlations in deeper layers. Furthermore, we propose two novel modules. 1) Correlation Matching Module (CMM), which mines correlations between images to achieve effective feature matching, 2) Feature Transmission Module (FTM), which extracts important spatial features to achieve effective feature transmission. Extensive experiments are conducted on three brain MRI datasets, and the results indicate that our method achieves state-of-the-art performance, with an average improvement of 2. 7% on DSC compared to the representative VoxelMorph.

Details DOI

ICRA Conference 2025 Conference Paper

Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization

Fei Han
Pengming Guo
Hao Chen
Weikun Li
Jingbo Ren
Naijun Liu
Ning Yang
Dixia Fan

This paper presents a Long Short-Term Memory network-based Fluid Experiment Data-Driven model (FEDLSTM) for predicting unsteady, nonlinear hydrodynamic forces on the underwater quadruped robot we constructed. Trained on experimental data from leg force and body drag tests conducted in both a recirculating water tank and a towing tank, FED-LSTM outperforms traditional Empirical Formulas (EF) commonly used for flow prediction over flat surfaces. The model demonstrates superior accuracy and adaptability in capturing complex fluid dynamics, particularly in straightline and turning-gait optimizations via the NSGA-II algorithm. FED-LSTM reduces deflection errors during straight-line swimming and improves turn times without increasing the turning radius. Hardware experiments further validate the model's precision and stability over EF. This approach provides a robust framework for enhancing the swimming performance of legged robots, laying the groundwork for future advances in underwater robotic locomotion.

Details

AAMAS Conference 2025 Conference Paper

Mean Field Correlated Imitation Learning

Zhiyu Zhao
Chengdong Ma
Qirui Mi
Ning Yang
Xue Yan
Mengyue Yang
Haifeng Zhang
Jun Wang

Modeling the behaviors of many-agent games is crucial for capturing the dynamics of large-scale complex systems. This is typically achieved by recovering policies from demonstrations within the Mean Field Game Imitation Learning (MFGIL) framework. However, most MFGIL methods assume that demonstrations are collected from Mean Field Nash Equilibrium (MFNE), implying that agents make decisions independently. When directly applied to situations where agents’ decisions are coordinated, such as publicly routed traffic networks, these techniques often fall short. In this paper, we propose the Adaptive Mean Field Correlated Equilibrium (AMFCE), which introduces a generalized assumption that effectively integrates the correlated behaviors common in real-world systems. We prove the existence of AMFCE under mild conditions and theoretically show that MFNE is a special case of AMFCE. Building upon this, we introduce a new Mean Field Correlated Imitation Learning (MFCIL) algorithm, which recovers expert policy more accurately in scenarios where agents’ decisions are coordinated. We also provide a theoretical upper bound for the error in recovering the expert policy, which is tighter than that of existing methods. Empirical results on real-world traffic flow prediction and large-scale economic simulations demonstrate that MFCIL significantly improves the predictive performance of large populations’ behaviors compared to existing MFGIL baselines. This improvement highlights potential of MFCIL to model real-world multi-agent systems. *Corresponding to Yaodong Yang ⟨yaodong. yang@pku. edu. cn⟩. This work is licensed under a Creative Commons Attribution International 4. 0 License. Proc. of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025), Y. Vorobeychik, S. Das, A. Nowé (eds.), May 19 – 23, 2025, Detroit, Michigan, USA. © 2025 International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org).

PDF

IJCAI Conference 2025 Conference Paper

Negative Metric Learning for Graphs

Yiyang Zhao
Chengpei Wu
Lilin Zhang
Ning Yang

Graph contrastive learning (GCL) often suffers from false negatives, which degrades the performance on downstream tasks. The existing methods addressing the false negative issue usually rely on human prior knowledge, still leading GCL to suboptimal results. In this paper, we propose a novel Negative Metric Learning (NML) enhanced GCL (NML-GCL). NML-GCL employs a learnable Negative Metric Network (NMN) to build a negative metric space, in which false negatives can be distinguished better from true negatives based on their distance to anchor node. To overcome the lack of explicit supervision signals for NML, we propose a joint training scheme with bi-level optimization objective, which implicitly utilizes the self-supervision signals to iteratively optimize the encoder and the negative metric network. The solid theoretical analysis and the extensive experiments conducted on widely used benchmarks verify the superiority of the proposed method.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Gait Recognition for Co-Existing Multiple People Using Millimeter Wave Sensing

Zhen Meng
Song Fu
Jie Yan
Hongyuan Liang
Anfu Zhou
Shilin Zhu
Huadong Ma
Jianhua Liu

Gait recognition, i. e. , recognizing persons from their walking postures, has found versatile applications in security check, health monitoring, and novel human-computer interaction. The millimeter-wave (mmWave) based gait recognition represents the most recent advance. Compared with traditional camera-based solutions, mmWave based gait recognition bears unique advantages of being still effective under non-line-of-sight scenarios, such as in black, weak light, or blockage conditions. Moreover, they are able to accomplish person identiﬁcation while preserving privacy. Currently, there are only few works in mmWave gait recognition, since no public data set is available. In this paper, we build a ﬁrst-of-its-kind mmWave gait data set, in which we collect gait of 95 volunteers ’seen’ from two mmWave radars in two different scenarios, which together lasts about 30 hours. Using the data set, we propose a novel deep-learning driven mmWave gait recognition method called mmGaitNet, and compare it with ﬁve state-of-the-art algorithms. We ﬁnd that mmGaitNet is able to achieve 90% accuracy for single-person scenarios, 88% accuracy for ﬁve co-existing persons, while the existing methods achieve less than 66% accuracy for both scenarios.

PDF Details

YNIMG Journal 2014 Journal Article

Fusing DTI and fMRI data: A survey of methods and applications

Dajiang Zhu
Tuo Zhang
Xi Jiang
Xintao Hu
Hanbo Chen
Ning Yang
Jinglei Lv
Junwei Han

The relationship between brain structure and function has been one of the centers of research in neuroimaging for decades. In recent years, diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI) techniques have been widely available and popular in cognitive and clinical neurosciences for examining the brain's white matter (WM) micro-structures and gray matter (GM) functions, respectively. Given the intrinsic integration of WM/GM and the complementary information embedded in DTI/fMRI data, it is natural and well-justified to combine these two neuroimaging modalities together to investigate brain structure and function and their relationships simultaneously. In the past decade, there have been remarkable achievements of DTI/fMRI fusion methods and applications in neuroimaging and human brain mapping community. This survey paper aims to review recent advancements on methodologies and applications in incorporating multimodal DTI and fMRI data, and offer our perspectives on future research directions. We envision that effective fusion of DTI/fMRI techniques will play increasingly important roles in neuroimaging and brain sciences in the years to come.

Details DOI