Yi Huang

AAAI Conference 2026 Conference Paper

C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation

• Yu Li
• Zhe Yang
• Yi Huang
• Xin Liu
• Guilin Qi

Recent advancements in large language models (LLMs) have demonstrated remarkable text generation capabilities. However, controlling specific attributes of generated text remains challenging without architectural modifications or extensive fine-tuning. Current methods typically toggle a single, basic attribute but struggle with precise multi-attribute control. In scenarios where attribute requirements conflict, existing methods lack coordination mechanisms, causing interference between desired attributes. Furthermore, these methods fail to incorporate iterative optimization processes in the controlled generation pipeline. To address these limitations, we propose Conflict-aware, Composite, and Collaborative Controlled Text Generation (C³TG), a two-phase framework for fine-grained, multi-dimensional text attribute control. During generation, C³TG selectively pairs the LLM with the required attribute classifiers from the 17 available dimensions and employs weighted KL-divergence to adjust token probabilities. The optimization phase then leverages an energy function combining classifier scores and penalty terms to resolve attribute conflicts through iterative feedback, enabling precise control over multiple dimensions simultaneously while preserving natural text flow. Experiments show that C³TG significantly outperforms baselines across multiple metrics including attribute accuracy, linguistic fluency, and output diversity, while simultaneously reducing toxicity. These results establish C³TG as an effective and flexible solution for multi-dimensional text attribute control that requires no costly model modifications.

AAAI Conference 2026 Conference Paper

Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning

• Yi Huang
• Qingyun Sun
• Yisen Gao
• Haonan Yuan
• Xingcheng Fu
• Jianxin Li

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However, its strong reliance on accurate labels makes it inherently vulnerable to label noise, prevalent in real-world scenarios, resulting in significant performance degradation and overfitting. To address this issue, we propose LaT-IB, a novel Label-Noise ResistanT Information Bottleneck method which introduces a "Minimal-Sufficient-Clean" (MSC) criterion. Instantiated as a mutual information regularizer to retain task-relevant information while discarding noise, MSC addresses standard IB’s vulnerability to noisy label supervision. To achieve this, LaT-IB employs a noise-aware latent disentanglement that decomposes the latent representation into components aligned with to the clean label space and the noise space. Theoretically, we first derive mutual information bounds for each component of our objective including prediction, compression, and disentanglement, and moreover prove that optimizing it encourages representations invariant to input noise and separates clean and noisy label information. Furthermore, we design a three-phase training framework: Warmup, Knowledge Injection and Robust Training, to progressively guide the model toward noise-resistant representations. Extensive experiments demonstrate that LaT-IB achieves superior robustness and efficiency under label noise, significantly enhancing robustness and applicability in real-world scenarios with label noise.

EAAI Journal 2026 Journal Article

Neural potential field for high-fidelity gravity modeling and density inversion of irregular small celestial bodies

• Wutong Gao
• Jianguo Yan
• Hakim Saibi
• Yi Huang

The gravity field of small celestial bodies, such as asteroids and comets, plays a critical role in revealing their internal structure and enhancing precise spacecraft navigation. Previous gravity field models face the following difficulties: (i) computational inefficiency for detailed shapes, (ii) divergence near irregular surfaces, (iii) limited capability to model heterogeneous bodies, and (iv) lack of physical feasibility for learning-based models. To overcome these limitations, we propose the neural potential field framework that represents the gravity potential using a coordinate-based neural network with periodic activation functions. By leveraging Poisson’s equation, a body’s internal density distribution can be derived directly from the learned potential field. Forward modeling experiments on the comet 67P/Churyumov-Gerasimenko and asteroid Itokawa demonstrate the model’s high accuracy. Inverse modeling applied to the asteroid Bennu, using real mission data, reveals an underdense core and equatorial bulge, consistent with prior studies. Compared to traditional models, the neural potential field model achieves the best accuracy (0. 2–0. 3 percent relative error) and efficiency (5–7 ms per 10, 000 evaluation points), while avoiding divergence issues as observed in the spherical harmonics model. Meanwhile, its compact memory footprint (0. 4 megabytes) is approximately 160 times smaller than the high-fidelity polyhedron model. The model’s dual capability in gravity field forward modeling and density inversion can effectively support trajectory planning, autonomous navigation, and scientific analysis for missions targeting asteroids or comets.

AAAI Conference 2026 Conference Paper

TARA: Token-Aware LoRA for Composable Personalization in Diffusion Models

• Yuqi Peng
• Lingtao Zheng
• Yufeng Yang
• Yi Huang
• Mingfu Yan
• Jianzhuang Liu
• Shifeng Chen

Personalized text-to-image generation aims to synthesize novel images of a specific subject or style using only a few reference images. Recent methods based on Low-Rank Adaptation (LoRA) enable efficient single-concept customization by injecting lightweight, concept-specific adapters into pre-trained diffusion models. However, combining multiple LoRA modules for multi-concept generation often leads to identity missing and visual feature leakage. In this work, we identify two key issues behind these failures: (1) token-wise interference among different LoRA modules, and (2) spatial misalignment between the attention map of a rare token and its corresponding concept-specific region. To address these issues, we propose Token-Aware LoRA (TARA), which introduces a token mask to explicitly constrain each module to focus on its associated rare token to avoid interference, and a training objective that encourages the spatial attention of a rare token to align with its concept region. Our method enables training-free multi-concept composition by directly injecting multiple independently trained TARA modules at inference time. Experimental results demonstrate that TARA enables efficient multi-concept inference and effectively preserving the visual identity of each concept by avoiding mutual interference between LoRA modules.

TMLR Journal 2025 Journal Article

Activate and Adapt: A Two-Stage Framework for Open-Set Model Adaptation

• Xiasi Wang
• Jiaqi Lin
• Chaoqi Chen
• Luyao Tang
• Yi Huang
• Chengsen Wang
• Lei YE
• Yuan Yao

The ability of generalizing to new environments is critical for deep neural networks. Most existing works presume that the training and test data share an identical label set, overlooking the potential presence of new classes in test data. In this paper, we tackle a practical and challenging problem: Open-Set Model Adaptation (OSMA). OSMA aims to train a model on the source domain, which contains only known class data, and then adapt the trained model to the distribution-shifted target domain to classify known class data while identifying new class data. In this context, we face two challenges: (1) enabling the model to recognize new classes using only the known class data from the source domain during training, and (2) adapting the source-trained model to the target domain that contains new class data. To address these challenges, we propose a novel and universal two-stage framework named Activate and Adapt (ADA). In the training stage, we extract potential new class information hidden within the rich semantics of the source domain data to enable the model to identify new class data. Additionally, to retain source domain information while preserving data privacy, we condense the source domain data into a small dataset, facilitating the subsequent adaptation phase. In the test stage, we adaptively adjust the source-trained model to the target domain with new classes by infusing the style of target data into the condensed dataset, and decoupling domain alignment for known and new classes. Experiments across three standard benchmarks demonstrate that ADA surpasses previous methods in both online and offline settings.

IROS Conference 2025 Conference Paper

Active Training Data Selection for Gaussian Process-based Robot Dynamics Learning and Control

• Feng Han
• Yi Huang
• Jingang Yi

Model-based robot control requires an accurate dynamics model and a machine learning-based method can extract robot dynamics from collected motion data by simulation and experiment. A Gaussian process (GP) has been used as one of the learning methods to obtain robot dynamics. To avoid large training datasets for learning robot dynamics, we propose an active training data selection strategy. The data sampling criteria are to minimize the probability density difference between the actual model and the GP-based estimate. Using such a criterion, the active training data strategy identifies where to sample the next data point for model training. We demonstrate the proposed active learning strategy with a 3-link robot arm in both fully actuated and underactuated modes. With the selected dataset containing 150 data points, the integrated probability density error compared with the entire dataset (over 30, 000 data points) is less than 0. 3. The experimental results confirm that the GP-based control performance is greater than that under the model-based control.

ICRA Conference 2025 Conference Paper

Efficient 7-DoF Grasp for Target-Driven Object in Dense Cluttered Scenes

• Tianjiao Lei
• Yizhuo Sun
• Yi Huang
• Jiangshuai Huang
• Tao Jiang

Achieving a real-time precise grasp of a specified target object in densely cluttered environments is an essential capability for autonomous robot operation. Recently, considerable investigations on planar and spatial grasp have been carried out, and significant results have been obtained. However, these point cloud-based grasp prediction methods often fail to ensure that the generated grasp configurations meet the precise requirements of the task. Additionally, some of the existing grasp pipelines are too time-consuming to meet the demand for real-time robot response. In more challenging cluttered scenes, the quality of pose and gripper jaw opening estimation in highdimensional space requires further improvement. Therefore, this paper introduces a data- and model-independent and efficient method to generate 7-DoF grasp configurations for arbitrary target objects from single-view point cloud data in dense cluttered scenes. In addition, this paper proposes a grasp framework that generates the grasp configuration for the target object while reducing the time consumed during the grasp process, to enable robots to efficiently grasp target objects for designated tasks. The grasp pipeline focuses on guided regions via target detection and rapidly adjusts grasp configurations through multi-region point cloud distribution perception. Extensive real-world robot experiments have demonstrated the effectiveness of the proposed method in grasping target objects in cluttered scenes, achieving higher success rates and reduced runtime compared to baseline methods. The realized code and video are available at https://github.com/L-tj/7DGCG.

NeurIPS Conference 2025 Conference Paper

K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling

• Yongrui Chen
• Yi Huang
• Yunchang Liu
• Shenyu Zhang
• Junhao He
• Tongtong Wu
• Guilin Qi
• Tianxing Wu

Continual Structured Knowledge Reasoning (CSKR) focuses on training models to handle sequential tasks, where each task involves translating natural language questions into structured queries grounded in structured knowledge. Existing general continual learning approaches face significant challenges when applied to this task, including poor generalization to heterogeneous structured knowledge and inefficient reasoning due to parameter growth as tasks increase. To address these limitations, we propose a novel CSKR framework, \textsc{K-DeCore}, which operates with a fixed number of tunable parameters. Unlike prior methods, \textsc{K-DeCore} introduces a knowledge decoupling mechanism that disentangles the reasoning process into task-specific and task-agnostic stages, effectively bridging the gaps across diverse tasks. Building on this foundation, \textsc{K-DeCore} integrates a dual-perspective memory consolidation mechanism for distinct stages and introduces a structure-guided pseudo-data synthesis strategy to further enhance the model's generalization capabilities. Extensive experiments on four benchmark datasets demonstrate the superiority of \textsc{K-DeCore} over existing continual learning methods across multiple metrics, leveraging various backbone large language models.

IROS Conference 2025 Conference Paper

PACR: Point-Axis Constraint Reasoning for Enhanced Robotic Manipulation with Dexterity and Compliance

• Haowen Xiong
• Yao Mu 0001
• Zhuang Liu
• Yusi Fan
• Yi Huang
• Jianxing Liu

Developing robotic systems for unstructured and contact-rich environments presents significant challenges, necessitating advanced dexterous motion planning, compliant interaction control, and spatio-temporal coordination. To address these, we introduce PACR (Point-Axis Constraint Reasoning), an unified framework that encodes robot trajectories and impedance profiles via constraint functions parameterized by point-axis primitives, extracted from multi-view RGB-D camera observations. This enables joint optimization of motion and impedance within a shared mathematical framework. For enhanced robustness, we implement a dual-agent Vision-Language Model (VLM) system: a Generator employs Chain-of-Thought reasoning to formulate constraints, while an adversarial Critic validates them, significantly mitigating hallucination risks. Integrated with the dual-agent system, the framework also features an error backtracking mechanism, enabling dynamic adaptation by learning from failures. Extensive experiments across diverse manipulation tasks reveal that PACR achieves a 61% success rate (compared to 37% for baseline methods) and reduces the average contact forces, demonstrating broad applicability through zero-shot generalization without task-specific training.

JBHI Journal 2025 Journal Article

Parallel Multi-Path Network for Ocular Disease Detection Inspired by Visual Cognition Mechanism

• Tao Deng
• Yi Huang
• Chengfan Yang

Various ocular diseases such as cataracts, glaucoma, and diabetic retinopathy have become several major factors causing non-congenital visual impairment, which seriously threatens people's vision health. The shortage of ophthalmic medical resources has brought huge obstacles to large-scale ocular disease screening. Therefore, it is necessary to use computer-aided diagnosis (CAD) technology to achieve large-scale screening and diagnosis of ocular diseases. In this work, inspired by the human visual cognition mechanism, we propose a parallel multi-path network for multiple ocular diseases detection, called PMP-OD, which integrates the detection of multiple common ocular diseases, including cataracts, glaucoma, diabetic retinopathy, and pathological myopia. The bottom-up features of the fundus image are extracted by a common convolutional module, the Low-level Feature Extraction module, which simulates the non-selective pathway. Simultaneously, the top-down vessel and other lesion features are extracted by the High-level Feature Extraction module that simulates the selective pathway. The retinal vessel and lesion features can be regarded as task-driven high-level semantic information in the physician's disease diagnosis process. Then, the features are fused by a feature fusion module based on the attention mechanism. Finally, the disease classifier gives prediction results according to the integrated multi-features. The experimental results indicate that our PMP-OD model outperforms other state-of-the-art (SOTA) models on an ocular disease dataset reconstructed from ODIR-5K, APTOS-2019, ORIGA-light, and Kaggle.

NeurIPS Conference 2025 Conference Paper

Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving

• Yi Huang
• Zhan Qu
• Lihui Jiang
• Bingbing Liu
• Hongbo Zhang

End-to-end autonomous driving systems, predominantly trained through imitation learning, have demonstrated considerable effectiveness in leveraging large-scale expert driving data. Despite their success in open-loop evaluations, these systems often exhibit significant performance degradation in closed-loop scenarios due to causal confusion. This confusion is fundamentally exacerbated by the overreliance of the imitation learning paradigm on expert trajectories, which often contain unattributable noise and interfere with the modeling of causal relationships between environmental contexts and appropriate driving actions. To address this fundamental limitation, we propose Perception-Guided Self-Supervision (PGS)—a simple yet effective training paradigm that leverages perception outputs as the primary supervisory signals, explicitly modeling causal relationships in decision-making. The proposed framework aligns both the inputs and outputs of the decision-making module with perception results—such as lane centerlines and the predicted motions of surrounding agents—by introducing positive and negative self-supervision for the ego trajectory. This alignment is specifically designed to mitigate causal confusion arising from the inherent noise in expert trajectories. Equipped with perception-driven supervision, our method—built on a standard end-to-end architecture—achieves a Driving Score of 78. 08 and a mean success rate of 48. 64\% on the challenging closed-loop Bench2Drive benchmark, significantly outperforming existing state-of-the-art methods, including those employing more complex network architectures and inference pipelines. These results underscore the effectiveness and robustness of the proposed PGS framework, and point to a promising direction for addressing causal confusion and enhancing real-world generalization in autonomous driving.

ECAI Conference 2024 Conference Paper

CSAdv: Class-Specific Adversarial Patches for DETR-Style Object Detection

• Yue Xu
• Chuanming Wang
• Xiaolong Zheng 0002
• Yi Huang
• Peilun Du
• Zeyuan Zhou
• Liang Liu 0001
• Huadong Ma

Remarkable advancements have been made in the field of object detection, and given its widespread application, it is of paramount importance to investigate the robustness of detection models. However, previous methods have primarily focused on models based on Convolutional Neural Networks (CNNs), seriously neglecting the Transformer-based models that develop rapidly but exhibit obvious differences in terms of information processing. Therefore, this paper aims to address this gap by exploring potential attacks arising from the self-attention mechanism inhered in Transformer. Specifically, we propose a novel adversarial attack scenario targeting Transformer-based object detection models, where only objects of specific class fail to be detected, while irrelevant objects remain undisturbed. Therefore, human perception is hard to find errors even with the detector fail. To achieve this goal, we introduce an adversarial patch generation method, termed Class-Specific Adversarial (CSAdv) patches, which simultaneously leverages class probability to attack specific objects and utilizes the output from Transformer decoder structures, Query Output, to protect irrelevant objects. Due to the long-range interactions of Transformer, the adversarial patch does not need to directly cover or closely surround the specific objects. Instead, it achieves remote targeted attacks simply by being placed in the corner of image, which greatly enhances the concealment of patches. Extensive experiments are conducted on various benchmark datasets and Transformer-based baselines, and the experimental results show that CSAdv can effectively mask certain class while keeping other classes as unaffected as far as possible.

EAAI Journal 2024 Journal Article

Global probability distribution structure-sparsity filter pruning for edge fault diagnosis in resource constrained wireless sensor networks

• Chunhua Zhao
• Baoping Tang
• Lei Deng
• Yi Huang
• Hao Tan

In this paper, a global probability distribution structure-sparsity filter pruning is proposed to address the problem of difficult deployment of diagnostic models in resource constrained wireless sensor networks (WSNs) for edge fault diagnosis. Firstly, local and global weight distributions are analyzed. A global probability distribution weight sparsity method is proposed to obtain the global sparse boundary and the important features of the model. Secondly, according to the distribution of weight amplitude, the problem of uneven weight distribution is disclosed. A computational acceleration sensing method is proposed to reduce the high computational cost caused by small weight amplitude with low importance estimation. Moreover, a novel layer filter clustering pruning scheme is proposed. The intra-layer filters are classified and redundant filters are removed by using the clustering idea according to the predetermined pruning rate. Thus, the structure-sparsity filter pruning is realized. Compared with other advanced filter pruning methods, the proposed method analyzes the global and local model weight distribution and the influence of weight importance on the computational complexity of the model. The proposed method then performs filter pruning on the importance of overall filters for each network layer rather than individual filters. The accuracy of the proposed method on experimental dataset for pruned ResNet8 model under pruning rate at 0. 95 is 99. 12% with 3. 668K parameters and 3. 636MFLOPs. The experimental results elucidate that the proposed method is more suitable for deployment in resource-constrained WSNs for fault diagnosis of rotating machinery. This provides a potential solution for practical engineering applications.

IROS Conference 2024 Conference Paper

Using Hip Assisted Running Exoskeleton with Impact Isolation Mechanism to Improve Energy Efficiency

• Ziqi Wang
• Junchen Liu
• Hongwu Li
• Qinghua Zhang
• Xianglong Li
• Yi Huang
• Haotian Ju
• Tianjiao Zheng

Research has indicated that exoskeletons can assist human movement, but due to the influence of additional weight and challenges in control strategy design, only a few exoskeletons effectively reduce the wearers’ metabolic costs during running. This paper proposes an innovative and efficient hip-assisted running exoskeleton (HARE) designed to facilitate the flexion and extension movements of the joint along the sagittal plane. In the field of structural engineering, we propose implementing an active-passive combination constant force suspension system, hereinafter referred to as CFS, to effectively mitigate the impact of inertial forces during running. The decoupled transmission mechanism allows the CFS and assist mechanisms to operate independently, ensuring the tension of the cables. The flexible structural design can reduce the locomotion limitation on human bodies and reduce the additional energy burden on the body. In control strategy designing, the joint torque-generating strategy provides personalized assistance strategies for wearers to actively optimize the control parameters. Meanwhile, the safety control strategy based on abnormal gait recognition can ensure human safety. Experiments have shown that compared to not wearing exoskeletons, this device can reduce the energy consumption of the human body by 5. 33 % at a speed of 9 km/h. This demonstrates its potential in human motion assistance processes.

AAAI Conference 2023 Conference Paper

Multi-Action Dialog Policy Learning from Logged User Feedback

• Shuo Zhang
• Junzhou Zhao
• Pinghui Wang
• Tianxiang Wang
• Zi Liang
• Jing Tao
• Yi Huang
• Junlan Feng

Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve MADPL with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid learning objective of SSL and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch improves MADPL over the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.

ICRA Conference 2023 Conference Paper

Unsupervised Learning of Depth and Pose Based on Monocular Camera and Inertial Measurement Unit (IMU)

• Yanbo Wang
• Hanwen Yang
• Jianwei Cai
• Guangming Wang 0001
• Jingchuan Wang
• Yi Huang

The main content of the research in this paper is the estimation of depth and pose based on monocular vision and Inertial Measurement Unit (IMU). The usual depth estimation network and pose estimation network require depth ground truth or pose ground truth as a supervised signal for training, while the depth ground truth and pose ground truth are hard to obtain, and monocular vision based depth estimation cannot predict absolute depth. In this paper, with the help of IMU, which is inexpensive and widely used, we can obtain angular velocity and acceleration information. Two new supervision signals are proposed and the calculation expressions are given. Among them, the model trained with acceleration constraint shows a good ability to estimate the absolute depth during the test. It can be considered that the model can estimate the absolute depth. We also derive the method of estimating the scale factor during the test from the acceleration constraint, and also achieve good results as the acceleration constraint does. In addition, this paper also studies the method of using IMU information as pose network input and as selecting conditions. Moreover, it analyzes and discusses the experimental results. At the same time, we also evaluate the effect of the pose estimation of the relevant models. This article starts by reviewing the achievements and deficiencies of the work in this field, combines the use of IMU, puts forward three new methods such as a new loss function, and conducts a test analysis and discussion of relevant indicators on the KITTI data set.

IJCAI Conference 2022 Conference Paper

AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation

• Xu Cao
• Xiaoye Li
• Liya Ma
• Yi Huang
• Xuan Feng
• Zening Chen
• Hongwu Zeng
• Jianguo Cao

Movement and pose assessment of newborns lets experienced pediatricians predict neurodevelopmental disorders, allowing early intervention for related diseases. However, most of the newest AI approaches for human pose estimation methods focus on adults, lacking publicly benchmark for infant pose estimation. In this paper, we fill this gap by proposing infant pose dataset and Deep Aggregation Vision Transformer for human pose estimation, which introduces a fast trained full transformer framework without using convolution operations to extract features in the early stages. It generalizes Transformer + MLP to high-resolution deep layer aggregation within feature maps, thus enabling information fusion between different vision levels. We pre-train AggPose on COCO pose dataset and apply it on our newly released large-scale infant pose estimation dataset. The results show that AggPose could effectively learn the multi-scale features among different resolutions and significantly improve the performance of infant pose estimation. We show that AggPose outperforms hybrid model HRFormer and TokenPose in the infant pose estimation dataset. Moreover, our AggPose outperforms HRFormer by 0. 8 AP on COCO val pose estimation on average. Our code is available at github. com/SZAR-LAB/AggPose.

JBHI Journal 2022 Journal Article

AwCPM-Net: A Collaborative Constraint GAN for 3D Coronary Artery Reconstruction in Intravascular Ultrasound Sequences

• Menghua Xia
• Hongbo Yang
• Yi Huang
• Yanan Qu
• Yi Guo
• Guohui Zhou
• Feng Zhang
• Yuanyuan Wang

3D coronary artery reconstruction (3D-CAR) in intravascular ultrasound (IVUS) sequences allows quantitative analyses of vessel properties. Existing methods treat two main tasks of the 3D-CAR separately, including the cardiac phase retrieval (CPR) and the membrane border extraction (MBE). They ignore the CPR-MBE connection that could achieve mutual promotions to both tasks. In this paper, we pioneer to achieve one-step 3D-CAR via a collaborative constraint generative adversarial network (GAN) named the AwCPM-Net. The AwCPM-Net consists of a dual-task collaborative generator and a dual-task constraint discriminator. The generator combines a self-supervised CPR branch with a semi-supervised MBE branch via a warming-up connection. The discriminator promotes dual-branch predictions simultaneously. The CPR branch requires no annotations and outputs inter-frame deformation fields used for identifying cardiac phases. Deformation fields are additionally constrained by the MBE branch and the discriminator. The MBE branch predicts membrane boundaries for each frame. Two aspects assist the semi-supervised segmentation: annotation augmentation by deformation fields of the CPR branch; information exploitation on unlabeled images enabled by GAN design. Trained and tested on an IVUS dataset acquired from atherosclerosis patients, the AwCPM-Net is effective in both CPR and MBE tasks, superior to state-of-the-art IVUS CPR or MBE methods. Hence, the AwCPM-Net reconstructs reliable 3D artery anatomy in the IVUS modality.

AAAI Conference 2022 Conference Paper

Cross-Modal Federated Human Activity Recognition via Modality-Agnostic and Modality-Specific Representation Learning

• Xiaoshan Yang
• Baochen Xiong
• Yi Huang
• Changsheng Xu

In this paper, we propose a new task of cross-modal federated human activity recognition (CMF-HAR), which is conducive to promote the large-scale use of the HAR model on more local devices. To address the new task, we propose a feature-disentangled activity recognition network (FDARN), which has five important modules of altruistic encoder, egocentric encoder, shared activity classifier, private activity classifier and modality discriminator. The altruistic encoder aims to collaboratively embed local instances on different clients into a modality-agnostic feature subspace. The egocentric encoder aims to produce modality-specific features that cannot be shared across clients with different modalities. The modality discriminator is used to adversarially guide the parameter learning of the altruistic and egocentric encoders. Through decentralized optimization with a spherical modality discriminative loss, our model can not only generalize well across different clients by leveraging the modality-agnostic features but also capture the modality-specific discriminative characteristics of each client. Extensive experiment results on four datasets demonstrate the effectiveness of our method.

IJCAI Conference 2022 Conference Paper

Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation

• Pei Ke
• Haozhe Ji
• Zhenyu Yang
• Yi Huang
• Junlan Feng
• Xiaoyan Zhu
• Minlie Huang

Despite the success of text-to-text pre-trained models in various natural language generation (NLG) tasks, the generation performance is largely restricted by the number of labeled data in downstream tasks, particularly in data-to-text generation tasks. Existing works mostly utilize abundant unlabeled structured data to conduct unsupervised pre-training for task adaption, which fail to model the complex relationship between source structured data and target texts. Thus, we introduce self-training as a better few-shot learner than task-adaptive pre-training, which explicitly captures this relationship via pseudo-labeled data generated by the pre-trained model. To alleviate the side-effect of low-quality pseudo-labeled data during self-training, we propose a novel method called Curriculum-Based Self-Training (CBST) to effectively leverage unlabeled data in a rearranged order determined by the difficulty of text generation. Experimental results show that our method can outperform fine-tuning and task-adaptive pre-training methods, and achieve state-of-the-art performance in the few-shot setting of data-to-text generation.

IJCAI Conference 2022 Conference Paper

“Think Before You Speak”: Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs

• Shuo Zhang
• Junzhou Zhao
• Pinghui Wang
• Yu Li
• Yi Huang
• Junlan Feng

Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing MADP models usually imitate action combinations from the labeled multi-action dialog samples. Due to data limitations, they generalize poorly toward unseen dialog flows. While interactive learning and reinforcement learning algorithms can be applied to incorporate external data sources of real users and user simulators, they take significant manual effort to build and suffer from instability. To address these issues, we propose Planning Enhanced Dialog Policy (PEDP), a novel multi-task learning framework that learns single-action dialog dynamics to enhance multi-action prediction. Our PEDP method employs model-based planning for conceiving what to express before deciding the current response through simulating single-action dialogs. Experimental results on the MultiWOZ dataset demonstrate that our fully supervised learning-based method achieves a solid task success rate of 90. 6%, improving 3% compared to the state-of-the-art methods. The source code and the appendix of this paper can be obtained from https: //github. com/ShuoZhangXJTU/PEDP.

AAAI Conference 2021 Conference Paper

Learning to Check Contract Inconsistencies

• Shuo Zhang
• Junzhou Zhao
• Pinghui Wang
• Nuo Xu
• Yang Yang
• Yiting Liu
• Yi Huang
• Junlan Feng

Contract consistency is important in ensuring the legal validity of the contract. In many scenarios, a contract is written by filling the blanks in a precompiled form. Due to carelessness, two blanks that should be filled with the same (or different) content may be incorrectly filled with different (or same) content. This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract. Traditional methods to address this issue mainly rely on manual contract review, which is labor-intensive and costly. In this work, we formulate a novel Contract Inconsistency Checking (CIC) problem, and design an end-to-end framework, called Pair-wise Blank Resolution (PBR), to solve the CIC problem with high accuracy. Our PBR model contains a novel BlankCoder to address the challenge of modeling meaningless blanks. BlankCoder adopts a two-stage attention mechanism that adequately associates a meaningless blank with its relevant descriptions while avoiding the incorporation of irrelevant context words. Experiments conducted on real-world datasets show the promising performance of our method with a balanced accuracy of 94. 05% and an F1 score of 90. 90% in the CIC problem.

YNIMG Journal 2020 Journal Article

Goal-oriented and habitual decisions: Neural signatures of model-based and model-free learning

• Yi Huang
• Zachary A. Yaple
• Rongjun Yu

Human decision-making is mainly driven by two fundamental learning processes: a slow, deliberative, goal-directed model-based process that maps out the potential outcomes of all options and a rapid habitual model-free process that enables reflexive repetition of previously successful choices. Although many model-informed neuroimaging studies have examined the neural correlates of model-based and model-free learning, the concordant activity among these two processes remains unclear. We used quantitative meta-analyses of functional magnetic resonance imaging experiments to identify the concordant activity pertaining to model-based and model-free learning over a range of reward-related paradigms. We found that: 1) both processes yielded concordant ventral striatum activity, 2) model-based learning activated the medial prefrontal cortex and orbital frontal cortex, and 3) model-free learning specifically activated the left globus pallidus and right caudate head. Our findings suggest that model-free and model-based decision making engage overlapping yet distinct neural regions. These stereotaxic maps improve our understanding of how deliberative goal-directed and reflexive habitual learning are implemented in the brain.

YNIMG Journal 2019 Journal Article

Common and distinct neural substrates of the money illusion in win and loss domains

• Yi Huang
• Rongjun Yu

People often evaluate money based on its face value and overlook its real purchasing power, a phenomenon known as the money illusion. In the present study, using functional magnetic resonance imaging (fMRI) combined with a gambling task, we examined the neural signatures of the money illusion in both win and loss domains. Behavioral results showed that self-reported satisfaction with outcomes was modulated by the face value but not the true value of money in both win and loss domains. At the neural level, activity in the posterior insula was associated with the true value of money in the win domain, but not in the loss domain. Importantly, we found that the ventral striatum, ventromedial prefrontal cortex (vmPFC) and amygdala encoded the money illusion in both domains, indicating a domain-general rather than domain-specific neural signature. Moreover, participants with a larger degree of money illusion at the behavioral level showed stronger functional connectivity between the ventral striatum and ventral anterior cingulate cortex (vACC) in the win domain, but stronger functional connectivity between the ventral striatum and amygdala in the loss domain. Our findings highlight the overlapping and distinct neural substrates underlying the money illusion in the context of wins and losses.

AAAI Conference 2019 Conference Paper

Wasserstein Soft Label Propagation on Hypergraphs: Algorithm and Generalization Error Bounds

• Tingran Gao
• Shahab Asoodeh
• Yi Huang
• James Evans

Inspired by recent interests of developing machine learning and data mining algorithms on hypergraphs, we investigate in this paper the semi-supervised learning algorithm of propagating ”soft labels” (e. g. probability distributions, class membership scores) over hypergraphs, by means of optimal transportation. Borrowing insights from Wasserstein propagation on graphs [Solomon et al. 2014], we re-formulate the label propagation procedure as a message-passing algorithm, which renders itself naturally to a generalization applicable to hypergraphs through Wasserstein barycenters. Furthermore, in a PAC learning framework, we provide generalization error bounds for propagating one-dimensional distributions on graphs and hypergraphs using 2-Wasserstein distance, by establishing the algorithmic stability of the proposed semisupervised learning algorithm. These theoretical results also shed new lights upon deeper understandings of the Wasserstein propagation on graphs.

YNIMG Journal 2017 Journal Article

Sex-linked association between cortical scene selectivity and navigational ability

• Xiang-Zhen Kong
• Yi Huang
• Xin Hao
• Siyuan Hu
• Jia Liu

Spatial navigation is a crucial ability for living. Previous studies have shown that males are better at navigation than females, but little is known about the neural basis underlying the sex differences. In this study, we investigated whether cortical scene processing in three well-established scene-selective regions was sexually different, by examining sex differences in scene selectivity and its behavioral relevance to navigation. To do this, we used functional magnetic resonance imaging (fMRI) to scan the parahippocampal place area (PPA), retrosplenial complex (RSC), and occipital place area (OPA) in a large cohort of healthy young adults viewing navigationally relevant scenes (N = 202), and correlated their neural selectivity to scenes with their self-reported navigational ability. Behaviorally, we replicated the previous finding that males were better at navigation than females. Neurally, we found that the scene selectivity in the bilateral PPA, not in the RSC or OPA, was significantly higher in males than females. Such differences could not be explained by confounding factors including brain size and fMRI data quality. Importantly, males, not females, with stronger scene selectivity in the left PPA possessed better navigational ability. This brain-behavior association could not be accounted for by non-navigational abilities (i. e. , intelligence and mental rotation ability). Overall, our study provides novel empirical evidence demonstrating sex differences in the brain activity, inviting further studies on sex differences in the neural network for spatial navigation.

AAMAS Conference 2016 Conference Paper

Recovering Social Networks by Observing Votes

• Benjamin Fish
• Yi Huang
• Lev Reyzin

IJCAI Conference 2015 Conference Paper

Training-Time Optimization of a Budgeted Booster

• Yi Huang
• Brian Powers
• Lev Reyzin

We consider the problem of feature-efficient prediction – a setting where features have costs and the learner is limited by a budget constraint on the total cost of the features it can examine in test time. We focus on solving this problem with boosting by optimizing the choice of base learners in the training phase and stopping the boosting process when the learner’s budget runs out. We experimentally show that our method improves upon the boosting approach AdaBoostRS [Reyzin, 2011] and in many cases also outperforms the recent algorithm SpeedBoost [Grubb and Bagnell, 2012]. We provide a theoretical justication for our optimization method via the margin bound. We also experimentally show that our method outperforms pruned decision trees, a natural budgeted classifier.

IS Journal 2011 Journal Article

Deductive and Inductive Stream Reasoning for Semantic Social Media Analytics

• Davide Barbieri
• Daniele Braga
• Stefano Ceri
• Emanuele Della Valle
• Yi Huang
• Volker Tresp
• Achim Rettinger
• Hendrik Wermser

IS Journal 2010 Journal Article

Deductive and Inductive Stream Reasoning for Semantic Social Media Analytics

• Davide Barbieri
• Daniele Braga
• Stefano Ceri
• Emanuele Della Valle
• Yi Huang
• Volker Tresp
• Achim Rettinger
• Hendrik Wermser

A combined approach of deductive and inductive reasoning can leverage the clear separation between the evolving (streaming) and static parts of online knowledge at conceptual and technological levels. What are the hottest topics discussed on Twitter? Which topics have my close friends discussed in the last hour? Which movie is my friend most likely to watch next? Which Tuscan red wine should I recommend? With many popular social networks publishing microblogs and feeds, the information required to answer these queries is becoming available on the Web.