Author name cluster

Yong Cheng

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.

21 papers

2 author rows

EAAI Journal 2026 Journal Article

A deep learning-based imaging classification framework for interstitial lung disease

Hongyi Wang
Anqi Liu
Xiaoyan Yang
Yifei Ni
Jianping Wang
Jie Du
Yuhui Qiang
Bingbing Xie

Rationale Interstitial lung diseases (ILD) are a diverse group of conditions, often diagnosed using high-resolution chest computed tomography (HRCT), which is susceptible to subjective biases in interpretation. Objectives This study aims to develop and validate SPAIDNet (Spatial Pattern Analysis for ILD Diagnosis using a residual neural Network), a deep learning (DL) model for the automated classification of ILD, to reduce subjective biases and improve diagnostic consistency. Methods The study included 2901 ILD patients who underwent 5213 HRCT scans across multiple centers between July 2017 and June 2023. SPAIDNet, built upon the pre-trained residual neural network with 18 layers, utilizes multi-instance learning in three centers in China. Measurements and main results The model demonstrated exceptional performance, achieving macro-average area under the receiver operating characteristic curve (AUC) of over 0. 999 in internal validation, 0. 905 in external cohort I, and 0. 870 in external cohort II for multiclass classification. SPAIDNet outperformed both a junior radiologist (AUC: 0. 737) and a senior radiologist (AUC: 0. 763). Furthermore, DL-assisted the two radiologists saw significant improvements in diagnostic accuracy, with AUCs rising to 0. 817 and 0. 787, respectively. Conclusions These results underscore SPAIDNet's potential to offer high accuracy, robustness, and generalizability in ILD diagnosis, providing a valuable tool to mitigate the subjectivity inherent in HRCT image interpretation.

Details DOI

EAAI Journal 2026 Journal Article

Multi-Agent Consultation and Uncertainty-guided Voting for text-to-image person retrieval

Mingcheng Ni
Zijie Wang
Aichun Zhu
Jingyi Xue
Guan-Nan Dong
Yong Cheng

Text-to-image person retrieval aims to search for the corresponding pedestrian images according to a natural language query, with applications in intelligent surveillance systems and public security monitoring, which remains a challenging task due to the Cross-modal Information Heterogeneity and Asymmetry (CIHA) problem. In this paper, a Multi-Agent Consultation and Uncertainty-guided Voting (MACUV) framework is proposed. Instead of blindly predicting what clues are expected for feature matching, MACUV manages to enable a multi-agent consultation among proposed agents during the feature extraction stage. It extracts a set of comprehensive and diverse features, which are afterward aligned adequately under the guidance of uncertainty. For the visual modality, a Multi-agent Saliency Consultation (MSC) module is designed to give MACUV a more complete perspective. For the textual modality, a Semantic Relation-guided Consultation (SRC) module is proposed to enforce the semantically related words to have consistent predictions for cross-modal correspondences regardless of the word distance. In addition, to achieve superior cross-modal feature alignments and fully excavate the multiple views of input data, an Uncertainty-guided Multi-agent Voting (UMV) mechanism is introduced during the feature matching stage. Extensive experimental analysis on the three datasets demonstrates that MACUV significantly outperforms existing methods and achieves the state-of-the-art performance among vanilla Residual Network 50 (ResNet-50) based method in the supervised, weakly supervised and cross-domain text-to-image person retrieval settings.

Details DOI

YNIMG Journal 2025 Journal Article

Brain development during the lifespan of cynomolgus monkeys

Zhiqiang Tan
Binbin Nie
Huanhua Wu
Bang Li
Jingjie Shang
Tianhao Zhang
Zeyu Xiao
Chenchen Dong

F]FDG PET-MRI data from 228 healthy cynomolgus monkeys spanning the age range of 0.5-29.5 years to construct an age-specific multimodal image brain template toolset tailored to cynomolgus monkeys. Their brain volume and glucose metabolism were quantitatively analyzed by utilizing an individualized spatial segmentation algorithm. Our findings encapsulated the growth and development trends, sex differences, and asymmetrical variations in brain volume and glucose metabolism in cynomolgus monkeys, and analyzed the correlation between the brain volume and glucose metabolism. This endeavor enhances our capacity to leverage the cynomolgus monkey model in neuroscience research by providing a valuable resource for researchers. The age-specific brain template toolset and associated data offer a robust foundation for future investigations, facilitating a nuanced understanding of brain development in this primate species and, consequently, informing and advancing neuroscience research employing cynomolgus monkeys.

Details DOI

EAAI Journal 2025 Journal Article

Enhancing primitive segmentation through transformer-based cross-task interaction

Tao Wang
Weibin Xi
Yong Cheng
Jun Zhang
Ruochen Yin
Yang Yang

Point cloud primitive segmentation, which divides a point cloud into surface patches of distinct primitive types, is fundamental to three-dimensional objects processing and recognition. However, existing deep learning methods for primitive segmentation lack the capability to capture global spatial relationships across tasks, limiting the exploitation of inter-task consistency. To address this issue, we propose a novel transformer-based cross-task interaction primitive segmentation (TCIPS) method that models global spatial relationships between all tasks, leading to improved segmentation accuracy. Specifically, TCIPS leverages center offset and regional purity prediction as auxiliary tasks, providing supplementary supervision to facilitate the learning of spatial and boundary information, thereby promoting richer and more generalized feature learning. Furthermore, we design a cross-task transformer fusion module that fuses and refines features from task-specific decoders using two types of transformer blocks: the feature fusion block and the task query block. Extensive experiments and comparisons with state-of-the-art methods demonstrate the effectiveness and robustness of our approach. Codes and models are publicly available at https: //github. com/MingFengHill/TCIPS.

Details DOI

EAAI Journal 2025 Journal Article

Mastering autonomous assembly in fusion application with learning-by-doing: A peg-in-hole study

Ruochen Yin
Huapeng Wu
Ming Li
Yong Cheng
Yuntao Song
Hongtao Pan
Heikki Handroos

Robotic peg-in-hole assembly represents a critical area of investigation in robotic automation. Traditional approaches primarily rely on optical or force/torque (F/T) sensors, each with inherent limitations: restricted assembly accuracy or inefficient peg-hole alignment. Deep Reinforcement Learning (DRL) based methods have the potential to combine data from both types of sensors to achieve improved results. However, our application scenario is situated inside a fusion reactor, where the radiation environment and the abundance of smooth metal surfaces make commonly used three-dimensional (3D) sensors face operational challenges. To address this, we propose a novel DRL-based approach that, unlike conventional methods, integrates data from a two-dimensional (2D) camera and an F/T sensor. This approach trains the agent to perform peg-in-hole assembly tasks by mimicking human hand-eye coordination. It utilizes multi-input branch neural network to fuse multi-sensor data with significant differences and automatically adjusts the weights of multi-source data at different stages of assembly, thereby simultaneously meeting the requirements of fast alignment and high-precision assembly. Real-world experimental results demonstrate the effectiveness of this multi-sensor fusion approach, particularly in rigid peg-in-hole assembly tasks. It achieves rapid assembly with a peg-hole clearance of less than 0. 1 mm (smaller than the repeatable accuracy of the robotic arm we used) while maintaining a high success rate and avoiding risky behaviors. This study shows that high-precision peg-in-hole assembly operations can be successfully accomplished using only a 2D camera as the optical sensor. This advancement significantly contributes to the development of high-precision automated operations in challenging environments, such as radiation-exposed settings.

Details DOI

ICLR Conference 2024 Conference Paper

Language Model Beats Diffusion - Tokenizer is key to visual generation

Lijun Yu
José Lezama
Nitesh Bharadwaj Gundavarapu
Luca Versari
Kihyuk Sohn
David Minnen
Yong Cheng
Agrim Gupta

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce \modelname{}, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.

Details

ICML Conference 2024 Conference Paper

VideoPoet: A Large Language Model for Zero-Shot Video Generation

Dan Kondratyuk
Lijun Yu
Xiuye Gu
José Lezama
Jonathan Huang
Grant Schindler
Rachel Hornung
Vighnesh Birodkar

We present VideoPoet, a language model capable of synthesizing high-quality video from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs – including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model’s state-of-the-art capabilities in zero-shot video generation, specifically highlighting the ability to generate high-fidelity motions. Project page: http: //sites. research. google/videopoet/

Details

ICML Conference 2023 Conference Paper

Mu 2 SLAM: Multitask, Multilingual Speech and Language Models

Yong Cheng
Yu Zhang 0033
Melvin Johnson
Wolfgang Macherey
Ankur Bapna

We present Mu$^2$SLAM, a multilingual sequence-to-sequence model pre-trained jointly on unlabeled speech, unlabeled text and supervised data spanning Automatic Speech Recognition (ASR), Automatic Speech Translation (AST) and Machine Translation (MT), in over 100 languages. By leveraging a quantized representation of speech as a target, Mu$^2$SLAM trains the speech-text models with a sequence-to-sequence masked denoising objective similar to T5 on the decoder and a masked language modeling objective (MLM) on the encoder, for both unlabeled speech and text, while utilizing the supervised tasks to improve cross-lingual and cross-modal representation alignment within the model. On CoVoST AST, Mu$^2$SLAM establishes a new state-of-the-art for models trained on public datasets, improving on xx-en translation over the previous best by 1. 9 BLEU points and on en-xx translation by 1. 1 BLEU points. On Voxpopuli ASR, our model matches the performance of an mSLAM model fine-tuned with an RNN-T decoder, despite using a relatively weaker Transformer decoder. On text understanding tasks, our model improves by more than 6% over mSLAM on XNLI, getting closer to the performance of mT5 models of comparable capacity on XNLI and TydiQA, paving the way towards a single model for all speech and text understanding tasks.

Details

NeurIPS Conference 2023 Conference Paper

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

Lijun Yu
Yong Cheng
Zhiruo Wang
Vivek Kumar
Wolfgang Macherey
Yanping Huang
David Ross
Irfan Essa

In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs to perform both understanding and generation tasks involving non-linguistic modalities such as images or videos. SPAE converts between raw pixels and interpretable lexical tokens (or words) extracted from the LLM's vocabulary. The resulting tokens capture both the rich semantic meaning and the fine-grained details needed for visual reconstruction, effectively translating the visual content into a language comprehensible to the LLM, and empowering it to perform a wide array of multimodal tasks. Our approach is validated through in-context learning experiments with frozen PaLM 2 and GPT 3. 5 on a diverse set of image understanding and generation tasks. Our method marks the first successful attempt to enable a frozen LLM to generate image content while surpassing state-of-the-art performance in image understanding tasks, under the same setting, by over 25%.

PDF Details

ICML Conference 2022 Conference Paper

Examining Scaling and Transfer of Language Model Architectures for Machine Translation

Biao Zhang 0006
Behrooz Ghorbani
Ankur Bapna
Yong Cheng
Xavier Garcia
Jonathan Shen
Orhan Firat

Natural language understanding and generation models follow one of the two dominant architectural paradigms: language models (LMs) that process concatenated sequences in a single stack of layers, and encoder-decoder models (EncDec) that utilize separate layer stacks for input and output processing. In machine translation, EncDec has long been the favoured approach, but with few studies investigating the performance of LMs. In this work, we thoroughly examine the role of several architectural design choices on the performance of LMs on bilingual, (massively) multilingual and zero-shot translation tasks, under systematic variations of data conditions and model sizes. Our results show that: (i) Different LMs have different scaling properties, where architectural differences often have a significant impact on model performance at small scales, but the performance gap narrows as the number of parameters increases, (ii) Several design choices, including causal masking and language-modeling objectives for the source sequence, have detrimental effects on translation quality, and (iii) When paired with full-visible masking for source sequences, LMs could perform on par with EncDec on supervised bilingual and multilingual translation tasks, and improve greatly on zero-shot directions by facilitating the reduction of off-target translations.

Details

ICML Conference 2021 Conference Paper

Self-supervised and Supervised Joint Training for Resource-rich Machine Translation

Yong Cheng
Wei Wang
Lu Jiang 0004
Wolfgang Macherey

Self-supervised pre-training of text representations has been successfully applied to low-resource Neural Machine Translation (NMT). However, it usually fails to achieve notable gains on resource-rich NMT. In this paper, we propose a joint training approach, F2-XEnDec, to combine self-supervised and supervised learning to optimize NMT models. To exploit complementary self-supervised signals for supervised learning, NMT models are trained on examples that are interbred from monolingual and parallel sentences through a new process called crossover encoder-decoder. Experiments on two resource-rich translation benchmarks, WMT’14 English-German and WMT’14 English-French, demonstrate that our approach achieves substantial improvements over several strong baseline methods and obtains a new state of the art of 46. 19 BLEU on English-French when incorporating back translation. Results also show that our approach is capable of improving model robustness to input perturbations such as code-switching noise which frequently appears on the social media.

Details

IROS Conference 2018 Conference Paper

Development and Error Compensation of a Flexible Multi-Joint Manipulator Applied in Nuclear Fusion Environment

Shanshuang Shi
Yong Cheng
Hongtao Pan
Wenlong Zhao 0002
Huapeng Wu

Experimental Advanced Superconducting Tokamak (EAST) is the world's first fully superconducting tokamak fusion device with non-circular cross-section which was built in China The EAST articulated maintenance arm (EAMA) system is developed for real-time detection and rapid repair operations to damaged internal components during plasma discharges without breaking the EAST ultra-high vacuum (UHV) condition. To achieve the desired objectives, the EAMA system design should guarantee that the robot can stably run in the harsh environments of high temperature (80-120 °C) and high vacuum (~ 10 -5 Pa). Meanwhile, the errors caused by the deformation of long flexible robot arms should also be predicted and compensated in real-time to obtain high accuracy for maintenance operations. In this paper, the vacuum-available design scheme of the manipulator system was firstly introduced. Secondly, inverse kinematics and obstacle avoidance strategy of the highly redundant EAMA robot was built. Then, flexible errors were predicted utilizing a back-propagation neural network (BPNN) model which was established on the basis of real experimental data. Finally, an integrated control strategy for error prediction and compensation was developed.

Details

IJCAI Conference 2018 Conference Paper

Neural Machine Translation with Key-Value Memory-Augmented Attention

Fandong Meng
Zhaopeng Tu
Yong Cheng
Haiyang Wu
Junjie Zhai
Yuekui Yang
Di Wang

Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value memory-augmented attention model for NMT, called KVMEMATT. Specifically, we maintain a timely updated keymemory to keep track of attention history and a fixed value-memory to store the representation of source sentence throughout the whole translation process. Via nontrivial transformations and iterative interactions between the two memories, the decoder focuses on more appropriate source word(s) for predicting the next target word at each decoding step, therefore can improve the adequacy of translations. Experimental results on Chinese)English and WMT17 German, English translation tasks demonstrate the superiority of the proposed model.

PDF Details

IROS Conference 2018 Conference Paper

Progress and Prospects of EAST Remote Maintenance System

Hongtao Pan
Shanshuang Shi
Yong Cheng
Wenlong Zhao 0002

Fast inspection and light maintenance capability is already a clear demand to control the tokamak condition and improve the efficiency of the experimental campaigns. EAST remote maintenance system has been developed to implement inspection and grasping tasks during plasma. The paper presents design description of EAMA (EAST articulated maintenance arm) robot, the gripper and the CASK. The field commissioning was performed both in mockup and EAST tokamak to demonstrate the availability and functionalities of EAMA system. To be able to realize fully routine operation on EAST, improvement of EAMA control system was proposed with integration developed algorithm, such as the robot flexible model modeling, vision servo, motion planning, etc. Finally, thoughts for CFETR In-Vessel Inspection System (CIVIS) are given.

Details

IJCAI Conference 2017 Conference Paper

Joint Training for Pivot-based Neural Machine Translation

Yong Cheng
Qian Yang
Yang Liu
Maosong Sun
Wei Xu

While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. We propose three methods to connect the two models and enable them to interact with each other during training. Experiments on Europarl and WMT corpora show that joint training of source-to-pivot and pivot-to-target models leads to significant improvements over independent training across various languages.

PDF Details

IJCAI Conference 2017 Conference Paper

Maximum Expected Likelihood Estimation for Zero-resource Neural Machine Translation

Hao Zheng
Yong Cheng
Yang Liu

While neural machine translation (NMT) has made remarkable progress in translating a handful of high-resource language pairs recently, parallel corpora are not always available for many zero-resource language pairs. To deal with this problem, we propose an approach to zero-resource NMT via maximum expected likelihood estimation. The basic idea is to maximize the expectation with respect to a pivot-to-source translation model for the intended source-to-target model on a pivot-target parallel corpus. To approximate the expectation, we propose two methods to connect the pivot-to-source and source-to-target models. Experiments on two zero-resource language pairs show that the proposed approach yields substantial gains over baseline methods. We also observe that when trained jointly with the source-to-target model, the pivot-to-source translation model also obtains improvements over independent training.

PDF Details

AAAI Conference 2017 Conference Paper

Maximum Reconstruction Estimation for Generative Latent-Variable Models

Yong Cheng
Yang Liu
Wei Xu

Generative latent-variable models are important for natural language processing due to their capability of providing compact representations of data. As conventional maximum likelihood estimation (MLE) is prone to focus on explaining irrelevant but common correlations in data, we apply maximum reconstruction estimation (MRE) to learning generative latent-variable models alternatively, which aims to ﬁnd model parameters that maximize the probability of reconstructing the observed data. We develop tractable algorithms to directly learn hidden Markov models and IBM translation models using the MRE criterion, without the need to introduce a separate reconstruction model to facilitate efﬁcient inference. Experiments on unsupervised part-of-speech induction and unsupervised word alignment show that our approach enables generative latent-variable models to better discover intended correlations in data and outperforms maximum likelihood estimators signiﬁcantly.

PDF Details

ECAI Conference 2016 Conference Paper

A Novel Cross-Modal Topic Correlation Model for Cross-Media Retrieval

Yong Cheng
Fei Huang
Cheng Jin 0001
Yuejie Zhang
Tao Zhang 0022

A novel cross-modal topic correlation model CMTCM is developed in this paper to facilitate more effective cross-modal analysis and cross-media retrieval for large-scale multimodal document collections. It can be modeled as a cross-modal topic correlation model which explores the inter-related correlation distribution over the deep representations of multimodal documents. It integrates the deep multimodal document representation, relational topic correlation modeling, and cross-modal topic correlation learning, which aims to characterize the correlations between the heterogeneous topic distributions of inter-related visual images and semantic texts, and measure their association degree more precisely. Very positive results were obtained in our experiments using a large quantity of public data.

Details

IJCAI Conference 2016 Conference Paper

Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation

Yong Cheng
Shiqi Shen
Zhongjun He
Wei He
Hua Wu
Maosong Sun
Yang Liu

The attentional mechanism has proven to be effective in improving end-to-end neural machine translation. However, due to the intricate structural divergence between natural languages, unidirectional attention-based models might only capture partial aspects of attentional regularities. We propose agreement-based joint training for bidirectional attention-based end-to-end neural machine translation. Instead of training source-to-target and target-to-source translation models independently, our approach encourages the two complementary models to agree on word alignment matrices on the same training data. Experiments on Chinese-English and English-French translation tasks show that agreement-based joint training significantly improves both alignment and translation quality over independent training.

PDF Details

ECAI Conference 2016 Conference Paper

Enhancing Sketch-Based Image Retrieval via Deep Discriminative Representation

Fei Huang
Yong Cheng
Cheng Jin 0001
Yuejie Zhang
Tao Zhang 0022

In this paper we aim to employ deep learning to enhance SBIR via deep discriminative representation. Our main contributions focus on: 1) The deep discriminative representation is established to bridge both the visual appearance gap and the semantic gap between sketches and images; 2) The deep learning pattern is applied to our SBIR model through training on our transformed sketch-like images to overcome the rarity of training sketches. Our experiments on a large number of public sketch and image data have obtained very positive results.

Details

YNIMG Journal 2011 Journal Article

Structural MRI detects progressive regional brain atrophy and neuroprotective effects in N171-82Q Huntington's disease mouse model

Yong Cheng
Qi Peng
Zhipeng Hou
Manisha Aggarwal
Jiangyang Zhang
Susumu Mori
Christopher A. Ross
Wenzhen Duan

Huntington's disease (HD) displays progressive striatal atrophy that occurs long before the onset of clinical motor symptoms. As there is no treatment for the disease once overt symptoms appear, it has been suggested that neuroprotective therapy given during this presymptomatic period might slow progression of the disease. This requires biomarkers that can reliably detect early changes and are sensitive to treatment response. In mouse models of HD, structural MRI measures have been shown to detect disease onset. To determine whether such measures could also be suitable biomarkers for following responses to treatment, we used T2-weighted MR imaging combined with automated morphological analyses and characterized changes in regional brain volumes longitudinally in the N171-82Q HD mouse model in a preclinical trial. We report here that N171-82Q HD mice exhibit adult-onset and progressive brain atrophy in the striatum and neocortex as well as in whole brain; the progressive atrophy in striatum and neocortex is positively correlated with motor deficits. Most notably, MRI also detected neuroprotective effects of sertraline treatment, a neuroprotective agent confirmed in our previous studies. Our present studies provide the first evidence that longitudinal structural MRI measures can detect the therapeutic effect in HD mice, suggesting that such measures in brain could be valuable biomarkers in HD clinical trials.

Details DOI