Xiaolei Huang

Haomiao Ni, Yuan Xue, Kelvin Wong et al.

Accurate infarct segmentation in non-contrast CT (NCCT) images is a crucial step toward computer-aided acute ischemic stroke (AIS) assessment. In clinical practice, bilateral symmetric comparison of brain hemispheres is usually used to locate pathological abnormalities. Recent research has explored asymmetries to assist with AIS segmentation. However, most previous symmetry-based work mixed different types of asymmetries when evaluating their contribution to AIS. In this paper, we propose a novel Asymmetry Disentanglement Network (ADN) to automatically separate pathological asymmetries and intrinsic anatomical asymmetries in NCCTs for more effective and interpretable AIS segmentation. ADN first performs asymmetry disentanglement based on input NCCTs, which produces different types of 3D asymmetry maps. Then a synthetic, intrinsic-asymmetry-compensated and pathology-asymmetry-salient NCCT volume is generated and later used as input to a segmentation network. The training of ADN incorporates domain knowledge and adopts a tissue-type aware regularization loss function to encourage clinically-meaningful pathological asymmetry extraction. Coupled with an unsupervised 3D transformation network, ADN achieves state-of-the-art AIS segmentation performance on a public NCCT dataset. In addition to the superior performance, we believe the learned clinically-interpretable asymmetry maps can also provide insights towards a better understanding of AIS assessment. Our code is available at https://github.com/nihaomiao/MICCAI22_ADN.

Yanglan Ou, Ye Yuan, Xiaolei Huang et al. · cmu

We present a new encoder-decoder Vision Transformer architecture, Patcher, for medical image segmentation. Unlike standard Vision Transformers, it employs Patcher blocks that segment an image into large patches, each of which is further divided into small patches. Transformers are applied to the small patches within a large patch, which constrains the receptive field of each pixel. We intentionally make the large patches overlap to enhance intra-patch communication. The encoder employs a cascade of Patcher blocks with increasing receptive fields to extract features from local to global levels. This design allows Patcher to benefit from both the coarse-to-fine feature extraction common in CNNs and the superior spatial relationship modeling of Transformers. We also propose a new mixture-of-experts (MoE) based decoder, which treats the feature maps from the encoder as experts and selects a suitable set of expert features to predict the label for each pixel. The use of MoE enables better specializations of the expert features and reduces interference between them during inference. Extensive experiments demonstrate that Patcher outperforms state-of-the-art Transformer- and CNN-based approaches significantly on stroke lesion segmentation and polyp segmentation. Code for Patcher is released with publication to facilitate future research.

Jiachen Liu, Pan Ji, Nitin Bansal et al.

We present a novel framework named PlaneMVS for 3D plane reconstruction from multiple input views with known camera poses. Most previous learning-based plane reconstruction methods reconstruct 3D planes from single images, which highly rely on single-view regression and suffer from depth scale ambiguity. In contrast, we reconstruct 3D planes with a multi-view-stereo (MVS) pipeline that takes advantage of multi-view geometry. We decouple plane reconstruction into a semantic plane detection branch and a plane MVS branch. The semantic plane detection branch is based on a single-view plane detection framework but with differences. The plane MVS branch adopts a set of slanted plane hypotheses to replace conventional depth hypotheses to perform plane sweeping strategy and finally learns pixel-level plane parameters and its planar depth map. We present how the two branches are learned in a balanced way, and propose a soft-pooling loss to associate the outputs of the two branches and make them benefit from each other. Extensive experiments on various indoor datasets show that PlaneMVS significantly outperforms state-of-the-art (SOTA) single-view plane reconstruction methods on both plane detection and 3D geometry metrics. Our method even outperforms a set of SOTA learning-based MVS methods thanks to the learned plane priors. To the best of our knowledge, this is the first work on 3D plane reconstruction within an end-to-end MVS framework. Source code: https://github.com/oppo-us-research/PlaneMVS.

Yuexin Wu, Xiaolei Huang

Class imbalance naturally exists when train and test models in different domains. Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations from the source domain and unlabeled data from the target domain. However, existing state-of-the-art UDA models learn domain-invariant representations and evaluate primarily on class-balanced data across domains. In this work, we propose an unsupervised domain adaptation approach via reinforcement learning that jointly leverages feature variants and imbalanced labels across domains. We experiment with the text classification task for its easily accessible datasets and compare the proposed method with five baselines. Experiments on three datasets prove that our proposed method can effectively learn robust domain-invariant representations and successfully adapt text classifiers on imbalanced classes over domains. The code is available at https://github.com/woqingdoua/ImbalanceClass.

Xiaolei Huang, Franck Dernoncourt, Mark Dredze

Clinical notes in Electronic Health Records (EHR) present rich documented information of patients to inference phenotype for disease diagnosis and study patient characteristics for cohort selection. Unsupervised user embedding aims to encode patients into fixed-length vectors without human supervisions. Medical concepts extracted from the clinical notes contain rich connections between patients and their clinical categories. However, existing unsupervised approaches of user embeddings from clinical notes do not explicitly incorporate medical concepts. In this study, we propose a concept-aware unsupervised user embedding that jointly leverages text documents and medical concepts from two clinical corpora, MIMIC-III and Diabetes. We evaluate user embeddings on both extrinsic and intrinsic tasks, including phenotype classification, in-hospital mortality prediction, patient retrieval, and patient relatedness. Experiments on the two clinical corpora show our approach exceeds unsupervised baselines, and incorporating medical concepts can significantly improve the baseline performance.

Yuexin Wu, I-Chan Huang, Xiaolei Huang

Imbalanced token distributions naturally exist in text documents, leading neural language models to overfit on frequent tokens. The token imbalance may dampen the robustness of radiology report generators, as complex medical terms appear less frequently but reflect more medical information. In this study, we demonstrate how current state-of-the-art models fail to generate infrequent tokens on two standard benchmark datasets (IU X-RAY and MIMIC-CXR) of radiology report generation. % However, no prior study has proposed methods to adapt infrequent tokens for text generators feeding with medical images. To solve the challenge, we propose the \textbf{T}oken \textbf{Im}balance Adapt\textbf{er} (\textit{TIMER}), aiming to improve generation robustness on infrequent tokens. The model automatically leverages token imbalance by an unlikelihood loss and dynamically optimizes generation processes to augment infrequent tokens. We compare our approach with multiple state-of-the-art methods on the two benchmarks. Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens. Our ablation analysis shows that our reinforcement learning method has a major effect in adapting token imbalance for radiology report generation.

Mohamed Elmoghany, Liangbing Zhao, Xiaoqian Shen et al. · allen-ai

Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background consistency across shots, seamless multi-subject shot-to-shot transitions, and scalability to hour-long narratives. Our approach introduces a background-consistent generation pipeline that maintains visual coherence across scenes while preserving character identity and spatial relationships. We further propose a transition-aware video synthesis module that generates smooth shot transitions for complex scenarios involving multiple subjects entering or exiting frames, going beyond the single-subject limitations of prior work. To support this, we contribute with a synthetic dataset of 10,000 multi-subject transition sequences covering underrepresented dynamic scene compositions. On VBench, InfinityStory achieves the highest Background Consistency (88.94), highest Subject Consistency (82.11), and the best overall average rank (2.80), showing improved stability, smoother transitions, and better temporal coherence.

Jiachen Liu, Yuan Xue, Jose Duarte et al.

The automatic generation of floorplans given user inputs has great potential in architectural design and has recently been explored in the computer vision community. However, the majority of existing methods synthesize floorplans in the format of rasterized images, which are difficult to edit or customize. In this paper, we aim to synthesize floorplans as sequences of 1-D vectors, which eases user interaction and design customization. To generate high fidelity vectorized floorplans, we propose a novel two-stage framework, including a draft stage and a multi-round refining stage. In the first stage, we encode the room connectivity graph input by users with a graph convolutional network (GCN), then apply an autoregressive transformer network to generate an initial floorplan sequence. To polish the initial design and generate more visually appealing floorplans, we further propose a novel panoptic refinement network(PRN) composed of a GCN and a transformer network. The PRN takes the initial generated sequence as input and refines the floorplan design while encouraging the correct room connectivity with our proposed geometric loss. We have conducted extensive experiments on a real-world floorplan dataset, and the results show that our method achieves state-of-the-art performance under different settings and evaluation metrics.

Saukun Thika You, Nguyen Anh Khoa Tran, Wesley K. Marizane et al.

Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses; when the experts disagree, a structured counter-argumentation round and cross-source adjudication resolve the conflict, followed by a cascading safety layer that filters common false-positive patterns. We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families. Experimental results show that BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines. Further analyses across six backbone models and two prompting strategies confirm that retrieval augmentation and structured debate are complementary, and that the framework benefits most from models with sufficient instruction-following and clinical language understanding.

Haomiao Ni, Yuan Xue, Liya Ma et al.

General movement assessment (GMA) of infant movement videos (IMVs) is an effective method for early detection of cerebral palsy (CP) in infants. We demonstrate in this paper that end-to-end trainable neural networks for image sequence recognition can be applied to achieve good results in GMA, and more importantly, augmenting raw video with infant body parsing and pose estimation information can significantly improve performance. To solve the problem of efficiently utilizing partially labeled IMVs for body parsing, we propose a semi-supervised model, termed SiamParseNet (SPN), which consists of two branches, one for intra-frame body parts segmentation and another for inter-frame label propagation. During training, the two branches are jointly trained by alternating between using input pairs of only labeled frames and input of both labeled and unlabeled frames. We also investigate training data augmentation by proposing a factorized video generative adversarial network (FVGAN) to synthesize novel labeled frames for training. When testing, we employ a multi-source inference mechanism, where the final result for a test frame is either obtained via the segmentation branch or via propagation from a nearby key frame. We conduct extensive experiments for body parsing using SPN on two infant movement video datasets, where SPN coupled with FVGAN achieves state-of-the-art performance. We further demonstrate that SPN can be easily adapted to the infant pose estimation task with superior performance. Last but not least, we explore the clinical application of our method for GMA. We collected a new clinical IMV dataset with GMA annotations, and our experiments show that SPN models for body parsing and pose estimation trained on the first two datasets generalize well to the new clinical dataset and their results can significantly boost the CRNN-based GMA prediction performance.

Xiaolei Huang, Alexandra Wormley, Adam Cohen

Classifying moral values in user-generated text from social media is critical in understanding community cultures and interpreting user behaviors of social movements. Moral values and language usage can change across the social movements; however, text classifiers are usually trained in source domains of existing social movements and tested in target domains of new social issues without considering the variations. In this study, we examine domain shifts of moral values and language usage, quantify the effects of domain shifts on the morality classification task, and propose a neural adaptation framework via instance weighting to improve cross-domain classification tasks. The quantification analysis suggests a strong correlation between morality shifts, language usage, and classification performance. We evaluate the neural adaptation framework on a public Twitter data across 7 social movements and gain classification improvements up to 12.1\%. Finally, we release a new data of the COVID-19 vaccine labeled with moral values and evaluate our approach on the new target domain. For the case study of the COVID-19 vaccine, our adaptation framework achieves up to 5.26\% improvements over neural baselines.

Xiaolei Huang

Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation model to reduce the gender bias and improve performance of text classifiers under multilingual settings. We evaluate our approach on two text classification tasks, hate speech detection and rating prediction, and demonstrate the effectiveness of our approach with three fair-aware baselines.

Hanshu Rao, Guangzeng Han, Xiaolei Huang

Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both class imbalance and data difficulty. HAMR employs bi-level optimizations to dynamically estimate instance-level weights that prioritize genuinely challenging samples and minority classes, while a neighborhood-aware resampling mechanism amplifies training focus on hard examples and their semantically similar neighbors. We validate HAMR on six imbalanced datasets covering multiple tasks and spanning biomedical, disaster response, and sentiment domains. Experimental results show that HAMR achieves substantial improvements for minority classes and consistently outperforms strong baselines. Extensive ablation studies demonstrate that our proposed modules synergistically contribute to performance gains and highlight HAMR as a flexible and generalizable approach for class imbalance adaptation. Code is available at https://github.com/trust-nlp/ImbalanceLearning.

Mayira Sharif, Guangzeng Han, Weisi Liu et al.

To support rapid AI advances and broaden access to large-scale computing resources for under-resourced institutions at the Mid-South, we established the first regional mid-scale GPU cluster at the University of Memphis (UofM), iTiger. We present and analyze efforts of infrastructure management and computational support for educators, students, and researchers across scientific and engineering disciplines, such as precision agriculture, smart transportation, and health informatics. We outline our initiatives to broaden cluster adoption on research and education, such as seed grant programs, workshop trainings, course integration, and other outreach activities. We also identify challenges and further discuss findings of GPU infrastructure adoptions among college students and multidisciplinary researchers. The insights will indicate how to effectively and broaden infrastructure adoption and integrate into research and workforce developments.

Guangzeng Han, Xiaolei Huang

Instruction-tuning datasets often contain substantial redundancy and low-quality samples, necessitating effective data selection methods. We propose an instruction data selection framework based on weighted in-context influence (wICI), which measures how effectively each candidate example reduces instruction-following difficulty for semantically related peers. Through systematic experiments, we address three key questions: what constitutes effective instruction tuning data from an in-context perspective, whether sample difficulty correlates with in-context influence, and how in-context influence translates to instruction tuning effectiveness. Experiments across multiple models and benchmarks demonstrate that our method consistently outperforms existing baselines under constrained data budgets, while empirically showing that sample difficulty negatively correlates with in-context influence.

Weisi Liu, Zhe He, Xiaolei Huang

Time roots in applying language models for biomedical applications: models are trained on historical data and will be deployed for new or future data, which may vary from training data. While increasing biomedical tasks have employed state-of-the-art language models, there are very few studies have examined temporal effects on biomedical models when data usually shifts across development and deployment. This study fills the gap by statistically probing relations between language model performance and data shifts across three biomedical tasks. We deploy diverse metrics to evaluate model performance, distance methods to measure data drifts, and statistical methods to quantify temporal effects on biomedical language models. Our study shows that time matters for deploying biomedical language models, while the degree of performance degradation varies by biomedical tasks and statistical quantification approaches. We believe this study can establish a solid benchmark to evaluate and assess temporal effects on deploying biomedical language models.

Yu Wu, Guangzeng Han, Ibra Niang Niang et al.

To improve crop genetics, high-throughput, effective and comprehensive phenotyping is a critical prerequisite. While such tasks were traditionally performed manually, recent advances in multimodal foundation models, especially in vision-language models (VLMs), have enabled more automated and robust phenotypic analysis. However, plant science remains a particularly challenging domain for foundation models because it requires domain-specific knowledge, fine-grained visual interpretation, and complex biological and agronomic reasoning. To address this gap, we develop PlantXpert, an evidence-grounded multimodal reasoning benchmark for soybean and cotton phenotyping. Our benchmark provides a structured and reproducible framework for agronomic adaptation of VLMs, and enables controlled comparison between base models and their domain-adapted counterparts. We constructed a dataset comprising 385 digital images and more than 3,000 benchmark samples spanning key plant science domains including disease, pest control, weed management, and yield. The benchmark can assess diverse capabilities including visual expertise, quantitative reasoning, and multi-step agronomic reasoning. A total of 11 state-of-the-art VLMs were evaluated. The results indicate that task-specific fine-tuning leads to substantial improvement in accuracy, with models such as Qwen3-VL-4B and Qwen3-VL-30B achieving up to 78%. At the same time, gains from model scaling diminish beyond a certain capacity, generalization across soybean and cotton remains uneven, and quantitative as well as biologically grounded reasoning continue to pose substantial challenges. These findings suggest that PlantXpert can serve as a foundation for assessing evidence-grounded agronomic reasoning and for advancing multimodal model development in plant science.

Guangzeng Han, James G. Murphy, Benjamin O. Ladd et al.

BACKGROUND: Coding Motivational Interviewing (MI) sessions is essential for understanding client behaviors and predicting outcomes, but it requires substantial time and labor from trained MI professionals. Recent advances in audio-language models (ALMs) offer new opportunities to automate MI coding by capturing multimodal behavioral signals. OBJECTIVE: This study aims to develop an automatic MI coding approach based on ALMs that analyzes raw audio input and integrates predictions from multiple reasoning trajectories using self-consistency to improve coding robustness. METHODS: We experimented with five recorded sessions from de-identified MI audio tapes. We deployed ALMs with four complementary analytic prompts to support utterance-level reasoning: analytic prompting for verbal cues, prosody-aware prompting for acoustic cues, evidence-scoring prompting for quantitative hypothesis testing, and comparative prompting for contrastive reasoning. Three stochastic samples were drawn for each prompt, generating 12 independent reasoning trajectories per utterance. Final predictions were determined by majority voting across all trajectories. RESULTS: Performance was evaluated using accuracy, precision, recall, and macro-F1 scores. The proposed multimodal self-consistency approach achieved 52.56% accuracy, 54.03% precision, 47.45% recall, and a macro-F1 score of 46.40%, exceeding baseline methods. Systematic ablation experiments that removed individual modules consistently degraded performance on the primary metrics. CONCLUSIONS: Multimodal self-consistency outperforms single-pass baseline prompting approaches for MI coding. These findings suggest that incorporating both what clients say and how they say it can support more reliable automatic MI coding.

Sampoorna Poria, Xiaolei Huang

Rapid developments of large language models have revolutionized many NLP tasks for English data. Unfortunately, the models and their evaluations for low-resource languages are being overlooked, especially for languages in South Asia. Although there are more than 650 languages in South Asia, many of them either have very limited computational resources or are missing from existing language models. Thus, a concrete question to be answered is: Can we assess the current stage and challenges to inform our NLP community and facilitate model developments for South Asian languages? In this survey, we have comprehensively examined current efforts and challenges of NLP models for South Asian languages by retrieving studies since 2020, with a focus on transformer-based models, such as BERT, T5, & GPT. We present advances and gaps across 3 essential aspects: data, models, & tasks, such as available data sources, fine-tuning strategies, & domain applications. Our findings highlight substantial issues, including missing data in critical domains (e.g., health), code-mixing, and lack of standardized evaluation benchmarks. Our survey aims to raise awareness within the NLP community for more targeted data curation, unify benchmarks tailored to cultural and linguistic nuances of South Asia, and encourage an equitable representation of South Asian languages. The complete list of resources is available at: https://github.com/trust-nlp/LM4SouthAsia-Survey.

Jiarong Ye, Yuan Xue, Peter Liu et al.

Generative models have been applied in the medical imaging domain for various image recognition and synthesis tasks. However, a more controllable and interpretable image synthesis model is still lacking yet necessary for important applications such as assisting in medical training. In this work, we leverage the efficient self-attention and contrastive learning modules and build upon state-of-the-art generative adversarial networks (GANs) to achieve an attribute-aware image synthesis model, termed AttributeGAN, which can generate high-quality histopathology images based on multi-attribute inputs. In comparison to existing single-attribute conditional generative models, our proposed model better reflects input attributes and enables smoother interpolation among attribute values. We conduct experiments on a histopathology dataset containing stained H&E images of urothelial carcinoma and demonstrate the effectiveness of our proposed model via comprehensive quantitative and qualitative comparisons with state-of-the-art models as well as different variants of our model. Code is available at https://github.com/karenyyy/MICCAI2021AttributeGAN.

Guangzeng Han, Weisi Liu, Xiaolei Huang et al.

Automatic coding patient behaviors is essential to support decision making for psychotherapists during the motivational interviewing (MI), a collaborative communication intervention approach to address psychiatric issues, such as alcohol and drug addiction. While the behavior coding task has rapidly adapted machine learning to predict patient states during the MI sessions, lacking of domain-specific knowledge and overlooking patient-therapist interactions are major challenges in developing and deploying those models in real practice. To encounter those challenges, we introduce the Chain-of-Interaction (CoI) prompting method aiming to contextualize large language models (LLMs) for psychiatric decision support by the dyadic interactions. The CoI prompting approach systematically breaks down the coding task into three key reasoning steps, extract patient engagement, learn therapist question strategies, and integrates dyadic interactions between patients and therapists. This approach enables large language models to leverage the coding scheme, patient state, and domain knowledge for patient behavioral coding. Experiments on real-world datasets can prove the effectiveness and flexibility of our prompting method with multiple state-of-the-art LLMs over existing prompting baselines. We have conducted extensive ablation analysis and demonstrate the critical role of dyadic interactions in applying LLMs for psychotherapy behavior understanding.

Weisi Liu, Guangzeng Han, Xiaolei Huang

Time introduces fundamental challenges in model development and deployment: models are usually trained on historical data while deployed on future data where semantic distributions and domain knowledge may evolve. Unfortunately, existing studies either overlook temporal shifts or hardly capture rich shifting patterns of both semantic and knowledge. We develop Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation (KARITA) to capture diverse temporal shifts (e.g., uncertainty and feature shift), construct and integrate rich knowledge sources (e.g., medical ontology like MeSH), and leverage shifting insights for selecting-retrieval augmented learning. We evaluate KARITA on classification tasks across multiple domains, clinical, legal, and scientific corpora, demonstrating consistent improvements across multiple domains with temporal adaptation. Our results show that knowledge integration can be more critical and effective in temporal augmentation and learning.

Guangzeng Han, Jack Tsao, Xiaolei Huang

Lengthy documents pose a unique challenge to neural language models due to substantial memory consumption. While existing state-of-the-art (SOTA) models segment long texts into equal-length snippets (e.g., 128 tokens per snippet) or deploy sparse attention networks, these methods have new challenges of context fragmentation and generalizability due to sentence boundaries and varying text lengths. For example, our empirical analysis has shown that SOTA models consistently overfit one set of lengthy documents (e.g., 2000 tokens) while performing worse on texts with other lengths (e.g., 1000 or 4000). In this study, we propose a Length-Aware Multi-Kernel Transformer (LAMKIT) to address the new challenges for the long document classification. LAMKIT encodes lengthy documents by diverse transformer-based kernels for bridging context boundaries and vectorizes text length by the kernels to promote model robustness over varying document lengths. Experiments on five standard benchmarks from health and law domains show LAMKIT outperforms SOTA models up to an absolute 10.9% improvement. We conduct extensive ablation analyses to examine model robustness and effectiveness over varying document lengths.

Guangzeng Han, Weisi Liu, Xiaolei Huang

Large Language Models (LLMs) excel at generating synthetic data, but ensuring its quality and diversity remains challenging. We propose Genetic Prompt, a novel framework that combines genetic algorithms with LLMs to augment synthetic data generation. Our approach treats semantic text attributes as gene sequences and leverages the LLM to simulate crossover and mutation operations. This genetic process enhances data quality and diversity by creating novel attribute combinations, yielding synthetic distributions closer to real-world data. To optimize parent selection, we also integrate an active learning scheme that expands the offspring search space. Our experiments on multiple NLP tasks reveal several key findings: Genetic Prompt not only significantly outperforms state-of-the-art baselines but also shows robust performance across various generator model sizes and scales. Moreover, we demonstrate that fusing our synthetic data with the original training set significantly boosts downstream model performance, particularly for class-imbalanced scenarios. Our findings validate that Genetic Prompt is an effective method for producing high-quality synthetic data for a wide range of NLP applications.

Precious Jones, Weisi Liu, I-Chan Huang et al.

Data imbalance is a fundamental challenge in applying language models to biomedical applications, particularly in ICD code prediction tasks where label and demographic distributions are uneven. While state-of-the-art language models have been increasingly adopted in biomedical tasks, few studies have systematically examined how data imbalance affects model performance and fairness across demographic groups. This study fills the gap by statistically probing the relationship between data imbalance and model performance in ICD code prediction. We analyze imbalances in a standard benchmark data across gender, age, ethnicity, and social determinants of health by state-of-the-art biomedical language models. By deploying diverse performance metrics and statistical analyses, we explore the influence of data imbalance on performance variations and demographic fairness. Our study shows that data imbalance significantly impacts model performance and fairness, but feature similarity to the majority class may be a more critical factor. We believe this study provides valuable insights for developing more equitable and robust language models in healthcare applications.

Weisi Liu, Guangzeng Han, Xiaolei Huang

Time is implicitly embedded in classification process: classifiers are usually built on existing data while to be applied on future data whose distributions (e.g., label and token) may change. However, existing state-of-the-art classification models merely consider the temporal variations and primarily focus on English corpora, which leaves temporal studies less explored, let alone under multilingual settings. In this study, we fill the gap by treating time as domains (e.g., 2024 vs. 2025), examining temporal effects, and developing a domain adaptation framework to generalize classifiers over time on multiple languages. Our framework proposes Mixture of Temporal Experts (MoTE) to leverage both semantic and data distributional shifts to learn and adapt temporal trends into classification models. Our analysis shows classification performance varies over time across different languages, and we experimentally demonstrate that MoTE can enhance classifier generalizability over temporal data shifts. Our study provides analytic insights and addresses the need for time-aware models that perform robustly in multilingual scenarios.

Mohamed Elmoghany, Ryan Rossi, Seunghyun Yoon et al.

Despite the significant progress that has been made in video generative models, existing state-of-the-art methods can only produce videos lasting 5-16 seconds, often labeled "long-form videos". Furthermore, videos exceeding 16 seconds struggle to maintain consistent character appearances and scene layouts throughout the narrative. In particular, multi-subject long videos still fail to preserve character consistency and motion coherence. While some methods can generate videos up to 150 seconds long, they often suffer from frame redundancy and low temporal diversity. Recent work has attempted to produce long-form videos featuring multiple characters, narrative coherence, and high-fidelity detail. We comprehensively studied 32 papers on video generation to identify key architectural components and training strategies that consistently yield these qualities. We also construct a comprehensive novel taxonomy of existing methods and present comparative tables that categorize papers by their architectural designs and performance characteristics.

Hanshu Rao, Weisi Liu, Haohan Wang et al.

Synthetic data generation--mitigating data scarcity, privacy concerns, and data quality challenges in biomedical fields--has been facilitated by rapid advances of large language models (LLMs). This scoping review follows PRISMA-ScR guidelines and synthesizes 59 studies, published between 2020 and 2025 and collected from PubMed, ACM, Web of Science, and Google Scholar. The review systematically examines biomedical research and application trends in synthetic data generation, emphasizing clinical applications, methodologies, and evaluations. Our analysis identifies data modalities of unstructured texts (78.0%), tabular data (13.6%), and multimodal sources (8.4%); generation methods of prompting (72.9%), fine-tuning (22.0%) LLMs and specialized model (5.1%); and heterogeneous evaluations of intrinsic metrics (27.1%), human-in-the-loop assessments (55.9%), and LLM-based evaluations (13.6%). The analysis addresses current limitations in what, where, and how health professionals can leverage synthetic data generation for biomedical domains. Our review also highlights challenges in adaption across clinical domains, resource and model accessibility, and evaluation standardizations.

Guo-Ye Yang, George Kiyohiro Nakayama, Zi-Kai Xiao et al.

Great progress has been made in learning-based object detection methods in the last decade. Two-stage detectors often have higher detection accuracy than one-stage detectors, due to the use of region of interest (RoI) feature extractors which extract transformation-invariant RoI features for different RoI proposals, making refinement of bounding boxes and prediction of object categories more robust and accurate. However, previous RoI feature extractors can only extract invariant features under limited transformations. In this paper, we propose a novel RoI feature extractor, termed Semantic RoI Align (SRA), which is capable of extracting invariant RoI features under a variety of transformations for two-stage detectors. Specifically, we propose a semantic attention module to adaptively determine different sampling areas by leveraging the global and local semantic relationship within the RoI. We also propose a Dynamic Feature Sampler which dynamically samples features based on the RoI aspect ratio to enhance the efficiency of SRA, and a new position embedding, \ie Area Embedding, to provide more accurate position information for SRA through an improved sampling area representation. Experiments show that our model significantly outperforms baseline models with slight computational overhead. In addition, it shows excellent generalization ability and can be used to improve performance with various state-of-the-art backbones and detection methods.

Josef Spjut, Fengyuan Zhu, Xiaolei Huang et al.

Augmented Reality (AR) is an emerging field ripe for experimentation, especially when it comes to developing the kinds of applications and experiences that will drive mass adoption of the technology. While we aren't aware of any current consumer product that realize a wearable, wide Field of View (FoV), AR Head Mounted Display (HMD), such devices will certainly come. In order for these sophisticated, likely high-cost hardware products to succeed, it is important they provide a high quality user experience. To that end, we prototyped 4 experimental applications for wide FoV displays that will likely exist in the future. Given current AR HMD limitations, we used a AR simulator built on web technology and VR headsets to demonstrate these applications, allowing users and designers to peer into the future.

Fengting Yang, Xiaolei Huang, Zihan Zhou

Depth-from-focus (DFF) is a technique that infers depth using the focus change of a camera. In this work, we propose a convolutional neural network (CNN) to find the best-focused pixels in a focal stack and infer depth from the focus estimation. The key innovation of the network is the novel deep differential focus volume (DFV). By computing the first-order derivative with the stacked features over different focal distances, DFV is able to capture both the focus and context information for focus analysis. Besides, we also introduce a probability regression mechanism for focus estimation to handle sparsely sampled focal stacks and provide uncertainty estimation to the final prediction. Comprehensive experiments demonstrate that the proposed model achieves state-of-the-art performance on multiple datasets with good generalizability and fast speed.

Yuan Xue, Jiarong Ye, Qianying Zhou et al.

Histopathological analysis is the present gold standard for precancerous lesion diagnosis. The goal of automated histopathological classification from digital images requires supervised training, which requires a large number of expert annotations that can be expensive and time-consuming to collect. Meanwhile, accurate classification of image patches cropped from whole-slide images is essential for standard sliding window based histopathology slide classification methods. To mitigate these issues, we propose a carefully designed conditional GAN model, namely HistoGAN, for synthesizing realistic histopathology image patches conditioned on class labels. We also investigate a novel synthetic augmentation framework that selectively adds new synthetic image patches generated by our proposed HistoGAN, rather than expanding directly the training set with synthetic images. By selecting synthetic images based on the confidence of their assigned labels and their feature similarity to real labeled images, our framework provides quality assurance to synthetic augmentation. Our models are evaluated on two datasets: a cervical histopathology image dataset with limited annotations, and another dataset of lymph node histopathology images with metastatic cancer. Here, we show that leveraging HistoGAN generated images with selective augmentation results in significant and consistent improvements of classification performance (6.7% and 2.8% higher accuracy, respectively) for cervical histopathology and metastatic cancer datasets.

Tongan Cai, Haomiao Ni, Mingli Yu et al.

In an emergency room (ER) setting, stroke triage or screening is a common challenge. A quick CT is usually done instead of MRI due to MRI's slow throughput and high cost. Clinical tests are commonly referred to during the process, but the misdiagnosis rate remains high. We propose a novel multimodal deep learning framework, DeepStroke, to achieve computer-aided stroke presence assessment by recognizing patterns of minor facial muscles incoordination and speech inability for patients with suspicion of stroke in an acute setting. Our proposed DeepStroke takes one-minute facial video data and audio data readily available during stroke triage for local facial paralysis detection and global speech disorder analysis. Transfer learning was adopted to reduce face-attribute biases and improve generalizability. We leverage a multi-modal lateral fusion to combine the low- and high-level features and provide mutual regularization for joint training. Novel adversarial training is introduced to obtain identity-free and stroke-discriminative features. Experiments on our video-audio dataset with actual ER patients show that DeepStroke outperforms state-of-the-art models and achieves better performance than both a triage team and ER doctors, attaining a 10.94% higher sensitivity and maintaining 7.37% higher accuracy than traditional stroke triage when specificity is aligned. Meanwhile, each assessment can be completed in less than six minutes, demonstrating the framework's great potential for clinical translation.

Yuan Xue, Yuan-Chen Guo, Han Zhang et al.

In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content. While classic works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation tasks. This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics. This motivates new perspectives on input representation and interactivity, cross pollination between major image generation paradigms, and evaluation and comparison of generation methods.

Yanglan Ou, Ye Yuan, Xiaolei Huang et al.

Diffusion-weighted (DW) magnetic resonance imaging is essential for the diagnosis and treatment of ischemic stroke. DW images (DWIs) are usually acquired in multi-slice settings where lesion areas in two consecutive 2D slices are highly discontinuous due to large slice thickness and sometimes even slice gaps. Therefore, although DWIs contain rich 3D information, they cannot be treated as regular 3D or 2D images. Instead, DWIs are somewhere in-between (or 2.5D) due to the volumetric nature but inter-slice discontinuities. Thus, it is not ideal to apply most existing segmentation methods as they are designed for either 2D or 3D images. To tackle this problem, we propose a new neural network architecture tailored for segmenting highly-discontinuous 2.5D data such as DWIs. Our network, termed LambdaUNet, extends UNet by replacing convolutional layers with our proposed Lambda+ layers. In particular, Lambda+ layers transform both intra-slice and inter-slice context around a pixel into linear functions, called lambdas, which are then applied to the pixel to produce informative 2.5D features. LambdaUNet is simple yet effective in combining sparse inter-slice information from adjacent slices while also capturing dense contextual features within a single slice. Experiments on a unique clinical dataset demonstrate that LambdaUNet outperforms existing 3D/2D image segmentation methods including recent variants of UNet. Code for LambdaUNet is released with the publication to facilitate future research.

Vincent Pisztora, Yanglan Ou, Xiaolei Huang et al.

In this paper we propose $ε$-Consistent Mixup ($ε$mu). $ε$mu is a data-based structural regularization technique that combines Mixup's linear interpolation with consistency regularization in the Mixup direction, by compelling a simple adaptive tradeoff between the two. This learnable combination of consistency and interpolation induces a more flexible structure on the evolution of the response across the feature space and is shown to improve semi-supervised classification accuracy on the SVHN and CIFAR10 benchmark datasets, yielding the largest gains in the most challenging low label-availability scenarios. Empirical studies comparing $ε$mu and Mixup are presented and provide insight into the mechanisms behind $ε$mu's effectiveness. In particular, $ε$mu is found to produce more accurate synthetic labels and more confident predictions than Mixup.

Xiaolei Huang, Michael J. Paul, Robin Burke et al.

Language varies across users and their interested fields in social media data: words authored by a user across his/her interests may have different meanings (e.g., cool) or sentiments (e.g., fast). However, most of the existing methods to train user embeddings ignore the variations across user interests, such as product and movie categories (e.g., drama vs. action). In this study, we treat the user interest as domains and empirically examine how the user language can vary across the user factor in three English social media datasets. We then propose a user embedding model to account for the language variability of user interests via a multitask learning framework. The model learns user language and its variations without human supervision. While existing work mainly evaluated the user embedding by extrinsic tasks, we propose an intrinsic evaluation via clustering and evaluate user embeddings by an extrinsic task, text classification. The experiments on the three English-language social media datasets show that our proposed approach can generally outperform baselines via adapting the user factor.

Yuexin Wu, Xiaolei Huang

Rating prediction is a core problem in recommender systems to quantify user's preferences towards items, however, rating imbalance naturally roots in real-world user ratings that cause biased predictions and lead to poor performance on tail ratings. While existing approaches in the rating prediction task deploy weighted cross-entropy to re-weight training samples, such approaches commonly assume an normal distribution, a symmetrical and balanced space. In contrast to the normal assumption, we propose a novel \underline{\emph{G}}umbel-based \underline{\emph{V}}ariational \underline{\emph{N}}etwork framework (GVN) to model rating imbalance and augment feature representations by the Gumbel distributions. We propose a Gumbel-based variational encoder to transform features into non-normal vector space. Second, we deploy a multi-scale convolutional fusion network to integrate comprehensive views of users and items from the rating matrix and user reviews. Third, we adopt a skip connection module to personalize final rating predictions. We conduct extensive experiments on five datasets with both error- and ranking-based metrics. Experiments on ranking and regression evaluation tasks prove that the GVN can effectively achieve state-of-the-art performance across the datasets and reduce the biased predictions of tail ratings. We compare with various distributions (e.g., normal and Poisson) and demonstrate the effectiveness of Gumbel-based methods on class-imbalance modeling.

Jiarong Ye, Yuan Xue, L. Rodney Long et al.

Synthesizing realistic medical images provides a feasible solution to the shortage of training data in deep learning based medical image recognition systems. However, the quality control of synthetic images for data augmentation purposes is under-investigated, and some of the generated images are not realistic and may contain misleading features that distort data distribution when mixed with real images. Thus, the effectiveness of those synthetic images in medical image recognition systems cannot be guaranteed when they are being added randomly without quality assurance. In this work, we propose a reinforcement learning (RL) based synthetic sample selection method that learns to choose synthetic images containing reliable and informative features. A transformer based controller is trained via proximal policy optimization (PPO) using the validation classification accuracy as the reward. The selected images are mixed with the original training data for improved training of image recognition systems. To validate our method, we take the pathology image recognition as an example and conduct extensive experiments on two histopathology image datasets. In experiments on a cervical dataset and a lymph node dataset, the image classification performance is improved by 8.1% and 2.3%, respectively, when utilizing high-quality synthetic images selected by our RL framework. Our proposed synthetic sample selection method is general and has great potential to boost the performance of various medical image recognition systems given limited annotation.

Haomiao Ni, Yuan Xue, Qian Zhang et al.

General movement assessment (GMA) of infant movement videos (IMVs) is an effective method for the early detection of cerebral palsy (CP) in infants. Automated body parsing is a crucial step towards computer-aided GMA, in which infant body parts are segmented and tracked over time for movement analysis. However, acquiring fully annotated data for video-based body parsing is particularly expensive due to the large number of frames in IMVs. In this paper, we propose a semi-supervised body parsing model, termed SiamParseNet (SPN), to jointly learn single frame body parsing and label propagation between frames in a semi-supervised fashion. The Siamese-structured SPN consists of a shared feature encoder, followed by two separate branches: one for intra-frame body parts segmentation, and one for inter-frame label propagation. The two branches are trained jointly, taking pairs of frames from the same videos as their input. An adaptive training process is proposed that alternates training modes between using input pairs of only labeled frames and using inputs of both labeled and unlabeled frames. During testing, we employ a multi-source inference mechanism, where the final result for a test frame is either obtained via the segmentation branch or via propagation from a nearby key frame. We conduct extensive experiments on a partially-labeled IMV dataset where SPN outperforms all prior arts, demonstrating the effectiveness of our proposed method.

Yanglan Ou, Yuan Xue, Ye Yuan et al.

Cervical cancer is the second most prevalent cancer affecting women today. As the early detection of cervical carcinoma relies heavily upon screening and pre-clinical testing, digital cervicography has great potential as a primary or auxiliary screening tool, especially in low-resource regions due to its low cost and easy access. Although an automated cervical dysplasia detection system has been desirable, traditional fully-supervised training of such systems requires large amounts of annotated data which are often labor-intensive to collect. To alleviate the need for much manual annotation, we propose a novel graph convolutional network (GCN) based semi-supervised classification model that can be trained with fewer annotations. In existing GCNs, graphs are constructed with fixed features and can not be updated during the learning process. This limits their ability to exploit new features learned during graph convolution. In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance. Our experimental results on a cervical dysplasia classification dataset show that the proposed framework outperforms previous methods under a semi-supervised setting, especially when the labeled samples are scarce.

Xiaolei Huang, Linzi Xing, Franck Dernoncourt et al.

Existing research on fairness evaluation of document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes. In this work, we assemble and publish a multilingual Twitter corpus for the task of hate speech detection with inferred four author demographic factors: age, country, gender and race/ethnicity. The corpus covers five languages: English, Italian, Polish, Portuguese and Spanish. We evaluate the inferred demographic labels with a crowdsourcing platform, Figure Eight. To examine factors that can cause biases, we take an empirical analysis of demographic predictability on the English corpus. We measure the performance of four popular document classifiers and evaluate the fairness and bias of the baseline classifiers on the author-level demographic attributes.

Yuan Xue, Hui Tang, Zhi Qiao et al.

In this work, we propose to resolve the issue existing in current deep learning based organ segmentation systems that they often produce results that do not capture the overall shape of the target organ and often lack smoothness. Since there is a rigorous mapping between the Signed Distance Map (SDM) calculated from object boundary contours and the binary segmentation map, we exploit the feasibility of learning the SDM directly from medical scans. By converting the segmentation task into predicting an SDM, we show that our proposed method retains superior segmentation performance and has better smoothness and continuity in shape. To leverage the complementary information in traditional segmentation training, we introduce an approximated Heaviside function to train the model by predicting SDMs and segmentation maps simultaneously. We validate our proposed models by conducting extensive experiments on a hippocampus segmentation dataset and the public MICCAI 2015 Head and Neck Auto Segmentation Challenge dataset with multiple organs. While our carefully designed backbone 3D segmentation network improves the Dice coefficient by more than 5% compared to current state-of-the-arts, the proposed model with SDM learning produces smoother segmentation results with smaller Hausdorff distance and average surface distance, thus proving the effectiveness of our method.

Yuan Xue, Zihan Zhou, Xiaolei Huang

In architecture and computer-aided design, wireframes (i.e., line-based models) are widely used as basic 3D models for design evaluation and fast design iterations. However, unlike a full design file, a wireframe model lacks critical information, such as detailed shape, texture, and materials, needed by a conventional renderer to produce 2D renderings of the objects or scenes. In this paper, we bridge the information gap by generating photo-realistic rendering of indoor scenes from wireframe models in an image translation framework. While existing image synthesis methods can generate visually pleasing images for common objects such as faces and birds, these methods do not explicitly model and preserve essential structural constraints in a wireframe model, such as junctions, parallel lines, and planar surfaces. To this end, we propose a novel model based on a structure-appearance joint representation learned from both images and wireframes. In our model, structural constraints are explicitly enforced by learning a joint representation in a shared encoder network that must support the generation of both images and wireframes. Experiments on a wireframe-scene dataset show that our wireframe-to-image translation model significantly outperforms the state-of-the-art methods in both visual quality and structural integrity of generated images.

Yuan Xue, Jiarong Ye, Rodney Long et al.

Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced for rare diseases. To mitigate these issues, we investigate a novel data augmentation pipeline that selectively adds new synthetic images generated by conditional Adversarial Networks (cGANs), rather than extending directly the training set with synthetic images. The selection mechanisms that we introduce to the synthetic augmentation pipeline are motivated by the observation that, although cGAN-generated images can be visually appealing, they are not guaranteed to contain essential features for classification performance improvement. By selecting synthetic images based on the confidence of their assigned labels and their feature similarity to real labeled images, our framework provides quality assurance to synthetic augmentation by ensuring that adding the selected synthetic images to the training set will improve performance. We evaluate our model on a medical histopathology dataset, and two natural image classification benchmarks, CIFAR10 and SVHN. Results on these datasets show significant and consistent improvements in classification performance (with 6.8%, 3.9%, 1.6% higher accuracy, respectively) by leveraging cGAN generated images with selective augmentation.

Xiaolei Huang, Jonathan May, Nanyun Peng

Building named entity recognition (NER) models for languages that do not have much training data is a challenging task. While recent work has shown promising results on cross-lingual transfer from high-resource languages to low-resource languages, it is unclear what knowledge is transferred. In this paper, we first propose a simple and efficient neural architecture for cross-lingual NER. Experiments show that our model achieves competitive performance with the state-of-the-art. We further analyze how transfer learning works for cross-lingual NER on two transferable factors: sequential order and multilingual embeddings, and investigate how model performance varies across entity lengths. Finally, we conduct a case-study on a non-Latin language, Bengali, which suggests that leveraging knowledge from Wikipedia will be a promising direction to further improve the model performances. Our results can shed light on future research for improving cross-lingual NER.

Yuan Xue, Qianying Zhou, Jiarong Ye et al.

Cervical intraepithelial neoplasia (CIN) grade of histopathology images is a crucial indicator in cervical biopsy results. Accurate CIN grading of epithelium regions helps pathologists with precancerous lesion diagnosis and treatment planning. Although an automated CIN grading system has been desired, supervised training of such a system would require a large amount of expert annotations, which are expensive and time-consuming to collect. In this paper, we investigate the CIN grade classification problem on segmented epithelium patches. We propose to use conditional Generative Adversarial Networks (cGANs) to expand the limited training dataset, by synthesizing realistic cervical histopathology images. While the synthetic images are visually appealing, they are not guaranteed to contain meaningful features for data augmentation. To tackle this issue, we propose a synthetic-image filtering mechanism based on the divergence in feature space between generated images and class centroids in order to control the feature quality of selected synthetic images for data augmentation. Our models are evaluated on a cervical histopathology image dataset with a limited number of patch-level CIN grade annotations. Extensive experimental results show a significant improvement of classification accuracy from 66.3% to 71.7% using the same ResNet18 baseline classifier after leveraging our cGAN generated images with feature-based filtering, which demonstrates the effectiveness of our models.

Yutao Ma, Tao Xu, Xiaolei Huang et al.

Objective: Ultrahigh-resolution optical coherence microscopy (OCM) has recently demonstrated its potential for accurate diagnosis of human cervical diseases. One major challenge for clinical adoption, however, is the steep learning curve clinicians need to overcome to interpret OCM images. Developing an intelligent technique for computer-aided diagnosis (CADx) to accurately interpret OCM images will facilitate clinical adoption of the technology and improve patient care. Methods: 497 high-resolution 3-D OCM volumes (600 cross-sectional images each) were collected from 159 ex vivo specimens of 92 female patients. OCM image features were extracted using a convolutional neural network (CNN) model, concatenated with patient information (e.g., age, HPV results), and classified using a support vector machine classifier. Ten-fold cross-validations were utilized to test the performance of the CADx method in a five-class classification task and a binary classification task. Results: An 88.3 plus or minus 4.9% classification accuracy was achieved for five fine-grained classes of cervical tissue, namely normal, ectropion, low-grade and high-grade squamous intraepithelial lesions (LSIL and HSIL), and cancer. In the binary classification task (low-risk [normal, ectropion and LSIL] vs. high-risk [HSIL and cancer]), the CADx method achieved an area-under-the-curve (AUC) value of 0.959 with an 86.7 plus or minus 11.4% sensitivity and 93.5 plus or minus 3.8% specificity. Conclusion: The proposed deep-learning based CADx method outperformed three human experts. It was also able to identify morphological characteristics in OCM images that were consistent with histopathological interpretations. Significance: Label-free OCM imaging, combined with deep-learning based CADx methods, hold a great promise to be used in clinical settings for the effective screening and diagnosis of cervical diseases.

Tao Xu, Pengchuan Zhang, Qiuyuan Huang et al.

In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation. With a novel attentional generative network, the AttnGAN can synthesize fine-grained details at different subregions of the image by paying attentions to the relevant words in the natural language description. In addition, a deep attentional multimodal similarity model is proposed to compute a fine-grained image-text matching loss for training the generator. The proposed AttnGAN significantly outperforms the previous state of the art, boosting the best reported inception score by 14.14% on the CUB dataset and 170.25% on the more challenging COCO dataset. A detailed analysis is also performed by visualizing the attention layers of the AttnGAN. It for the first time shows that the layered attentional GAN is able to automatically select the condition at the word level for generating different parts of the image.

Han Zhang, Tao Xu, Hongsheng Li et al.

Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images. First, we propose a two-stage generative adversarial network architecture, StackGAN-v1, for text-to-image synthesis. The Stage-I GAN sketches the primitive shape and colors of the object based on given text description, yielding low-resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high-resolution images with photo-realistic details. Second, an advanced multi-stage generative adversarial network architecture, StackGAN-v2, is proposed for both conditional and unconditional generative tasks. Our StackGAN-v2 consists of multiple generators and discriminators in a tree-like structure; images at multiple scales corresponding to the same scene are generated from different branches of the tree. StackGAN-v2 shows more stable training behavior than StackGAN-v1 by jointly approximating multiple distributions. Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.