3D human motion generation has seen substantial advancement in recent years. While state-of-the-art approaches have improved performance significantly, they still struggle with complex and detailed motions unseen in training data, largely due to the scarcity of motion datasets and the prohibitive cost of generating new training examples. To address these challenges, we introduce CoMA, an agent-based solution for complex human motion generation, editing, and comprehension. CoMA leverages multiple collaborative agents powered by large language and vision models, alongside a mask transformer-based motion generator featuring body part-specific encoders and codebooks for fine-grained control. Our framework enables generation of both short and long motion sequences with detailed instructions, text-guided motion editing, and self-correction for improved quality. Evaluations on the HumanML3D dataset demonstrate competitive performance against state-of-the-art methods. Additionally, we create a set of context-rich, compositional, and long text prompts, where user studies show our method significantly outperforms existing approaches.

Artificial intelligence is rapidly transforming biomedical imaging, from tumor segmentation to multimodal diagnosis, but reliable deployment in hospitals remains a pressing challenge. Models often struggle with limited labeled data, fail to generalize across scanners and institutions, and lack theoretical guarantees needed for safety-critical decisions. In this talk, I will present our research on overcoming these challenges. I will discuss label-efficient and class-imbalanced learning methods that make effective use of large-scale unlabeled data, theoretical frameworks that embed statistical principles into deep learning for stability and reliability, and medical foundation models that provide universal anatomical priors with lightweight refinement for diverse clinical settings. Together, these advances move biomedical AI beyond benchmark performance toward systems that are robust, generalizable, and clinically actionable.

Head movement poses a significant challenge in brain positron emission tomography (PET) imaging, resulting in image artifacts and tracer uptake quantification inaccuracies. Effective head motion estimation and correction are crucial for precise quantitative image analysis and accurate diagnosis of neurological disorders. Hardware-based motion tracking (HMT) has limited applicability in real-world clinical practice. To overcome this limitation, we propose a deep-learning head motion correction approach with cross-attention (DL-HMC++) to predict rigid head motion from one-second 3D PET raw data. DL-HMC++ is trained in a supervised manner by leveraging existing dynamic PET scans with gold-standard motion measurements from external HMT. We evaluate DL-HMC++ on two PET scanners (HRRT and mCT) and four radiotracers (18F-FDG,18F-FPEB,11C-UCB-J, and11C-LSN3172176) to demonstrate the effectiveness and generalization of the approach in large cohort PET studies. Quantitative and qualitative results demonstrate that DL-HMC++ consistently outperforms state-of-the-art data-driven motion estimation methods, producing motion-free images with clear delineation of brain structures and reduced motion artifacts that are indistinguishable from gold-standard HMT. Brain region of interest standard uptake value analysis exhibits average difference ratios between DL-HMC++ and gold-standard HMT to be 1.2±0.5% for HRRT and 0.5±0.2% for mCT. DL-HMC++ demonstrates the potential for data-driven PET head motion correction to remove the burden of HMT, making motion correction accessible to clinical populations beyond research settings. The code is available at https://github.com/maxxxxxxcai/DL-HMC-TMI.

Despite the remarkable successes of Large Language Models (LLMs), the underlying Transformer architecture has inherent limitations in handling complex reasoning tasks.Chainof-Thought (CoT) prompting has emerged as a practical workaround, but most CoT-based methods rely on a single generic prompt like "think step by step," with no task-specific adaptation.These approaches expect the model to discover an effective reasoning path on its own, forcing it to search through a vast prompt space.In contrast, many work has explored task-specific prompt designs to boost performance.However, these designs are typically developed through trial and error, lacking a theoretical ground.As a result, prompt engineering remains largely ad hoc and unguided.In this paper, we provide a theoretical framework that explains why some prompts succeed while others fail.We show that prompts function as selectors, extracting specific task-relevant information from the model's full hidden state during CoT reasoning.Each prompt defines a unique trajectory through the answer space, and the choice of this trajectory is crucial for task performance and future navigation in the answer space.We analyze the complexity of finding optimal prompts and the size of the prompt space for a given task.Our theory reveals principles behind effective prompt design and shows that naive CoT-using model-selfguided prompt like "think step by step" -can severely hinder performance.Showing that optimal prompt search can lead to over a 50% improvement on reasoning tasks through experiments, our work provide a theoretical foundation for prompt engineering.

Recent advances in large language models (LLMs) have demonstrated significant promise in document understanding and questionanswering.Despite the progress, existing approaches can only process short documents due to limited context length or fail to fully leverage multi-modal information.In this work, we introduce DocAgent, a multi-agent framework for long-context document understanding that imitates the human reading practice.Specifically, we first extract a structured, tree-formatted outline from documents to help agents identify relevant sections efficiently.Further, we develop an interactive reading interface that enables agents to query and retrieve various types of content dynamically.To ensure answer reliability, we introduce a reviewer agent that cross-checks responses using complementary sources and maintains a task-agnostic memory bank to facilitate knowledge sharing across tasks.We evaluate our method on two long-context document understanding benchmarks, where it bridges the gap to human-level performance by surpassing competitive baselines, while maintaining a short context length.Our code is available at https://github.com/lisun-ai/DocAgent.

While multi-step diffusion models have advanced both forward and inverse rendering, existing approaches often treat these problems independently, leading to cycle inconsistency and slow inference speed. In this work, we present Ouroboros, a framework composed of two single-step diffusion models that handle forward and inverse rendering with mutual reinforcement. Our approach extends intrinsic decomposition to both indoor and outdoor scenes and introduces a cycle consistency mechanism that ensures coherence between forward and inverse rendering outputs. Experimental results demonstrate state-of-the-art performance across diverse scenes while achieving substantially faster inference speed compared to other diffusion-based methods. We also demonstrate that Ouroboros can transfer to video decomposition in a training-free manner, reducing temporal inconsistency in video sequences while maintaining high-quality per-frame inverse rendering.

Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learning (MRL) recently emerged as a solution for adaptive embedding lengths, but it requires full model retraining and suffers from noticeable performance degradations at short lengths. In this paper, we show that sparse coding offers a compelling alternative for achieving adaptive representation with minimal overhead and higher fidelity. We propose Contrastive Sparse Representation (CSR), a method that specifies pre-trained embeddings into a high-dimensional but selectively activated feature space. By leveraging lightweight autoencoding and task-aware contrastive objectives, CSR preserves semantic quality while allowing flexible, cost-effective inference at different sparsity levels. Extensive experiments on image, text, and multimodal benchmarks demonstrate that CSR consistently outperforms MRL in terms of both accuracy and retrieval speed—often by large margins—while also cutting training time to a fraction of that required by MRL. Our results establish sparse coding as a powerful paradigm for adaptive representation learning in real-world applications where efficiency and fidelity are both paramount. Code is available at this URL.

Dehai Min, Zhiyang Xu, Guilin Qi, Lifu Huang, Chenyu You. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

The synthesis of realistic Martian landscape videos, essential for mission rehearsal and robotic simulation, presents unique challenges. These primarily stem from the scarcity of high-quality Martian data and the significant domain gap relative to terrestrial imagery.To address these challenges, we introduce a holistic solution comprising two main components: 1) a data curation framework, Multimodal Mars Synthesis (M3arsSynth), which processes stereo navigation images to render high-fidelity 3D video sequences. 2) a video-based Martian terrain generator (MarsGen), that utilizes multimodal conditioning data to accurately synthesize novel, 3D-consistent frames. Our data are sourced from NASA’s Planetary Data System (PDS), covering diverse Martian terrains and dates, enabling the production of physics-accurate 3D surface models at metric-scale resolution. During inference, MarsGen is conditioned on an initial image frame and can be guided by specified camera trajectories or textual prompts to generate new environments.Experimental results demonstrate that our solution surpasses video synthesis approaches trained on terrestrial data, achieving superior visual quality and 3D structural consistency.

Magnetic Resonance Spectroscopic Imaging (MRSI) is a non-invasive imaging technique for studying metabolism and has become a crucial tool for understanding neurological diseases , cancers and diabetes. High spatial resolution MRSI is needed to characterize lesions, but in practice MRSI is acquired at low resolution due to time and sensitivity restrictions caused by the low metabolite concentrations. Therefore, there is an imperative need for a post-processing approach to generate high-resolution MRSI from low-resolution data that can be acquired fast and with high sensitivity. Deep learning-based super-resolution methods provided promising results for improving the spatial resolution of MRSI, but they still have limited capability to generate accurate and high-quality images. Recently, diffusion models have demonstrated superior learning capability than other generative models in various tasks, but sampling from diffusion models requires iterating through a large number of diffusion steps, which is time-consuming. This work introduces a Flow-based Truncated Denoising Diffusion Model (FTDDM) for super-resolution MRSI, which shortens the diffusion process by truncating the diffusion chain, and the truncated steps are estimated using a normalizing flow-based network. The network is conditioned on upscaling factors to enable multi-scale super-resolution. To train and evaluate the deep learning models, we developed a 1 H-MRSI dataset acquired from 25 high-grade glioma patients. We demonstrate that FTDDM outperforms existing generative models while speeding up the sampling process by over 9-fold compared to the baseline diffusion model. Neuroradiologists’ evaluations confirmed the clinical advantages of our method, which also supports uncertainty estimation and sharpness adjustment, extending its potential clinical applications.

In natural language generation, language models, particularly those based on decoder-only architectures as in popular Large Language Models (LLMs), have demonstrated impressive performance across a wide range of tasks. However, encoder-decoder architectures remain highly effective for tasks involving non-text data, such as images and time-series data. The decoder relies on the attention mechanism to efficiently extract information from the encoder. While it is common practice to draw information from only the last encoder layer, this might lead to insufficient training of the encoder layer stack due to the hierarchy bypassing problem. In this work, we propose layer-wise multi-view decoding for improved encoder-decoder language models, where for each decoder layer, together with the representations from the last encoder layer, which serve as a global view, those from other encoder layers are supplemented for a stereoscopic view of the source inputs. Systematic experiments and analyses show that we successfully address the hierarchy bypassing problem, require almost negligible parameter increase, and improve the performance of sequence learning with deep representations on diverse tasks, i.e., machine translation, abstractive summarization, image captioning, video captioning, medical report generation, and paraphrase generation. In particular, our approach achieves new state-of-the-art results on benchmark datasets, including a low-resource machine translation dataset and low-resource medical report generation datasets.

Recent developments underscore the potential of textual information in enhancing learning models for a deeper understanding of medical visual semantics. However, language-guided medical image segmentation still faces a challenging issue. Previous works employ implicit architectures to embed textual information. This leads to segmentation results that are inconsistent with the semantics represented by the language, sometimes even diverging significantly. To this end, we propose a novel cross-modal conditioned Reconstruction for Language-guided Medical Image Segmentation (RecLMIS) to explicitly capture cross-modal interactions, which assumes that well-aligned medical visual features and medical notes can effectively reconstruct each other. We introduce conditioned interaction to adaptively predict patches and words of interest. Subsequently, they are utilized as conditioning factors for mutual reconstruction to align with regions described in the medical notes. Extensive experiments demonstrate the superiority of our RecLMIS, surpassing LViT by 3.74% mIoU on the MosMedData+ dataset and 1.89% mIoU on the QATA-CoV19 dataset. More importantly, we achieve a relative reduction of 20.2% in parameter count and a 55.5% decrease in computational load. The code will be available at https://github.com/ShawnHuang497/RecLMIS.

Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive and computationally costly. Additionally, these tuned models tend to become highly specialized, limiting their practicality for real-world deployment; (ii) recent studies indicate that pre-trained vision-language classifiers may overly depend on spurious features - patterns that correlate with the target in training data, but are not related to the true labeling function; and (iii) existing studies on mitigating the reliance on spurious features, largely based on the assumption that we can identify such features, does not provide definitive assurance for real-world applications. As a piloting study, this work focuses on exploring mitigating the reliance on spurious features for CLIP without using any group annotation. To this end, we systematically study the existence of spurious correlation on CLIP and CLIP+ERM. We first, following recent work on Deep Feature Reweighting (DFR), verify that last-layer retraining can greatly improve group robustness on pretrained CLIP. In view of them, we advocate a lightweight representation calibration method for fine-tuning CLIP, by first generating a calibration set using the pretrained CLIP, and then calibrating representations of samples within this set through contrastive learning, all without the need for group labels. Extensive experiments and in-depth visualizations on several benchmarks validate the effectiveness of our proposals, largely reducing reliance and significantly boosting the model generalization. Our codes will be available in here.

Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. Albeit achieving remarkable success, existing COD detectors still struggle to obtain precise results in some challenging cases. To handle this problem, we draw inspiration from the prey-vs-predator game that leads preys to develop better camouflage and predators to acquire more acute vision systems and develop algorithms from both the prey side and the predator side. On the prey side, we propose an adversarial training framework, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect. Camouflageator trains the generator and detector in an adversarial way such that the enhanced auxiliary generator helps produce a stronger detector. On the predator side, we introduce a novel COD method, called Internal Coherence and Edge Guidance (ICEG), which introduces a camouflaged feature coherence module to excavate the internal coherence of camouflaged objects, striving to obtain more complete segmentation results. Additionally, ICEG proposes a novel edge-guided separated calibration module to remove false predictions to avoid obtaining ambiguous boundaries. Extensive experiments show that ICEG outperforms existing COD detectors and Camouflageator is flexible to improve various COD detectors, including ICEG, which brings state-of-the-art COD performance.

Structural Entropy (SE) measures the structural information contained in a graph. Minimizing or maximizing SE helps to reveal or obscure the intrinsic structural patterns underlying graphs in an interpretable manner, finding applications in various tasks driven by networked data. However, SE ignores the heterogeneity inherent in the graph relations, which is ubiquitous in modern networks. In this work, we extend SE to consider heterogeneous relations and propose the first metric for multi-relational graph structural information, namely, Multi-relational Structural Entropy (MrSE). To this end, we first cast SE through the novel lens of the stationary distribution from random surfing, which readily extends to multi-relational networks by considering the choices of both nodes and relation types simultaneously at each step. The resulting MrSE is then optimized by a new greedy algorithm to reveal the essential structures within a multi-relational network. Experimental results highlight that the proposed MrSE offers a more insightful interpretation of the structure of multi-relational graphs compared to SE. Additionally, it enhances the performance of two tasks that involve real-world multi-relational graphs, including node clustering and social event detection.

Deep Implicit Functions (DIFs) have gained popularity in 3D computer vision due to their compactness and continuous representation capabilities. However, addressing dense correspondences and semantic relationships across DIF-encoded shapes remains a critical challenge, limiting their applications in texture transfer and shape analysis. Moreover, recent endeavors in 3D shape generation using DIFs often neglect correspondence and topology preservation. This paper presents HNDF (Hybrid Neural Diffeomorphic Flow), a method that implicitly learns the underlying representation and decomposes intricate dense correspondences into explicitly axis-aligned triplane features. To avoid suboptimal representations trapped in local minima, we propose hybrid supervision that captures both local and global correspondences. Unlike conventional approaches that directly generate new 3D shapes, we further explore the idea of shape generation with deformed template shape via diffeomorphic flows, where the deformation is encoded by the generated triplane features. Leveraging a pre-existing 2D diffusion model, we produce high-quality and diverse 3D diffeomorphic flows through generated triplanes features, ensuring topological consistency with the template shape. Extensive experiments on medical image organ segmentation datasets evaluate the effectiveness of HNDF in 3D shape representation and generation.

The Segmentation Anything Model (SAM) has demonstrated effectiveness in various segmentation tasks. However, its application to 3D medical data has posed challenges due to its inherent design for both 2D and natural images. While there have been attempts to apply SAM to medical images on a slice-by-slice basis, the outcomes have been less than optimal. In this study, we introduce AFTer-SAM, an adaptation of SAM designed for volumetric medical image segmentation. By incorporating an Axial Fusion Transformer, AFTer-SAM is capable of capturing both intra-slice details and inter-slice contextual information, essential for accurate medical image segmentation. Given the potential computational challenges of training this enhanced model, we utilize Low-Rank Adaptation (LoRA) to efficiently finetune the weights of the Axial Fusion Transformer. This ensures a streamlined training process without compromising on performance. Our results indicate that AFTer-SAM offers significant improvements in volumetric medical image segmentation, suggesting a promising direction for the application of large pre-trained models in medical imaging.

Image registration is an essential step in many medical image analysis tasks. Traditional methods for image registration are primarily optimization-driven, finding the optimal deformations that maximize the similarity between two images. Recent learning-based methods, trained to directly predict transformations between two images, run much faster, but suffer from performance deficiencies due to domain shift. Here we present a new neural network based image registration framework, called NIR (Neural Image Registration), which is based on optimization but utilizes deep neural networks to model deformations between image pairs. NIR represents the transformation between two images with a continuous function implemented via neural fields, receiving a 3D coordinate as input and outputting the corresponding deformation vector. NIR provides two ways of generating deformation field: directly output a displacement vector field for general deformable registration, or output a velocity vector field and integrate the velocity field to derive the deformation field for diffeomorphic image registration. The optimal registration is discovered by updating the parameters of the neural field via stochastic mini-batch gradient descent. We describe several design choices that facilitate model optimization, including coordinate encoding, sinusoidal activation, coordinate sampling, and intensity sampling. NIR is evaluated on two 3D MR brain scan datasets, demonstrating highly competitive performance in terms of both registration accuracy and regularity. Compared to traditional optimization-based methods, our approach achieves better results in shorter computation times. In addition, our methods exhibit performance on a cross-dataset registration task, compared to the pre-trained learning-based methods.

Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus on instance discrimination and invariant mapping (i.e., pulling positive samples closer and negative samples apart in the feature space). However, they face three common pitfalls: (1) tailness: medical image data usually follows an implicit long-tail class distribution. Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent anatomical features due to the intra-class variations between different anatomical features; and (3) diversity: the intra-slice correlations within the entire dataset have received significantly less attention. This motivates us to seek a principled approach for strategically making use of the dataset itself to discover similar yet distinct samples from different anatomical views. In this paper, we introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owNAnatomy (MONA), and make three contributions. First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features, mainly due to lacking the supervision signal. We show two simple solutions towards learning invariances-through the use of stronger data augmentations and nearest neighbors. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features in an unsupervised manner. Lastly, we both empirically and theoretically, demonstrate the efficacy of our MONA on three benchmark datasets with different labeled settings, achieving new state-of-the-art under different labeled semi-supervised settings. MONA makes minimal assumptions on domain expertise, and hence constitutes a practical and versatile solution in medical image analysis. We provide the PyTorch-like pseudo-code in supplementary.

Unsupervised Domain Adaptation (UDA), which aligns the labeled source distribution to the unlabeled target distribution, has shown remarkable achievement in the medical image segmentation task. Previous UDA methods unilaterally consider the global distribution alignment through explicit category-based loss while good separation and discrimination of class are insufficiently explored, resulting in the sub-aligned distribution across domains. In this paper, we propose cross-prototype contrastive learning method (CPCL) for UDA segmentation through class centroid alignment. Specifically, to reduce the intra-class distance and increase the inter-class distance, we first introduce prototype-feature contrastive learning to align the pixel-level features and the same-class global prototype across domains. Secondly, we further present prototype-prototype contrastive learning to align the same class prototypes between the source domain and target domain for compact category centroid and better global domain distribution alignment. Extensive experiments on two public cardiac datasets demonstrate that the proposed CPCL achieves superior domain adaptation performance as compared with the state-of-the-art.

Transformer-based sequential recommendation (SR) has been booming in recent years, with the self-attention mechanism as its key component. Self-attention has been widely believed to be able to effectively select those informative and relevant items from a sequence of interacted items for next-item prediction via learning larger attention weights for these items. However, this may not always be true in reality. Our empirical analysis of some representative Transformer-based SR models reveals that it is not uncommon for large attention weights to be assigned to less relevant items, which can result in inaccurate recommendations. Through further in-depth analysis, we find two factors that may contribute to such inaccurate assignment of attention weights:sub-optimal position encoding andnoisy input. To this end, in this paper, we aim to address this significant yet challenging gap in existing works. To be specific, we propose a simple yet effective framework called Attention Calibration for Transformer-based Sequential Recommendation (AC-TSR). In AC-TSR, a novel spatial calibrator and adversarial calibrator are designed respectively to directly calibrates those incorrectly assigned attention weights. The former is devised to explicitly capture the spatial relationships (i.e., order and distance) among items for more precise calculation of attention weights. The latter aims to redistribute the attention weights based on each item's contribution to the next-item prediction. AC-TSR is readily adaptable and can be seamlessly integrated into various existing transformer-based SR models. Extensive experimental results on four benchmark real-world datasets demonstrate the superiority of our proposed AC-TSR via significant recommendation performance enhancements. The source code is available at https://github.com/AIM-SE/AC-TSR.

Recent advancements in large language models (LLMs) have transformed the field of question answering (QA). However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam, sourced from the Chinese National Medical Licensing Examination. CMExam consists of 60K+ multiple-choice questions for standardized and objective evaluations, as well as solution explanations for model reasoning evaluation in an open-ended manner. For in-depth analyses of LLMs, we invited medical professionals to label five additional question-wise annotations, including disease groups, clinical departments, medical disciplines, areas of competency, and question difficulty levels. Alongside the dataset, we further conducted thorough experiments with representative LLMs and QA algorithms on CMExam. The results show that GPT-4 had the best accuracy of 61.6% and a weighted F1 score of 0.617. These results highlight a great disparity when compared to human accuracy, which stood at 71.6%. For explanation tasks, while LLMs could generate relevant reasoning and demonstrate improved performance after finetuning, they fall short of a desired standard, indicating ample room for improvement. To the best of our knowledge, CMExam is the first Chinese medical exam dataset to provide comprehensive medical annotations. The experiments and findings of LLM evaluation also provide valuable insights into the challenges and potential solutions in developing Chinese medical QA systems and LLM evaluation pipelines.

For medical image segmentation, contrastive learning is the dominant practice to improve the quality of visual representations by contrasting semantically similar and dissimilar pairs of samples. This is enabled by the observation that without accessing ground truth labels, negative examples with truly dissimilar anatomical features, if sampled, can significantly improve the performance. In reality, however, these samples may come from similar anatomical features and the models may struggle to distinguish the minority tail-class samples, making the tail classes more prone to misclassification, both of which typically lead to model collapse. In this paper, we propose $\texttt{ARCO}$, a semi-supervised contrastive learning (CL) framework with stratified group theory for medical image segmentation. In particular, we first propose building $\texttt{ARCO}$ through the concept of variance-reduced estimation, and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks with extremely limited labels. Furthermore, we theoretically prove these sampling techniques are universal in variance reduction. Finally, we experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings, and our methods consistently outperform state-of-the-art semi-supervised methods. Additionally, we augment the CL frameworks with these sampling techniques and demonstrate significant gains over previous methods. We believe our work is an important step towards semi-supervised medical image segmentation by quantifying the limitation of current self-supervision objectives for accomplishing such challenging safety-critical tasks.

Recommendation systems suffer in the strict cold-start (SCS) scenario, where the user-item interactions are entirely unavailable. The well-established, dominating identity (ID)-based approaches completely fail to work. Cold-start recommenders, on the other hand, leverage item contents (brand, title, descriptions, etc.) to map the new items to the existing ones. However, the existing SCS recommenders explore item contents in coarse-grained manners that introduce noise or information loss. Moreover, informative data sources other than item contents, such as users’ purchase sequences and review texts, are largely ignored. In this work, we explore the role of the fine-grained item attributes in bridging the gaps between the existing and the SCS items and pre-train a knowledgeable item-attribute graph for SCS item recommendation. Our proposed framework, ColdGPT, models item-attribute correlations into an item-attribute graph by extracting fine-grained attributes from item contents. ColdGPT then transfers knowledge into the item-attribute graph from various available data sources, i.e., item contents, historical purchase sequences, and review texts of the existing items, via multi-task learning. To facilitate the positive transfer, ColdGPT designs specific submodules according to the natural forms of the data sources and proposes to coordinate the multiple pre-training tasks via unified alignment-and-uniformity losses. Our pre-trained item-attribute graph acts as an implicit, extendable item embedding matrix, which enables the SCS item embeddings to be easily acquired by inserting these items into the item-attribute graph and propagating their attributes’ embeddings. We carefully process three public datasets, i.e., Yelp, Amazon-home, and Amazon-sports, to guarantee the SCS setting for evaluation. Extensive experiments show that ColdGPT consistently outperforms the existing SCS recommenders by large margins and even surpasses models that are pre-trained on 75 - 224 times more, cross-domain data on two out of four datasets. Our code and pre-processed datasets for SCS evaluations are publicly available to help future SCS studies.

Diffeomorphic image registration, offering smooth transformation and topology preservation, is required in many medical image analysis tasks. Traditional methods impose certain modeling constraints on the space of admissible transformations and use optimization to find the optimal transformation between two images. Specifying the right space of admissible transformations is challenging: the registration quality can be poor if the space is too restrictive, while the optimization can be hard to solve if the space is too general. Recent learning-based methods, utilizing deep neural networks to learn the transformation directly, achieve fast inference, but face challenges in accuracy due to the difficulties in capturing the small local deformations and generalization ability. Here we propose a new optimization-based method named DNVF (Diffeomorphic Image Registration with Neural Velocity Field) which utilizes deep neural network to model the space of admissible transformations. A multilayer perceptron (MLP) with sinusoidal activation function is used to represent the continuous velocity field and assigns a velocity vector to every point in space, providing the flexibility of modeling complex deformations as well as the convenience of optimization. Moreover, we propose a cascaded image registration framework (Cas-DNVF) by combining the benefits of both optimization and learning based methods, where a fully convolutional neural network (FCN) is trained to predict the initial deformation, followed by DNVF for further refinement. Experiments on two large-scale 3D MR brain scan datasets demonstrate that our proposed methods significantly outperform the state-of-the-art registration methods.

Advances in self-supervised learning have drawn attention to developing techniques to extract effective visual representations from unlabeled images. Contrastive learning (CL) trains a model to extract consistent features by generating different views. Recent success of Masked Autoencoders (MAE) highlights the benefit of generative modeling in self-supervised learning. The generative approaches encode the input into a compact embedding and empower the model’s ability of recovering the original input. However, in our experiments, we found vanilla MAE mainly recovers coarse high level semantic information and is inadequate in recovering detailed low level information. We show that in dense downstream prediction tasks like multi-organ segmentation, directly applying MAE is not ideal. Here, we propose RepRec, a hybrid visual representation learning framework for self-supervised pre-training on large-scale unlabelled medical datasets, which takes advantage of both contrastive and generative modeling. To solve the aforementioned dilemma that MAE encounters, a convolutional encoder is pre-trained to provide low-level feature information, in a contrastive way; and a transformer encoder is pre-trained to produce high level semantic dependency, in a generative way – by recovering masked representations from the convolutional encoder. Extensive experiments on three multi-organ segmentation datasets demonstrate that our method outperforms current state-of-the-art methods.

Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted combinatorial features of graphs. In recent years, graph neural networks (GNNs) have become the state-of-the-art method in downstream graph-related tasks due to their superior performance. Most GNNs are based on Message Passing Neural Network (MPNN) frameworks. However, recent studies show that MPNNs can not exceed the power of the Weisfeiler-Lehman (WL) algorithm in graph isomorphism test. To address the limitations of existing graph kernel and GNN methods, in this paper, we propose a novel GNN framework, termed Kernel Graph Neural Networks (KerGNNs), which integrates graph kernels into the message passing process of GNNs. Inspired by convolution filters in convolutional neural networks (CNNs), KerGNNs adopt trainable hidden graphs as graph filters which are combined with subgraphs to update node embeddings using graph kernels. In addition, we show that MPNNs can be viewed as special cases of KerGNNs. We apply KerGNNs to multiple graph-related tasks and use cross-validation to make fair comparisons with benchmarks. We show that our method achieves competitive performance compared with existing state-of-the-art methods, demonstrating the potential to increase the representation ability of GNNs. We also show that the trained graph filters in KerGNNs can reveal the local graph structures of the dataset, which significantly improves the model interpretability compared with conventional GNN models.

Gene Ontology (GO) is the primary gene function knowledge base that enables computational tasks in biomedicine. The basic element of GO is a term, which includes a set of genes with the same function. Existing research efforts of GO mainly focus on predicting gene term associations. Other tasks, such as generating descriptions of new terms, are rarely pursued. In this paper, we propose a novel task: GO term description generation. This task aims to automatically generate a sentence that describes the function of a GO term belonging to one of the three categories, i.e., molecular function, biological process, and cellular component. To address this task, we propose a Graph-in-Graph network that can efficiently leverage the structural information of GO. The proposed network introduces a two-layer graph: the first layer is a graph of GO terms where each node is also a graph (gene graph). Such a Graph-in-Graph network can derive the biological functions of GO terms and generate proper descriptions. To validate the effectiveness of the proposed network, we build three large-scale benchmark datasets. By incorporating the proposed Graph-in-Graph network, the performances of seven different sequence-to-sequence models can be substantially boosted across all evaluation metrics, with up to 34.7%, 14.5%, and 39.1% relative improvements in BLEU, ROUGE-L, and METEOR, respectively.

The "Patient Instruction" (PI), which contains critical instructional information provided both to carers and to the patient at the time of discharge, is essential for the patient to manage their condition outside hospital. An accurate and easy-to-follow PI can improve the self-management of patients which can in turn reduce hospital readmission rates. However, writing an appropriate PI can be extremely time consuming for physicians, and is subject to being incomplete or error-prone for (potentially overworked) physicians. Therefore, we propose a new task that can provide an objective means of avoiding incompleteness, while reducing clinical workload: the automatic generation of the PI, which is imagined as being a document that the clinician can review, modify, and approve as necessary (rather than taking the human "out of the loop"). We build a benchmark clinical dataset and propose the Re$^3$Writer, which imitates the working patterns of physicians to first retrieve related working experience from historical PIs written by physicians, then reason related medical knowledge. Finally, it refines the retrieved working experience and reasoned medical knowledge to extract useful information, which is used to generate the PI for previously-unseen patient according to their health records during hospitalization. Our experiments show that, using our method, the performance of 6 different models can be substantially boosted across all metrics, with up to 20%, 11%, and 19% relative improvements in BLEU-4, ROUGE-L, and METEOR, respectively. Meanwhile, we show results from human evaluations to measure the effectiveness in terms of its usefulness for clinical practice. The code is available at https://github.com/AI-in-Health/Patient-Instructions.

Transformers have made remarkable progress towards modeling long-range dependencies within the medical image analysis domain. However, current transformer-based models suffer from several disadvantages: (1) existing methods fail to capture the important features of the images due to the naive tokenization scheme; (2) the models suffer from information loss because they only consider single-scale feature representations; and (3) the segmentation label maps generated by the models are not accurate enough without considering rich semantic contexts and anatomical textures. In this work, we present CASTformer, a novel type of adversarial transformers, for 2D medical image segmentation. First, we take advantage of the pyramid structure to construct multi-scale representations and handle multi-scale variations. We then design a novel class-aware transformer module to better learn the discriminative regions of objects with semantic structures. Lastly, we utilize an adversarial training strategy that boosts segmentation accuracy and correspondingly allows a transformer-based discriminator to capture high-level semantically correlated contents and low-level anatomical features. Our experiments demonstrate that CASTformer dramatically outperforms previous state-of-the-art transformer-based approaches on three benchmarks, obtaining 2.54%-5.88% absolute improvements in Dice over previous models. Further qualitative experiments provide a more detailed picture of the model’s inner workings, shed light on the challenges in improved transparency, and demonstrate that transfer learning can greatly improve performance and reduce the size of medical image datasets in training, making CASTformer a strong starting point for downstream medical image analysis tasks.

Space-time video super-resolution (STVSR) aims to construct a high space-time resolution video sequence from the corresponding low-frame-rate, low-resolution video sequence. Inspired by the recent success to consider spatial-temporal information for space-time super-resolution, our main goal in this work is to take full considerations of spatial and temporal correlations within the video sequences of fast dynamic events. To this end, we propose a novel one-stage memory enhanced graph attention network (MEGAN) for space-time video super-resolution. Specifically, we build a novel long-range memory graph aggregation (LMGA) module to dynamically capture correlations along the channel dimensions of the feature maps and adaptively aggregate channel features to enhance the feature representations. We introduce a non-local residual block, which enables each channel-wise feature to attend global spatial hierarchical features. In addition, we adopt a progressive fusion module to further enhance the representation ability by extensively exploiting spatial-temporal correlations from multiple frames. Experiment results demonstrate that our method achieves better results compared with the state-of-the-art methods quantitatively and visually.

Training supervised video captioning model requires coupled video-caption pairs. However, for many targeted languages, sufficient paired data are not available. To this end, we introduce the unpaired video captioning task aiming to train models without coupled video-caption pairs in target language. To solve the task, a natural choice is to employ a two-step pipeline system: first utilizing video-to-pivot captioning model to generate captions in pivot language and then utilizing pivot-to-target translation model to translate the pivot captions to the target language. However, in such a pipeline system, 1) visual information cannot reach the translation model, generating visual irrelevant target captions; 2) the errors in the generated pivot captions will be propagated to the translation model, resulting in disfluent target captions. To address these problems, we propose the Unpaired Video Captioning with Visual Injection system (UVC-VI). UVC-VI first introduces the Visual Injection Module (VIM), which aligns source visual and target language domains to inject the source visual information into the target language domain. Meanwhile, VIM directly connects the encoder of the video-to-pivot model and the decoder of the pivot-to-target model, allowing end-to-end inference by completely skipping the generation of pivot captions. To enhance the cross-modality injection of the VIM, UVC-VI further introduces a pluggable video encoder, i.e., Multimodal Collaborative Encoder (MCE). The experiments show that UVC-VI outperforms pipeline systems and exceeds several supervised systems. Furthermore, equipping existing supervised systems with our MCE can achieve 4% and 7% relative margins on the CIDEr scores to current state-of-the-art models on the benchmark MSVD and MSR-VTT datasets, respectively.

Automated segmentation in medical image analysis is a challenging task that requires a large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited manually annotated medical data, which poses a major practical problem for accurate and robust medical image segmentation. In addition, most existing semi-supervised approaches are usually not robust compared with the supervised counterparts, and also lack explicit modeling of geometric structure and semantic information, both of which limit the segmentation accuracy. In this work, we present SimCVD, a simple contrastive distillation framework that significantly advances state-of-the-art voxel-wise representation learning. We first describe an unsupervised training strategy, which takes two views of an input volume and predicts their signed distance maps of object boundaries in a contrastive objective, with only two independent dropout as mask. This simple approach works surprisingly well, performing on the same level as previous fully supervised methods with much less labeled data. We hypothesize that dropout can be viewed as a minimal form of data augmentation and makes the network robust to representation collapse. Then, we propose to perform structural distillation by distilling pair-wise similarities. We evaluate SimCVD on two popular datasets: the Left Atrial Segmentation Challenge (LA) and the NIH pancreas CT dataset. The results on the LA dataset demonstrate that, in two types of labeled ratios (i.e., 20% and 10%), SimCVD achieves an average Dice score of 90.85% and 89.03% respectively, a 0.91% and 2.22% improvement compared to previous best results. Our method can be trained in an end-to-end fashion, showing the promise of utilizing SimCVD as a general framework for downstream tasks, such as medical image synthesis, enhancement, and registration.

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from the final encoder layer which generates the coarse-grained representations of the source sequences, i.e., passage and question. Previous studies have shown that the representation of source sequence becomes more coarse-grained from fine-grained as the encoding layer increases. It is generally believed that with the growing number of layers in deep neural networks, the encoding process will gather relevant information for each location increasingly, resulting in more coarse-grained representations, which adds the likelihood of similarity to other locations (referring to homogeneity). Such a phenomenon will mislead the model to make wrong judgments so as to degrade the performance. To this end, we propose a novel approach called Adaptive Bidirectional Attention, which adaptively exploits the source representations of different levels to the predictor. Experimental results on the benchmark dataset, SQuAD 2.0 demonstrate the effectiveness of our approach, and the results are better than the previous state-of-the-art model by 2.5% EM and 2.3% F1 scores.

Spoken question answering (SQA) is a challenging task that requires the machine to fully understand the complex spoken documents. Automatic speech recognition (ASR) plays a significant role in the development of QA systems. However, the recent work shows that ASR systems generate highly noisy transcripts, which critically limit the capability of machine comprehension on the SQA task. To address the issue, we present a novel distillation framework. Specifically, we devise a training strategy to perform knowledge distillation (KD) from spoken documents and written counterparts. Our work aims at distilling rich knowledge from the language model to improve the performance of the student model by reducing the misalignment between automatic and manual transcripts. Experiments demonstrate that our approach outperforms several state-of-the-art language models on the Spoken-SQuAD dataset.

Spoken question answering (SQA) has recently drawn considerable attention in the speech community. It requires systems to find correct answers from the given spoken passages simultaneously. The common SQA systems consist of the automatic speech recognition (ASR) module and text-based question answering module. However, previous methods suffer from severe performance degradation due to ASR errors. To alleviate this problem, this work proposes a novel multi-modal residual knowledge distillation method (MRD-Net), which further distills knowledge at the acoustic level from the audio-assistant (Audio-A). Specifically, we utilize the teacher (T) trained on manual transcriptions to guide the training of the student (S) on ASR transcriptions. We also show that introducing an Audio-A helps this procedure by learning residual errors between T and S. Moreover, we propose a simple yet effective attention mechanism to adaptively leverage audio-text features as the new deep attention knowledge to boost the network performance. Extensive experiments demonstrate that the proposed MRD-Net achieves superior results compared with state-of-the-art methods on three spoken question answering benchmark datasets.

In spoken conversational question answering (SCQA), the answer to the corresponding question is generated by retrieving and then analyzing a fixed spoken document, including multi-part conversations. Most SCQA systems have considered only retrieving information from ordered utterances. However, the sequential order of dialogue is important to build a robust spoken conversational question answering system, and the changes of utterances order may severely result in low-quality and incoherent corpora. To this end, we introduce a self-supervised learning approach, including incoherence discrimination, insertion detection, and question prediction, to explicitly capture the coreference resolution and dialogue coherence among spoken documents. Specifically, we design a joint learning framework where the auxiliary self-supervised tasks can enable the pre-trained SCQA systems towards more coherent and meaningful spoken dialogue learning. We also utilize the proposed self-supervised learning tasks to capture intra-sentence coherence. Experimental results demonstrate that our proposed method provides more coherent, meaningful, and appropriate responses, yielding superior performance gains compared to the original pre-trained language models. Our method achieves state-of-the-art results on the Spoken-CoQA dataset.

Spoken conversational question answering (SCQA) requires machines to model complex dialogue flow given the speech utterances and text corpora. Different from traditional text question answering (QA) tasks, SCQA involves audio signal processing, passage comprehension, and contextual understanding. However, ASR systems introduce unexpected noisy signals to the transcriptions, which result in performance degradation on SCQA. To overcome the problem, we propose CADNet, a novel contextualized attention-based distillation approach, which applies both cross-attention and self-attention to obtain ASR-robust contextualized embedding representations of the passage and dialogue history for performance improvements. We also introduce the spoken conventional knowledge distillation framework to distill the ASR-robust knowledge from the estimated probabilities of the teacher model to the student. We conduct extensive experiments on the Spoken-CoQA dataset and demonstrate that our approach achieves remarkable performance in this task.

Medical report generation, which aims to automatically generate a long and coherent report of a given medical image, has been receiving growing research interests. Existing approaches mainly adopt a supervised manner and heavily rely on coupled image-report pairs. However, in the medical domain, building a large-scale image-report paired dataset is both time-consuming and expensive. To relax the dependency on paired data, we propose an unsupervised model Knowledge Graph Auto-Encoder (KGAE) which accepts independent sets of images and reports in training. KGAE consists of a pre-constructed knowledge graph, a knowledge-driven encoder and a knowledge-driven decoder. The knowledge graph works as the shared latent space to bridge the visual and textual domains; The knowledge-driven encoder projects medical images and reports to the corresponding coordinates in this latent space and the knowledge-driven decoder generates a medical report given a coordinate in this space. Since the knowledge-driven encoder and decoder can be trained with independent sets of images and reports, KGAE is unsupervised. The experiments show that the unsupervised KGAE generates desirable medical reports without using any image-report training pairs. Moreover, KGAE can also work in both semi-supervised and supervised settings, and accept paired images and reports in training. By further fine-tuning with image-report pairs, KGAE consistently outperforms the current state-of-the-art models on two datasets.

Segmenting cell nuclei within microscopy images is a ubiquitous task in biological research and clinical applications. Unfortunately, segmenting low-contrast overlapping objects that may be tightly packed is a major bottleneck in standard deep learning-based models. We report a Nuclear Segmentation Tool (NuSeT) based on deep learning that accurately segments nuclei across multiple types of fluorescence imaging data. Using a hybrid network consisting of U-Net and Region Proposal Networks (RPN), followed by a watershed step, we have achieved superior performance in detecting and delineating nuclear boundaries in 2D and 3D images of varying complexities. By using foreground normalization and additional training on synthetic images containing non-cellular artifacts, NuSeT improves nuclear detection and reduces false positives. NuSeT addresses common challenges in nuclear segmentation such as variability in nuclear signal and shape, limited training sample size, and sample preparation artifacts. Compared to other segmentation models, NuSeT consistently fares better in generating accurate segmentation masks and assigning boundaries for touching nuclei.

In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs. We also include the joint constraints in the loss function to facilitate structural preservation. In this process, we incorporate deep convolutional neural network (CNN), residual learning, and network in network techniques for feature extraction and restoration. In contrast to the current trend of increasing network depth and complexity to boost the imaging performance, we apply a parallel 1×1 CNN to compress the output of the hidden layer and optimize the number of layers and the number of filters for each convolutional layer. The quantitative and qualitative evaluative results demonstrate that our proposed model is accurate, efficient and robust for super-resolution (SR) image restoration from noisy LR input images. In particular, we validate our composite SR networks on three large-scale CT datasets, and obtain promising results as compared to the other state-of-the-art methods.