Yuan Gao

Dehua Zheng, Xiaochen Zheng, Laurence T. Yang et al.

Recent research about camouflaged object detection (COD) aims to segment highly concealed objects hidden in complex surroundings. The tiny, fuzzy camouflaged objects result in visually indistinguishable properties. However, current single-view COD detectors are sensitive to background distractors. Therefore, blurred boundaries and variable shapes of the camouflaged objects are challenging to be fully captured with a single-view detector. To overcome these obstacles, we propose a behavior-inspired framework, called Multi-view Feature Fusion Network (MFFN), which mimics the human behaviors of finding indistinct objects in images, i.e., observing from multiple angles, distances, perspectives. Specifically, the key idea behind it is to generate multiple ways of observation (multi-view) by data augmentation and apply them as inputs. MFFN captures critical boundary and semantic information by comparing and fusing extracted multi-view features. In addition, our MFFN exploits the dependence and interaction between views and channels. Specifically, our methods leverage the complementary information between different views through a two-stage attention module called Co-attention of Multi-view (CAMV). And we design a local-overall module called Channel Fusion Unit (CFU) to explore the channel-wise contextual clues of diverse feature maps in an iterative manner. The experiment results show that our method performs favorably against existing state-of-the-art methods via training with the same data. The code will be available at https://github.com/dwardzheng/MFFN_COD.

Xi Chen, Ali Ghadirzadeh, Tianhe Yu et al. · stanford

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic applications for which online data collection based on trial-and-error is costly and potentially unsafe. In practice, offline datasets are often heterogeneous, i.e., collected in a variety of scenarios, such as data from several human demonstrators or from policies that act with different purposes. Unfortunately, such datasets can exacerbate the distribution shift between the behavior policy underlying the data and the optimal policy to be learned, leading to poor performance. To address this challenge, we propose to leverage latent-variable policies that can represent a broader class of policy distributions, leading to better adherence to the training data distribution while maximizing reward via a policy over the latent variable. As we empirically show on a range of simulated locomotion, navigation, and manipulation tasks, our method referred to as latent-variable advantage-weighted policy optimization (LAPO), improves the average performance of the next best-performing offline reinforcement learning methods by 49% on heterogeneous datasets, and by 8% on datasets with narrow and biased distributions.

Yu Guo, Yuan Gao, Ryan Wen Liu et al.

The presence of non-homogeneous haze can cause scene blurring, color distortion, low contrast, and other degradations that obscure texture details. Existing homogeneous dehazing methods struggle to handle the non-uniform distribution of haze in a robust manner. The crucial challenge of non-homogeneous dehazing is to effectively extract the non-uniform distribution features and reconstruct the details of hazy areas with high quality. In this paper, we propose a novel self-paced semi-curricular attention network, called SCANet, for non-homogeneous image dehazing that focuses on enhancing haze-occluded regions. Our approach consists of an attention generator network and a scene reconstruction network. We use the luminance differences of images to restrict the attention map and introduce a self-paced semi-curricular learning strategy to reduce learning ambiguity in the early stages of training. Extensive quantitative and qualitative experiments demonstrate that our SCANet outperforms many state-of-the-art methods. The code is publicly available at https://github.com/gy65896/SCANet.

Tianyu Zhang, Luyi Han, Anna D'Angelo et al.

Magnetic resonance imaging (MRI) is the most sensitive technique for breast cancer detection among current clinical imaging modalities. Contrast-enhanced MRI (CE-MRI) provides superior differentiation between tumors and invaded healthy tissue, and has become an indispensable technique in the detection and evaluation of cancer. However, the use of gadolinium-based contrast agents (GBCA) to obtain CE-MRI may be associated with nephrogenic systemic fibrosis and may lead to bioaccumulation in the brain, posing a potential risk to human health. Moreover, and likely more important, the use of gadolinium-based contrast agents requires the cannulation of a vein, and the injection of the contrast media which is cumbersome and places a burden on the patient. To reduce the use of contrast agents, diffusion-weighted imaging (DWI) is emerging as a key imaging technique, although currently usually complementing breast CE-MRI. In this study, we develop a multi-sequence fusion network to synthesize CE-MRI based on T1-weighted MRI and DWIs. DWIs with different b-values are fused to efficiently utilize the difference features of DWIs. Rather than proposing a pure data-driven approach, we invent a multi-sequence attention module to obtain refined feature maps, and leverage hierarchical representation information fused at different scales while utilizing the contributions from different sequences from a model-driven approach by introducing the weighted difference module. The results show that the multi-b-value DWI-based fusion model can potentially be used to synthesize CE-MRI, thus theoretically reducing or avoiding the use of GBCA, thereby minimizing the burden to patients. Our code is available at \url{https://github.com/Netherlands-Cancer-Institute/CE-MRI}.

Luyi Han, Tao Tan, Tianyu Zhang et al.

Multi-sequence MRIs can be necessary for reliable diagnosis in clinical practice due to the complimentary information within sequences. However, redundant information exists across sequences, which interferes with mining efficient representations by modern machine learning or deep learning models. To handle various clinical scenarios, we propose a sequence-to-sequence generation framework (Seq2Seq) for imaging-differentiation representation learning. In this study, not only do we propose arbitrary 3D/4D sequence generation within one model to generate any specified target sequence, but also we are able to rank the importance of each sequence based on a new metric estimating the difficulty of a sequence being generated. Furthermore, we also exploit the generation inability of the model to extract regions that contain unique information for each sequence. We conduct extensive experiments using three datasets including a toy dataset of 20,000 simulated subjects, a brain MRI dataset of 1,251 subjects, and a breast MRI dataset of 2,101 subjects, to demonstrate that (1) our proposed Seq2Seq is efficient and lightweight for complex clinical datasets and can achieve excellent image quality; (2) top-ranking sequences can be used to replace complete sequences with non-inferior performance; (3) combining MRI with our imaging-differentiation map leads to better performance in clinical tasks such as glioblastoma MGMT promoter methylation status prediction and breast cancer pathological complete response status prediction. Our code is available at https://github.com/fiy2W/mri_seq2seq.

Luyi Han, Tianyu Zhang, Yunzhi Huang et al.

Multi-sequence MRI is valuable in clinical settings for reliable diagnosis and treatment prognosis, but some sequences may be unusable or missing for various reasons. To address this issue, MRI synthesis is a potential solution. Recent deep learning-based methods have achieved good performance in combining multiple available sequences for missing sequence synthesis. Despite their success, these methods lack the ability to quantify the contributions of different input sequences and estimate the quality of generated images, making it hard to be practical. Hence, we propose an explainable task-specific synthesis network, which adapts weights automatically for specific sequence generation tasks and provides interpretability and reliability from two sides: (1) visualize the contribution of each input sequence in the fusion stage by a trainable task-specific weighted average module; (2) highlight the area the network tried to refine during synthesizing by a task-specific attention module. We conduct experiments on the BraTS2021 dataset of 1251 subjects, and results on arbitrary sequence synthesis indicate that the proposed method achieves better performance than the state-of-the-art methods. Our code is available at \url{https://github.com/fiy2W/mri_seq2seq}.

Tianyu Zhang, Tao Tan, Luyi Han et al.

Magnetic resonance imaging (MRI) is highly sensitive for lesion detection in the breasts. Sequences obtained with different settings can capture the specific characteristics of lesions. Such multi-parameter MRI information has been shown to improve radiologist performance in lesion classification, as well as improving the performance of artificial intelligence models in various tasks. However, obtaining multi-parameter MRI makes the examination costly in both financial and time perspectives, and there may be safety concerns for special populations, thus making acquisition of the full spectrum of MRI sequences less durable. In this study, different than naive input fusion or feature concatenation from existing MRI parameters, a novel $\textbf{I}$ntegrated MRI $\textbf{M}$ulti-$\textbf{P}$arameter reinf$\textbf{O}$rcement fusion generato$\textbf{R}$ wi$\textbf{T}$h $\textbf{A}$tte$\textbf{NT}$ion Network (IMPORTANT-Net) is developed to generate missing parameters. First, the parameter reconstruction module is used to encode and restore the existing MRI parameters to obtain the corresponding latent representation information at any scale level. Then the multi-parameter fusion with attention module enables the interaction of the encoded information from different parameters through a set of algorithmic strategies, and applies different weights to the information through the attention mechanism after information fusion to obtain refined representation information. Finally, a reinforcement fusion scheme embedded in a $V^{-}$-shape generation module is used to combine the hierarchical representations to generate the missing MRI parameter. Results showed that our IMPORTANT-Net is capable of generating missing MRI parameters and outperforms comparable state-of-the-art networks. Our code is available at https://github.com/Netherlands-Cancer-Institute/MRI_IMPORTANT_NET.

Junjie Li, Zilei Wang, Yuan Gao et al.

In unsupervised domain adaptive (UDA) semantic segmentation, the distillation based methods are currently dominant in performance. However, the distillation technique requires complicate multi-stage process and many training tricks. In this paper, we propose a simple yet effective method that can achieve competitive performance to the advanced distillation methods. Our core idea is to fully explore the target-domain information from the views of boundaries and features. First, we propose a novel mix-up strategy to generate high-quality target-domain boundaries with ground-truth labels. Different from the source-domain boundaries in previous works, we select the high-confidence target-domain areas and then paste them to the source-domain images. Such a strategy can generate the object boundaries in target domain (edge of target-domain object areas) with the correct labels. Consequently, the boundary information of target domain can be effectively captured by learning on the mixed-up samples. Second, we design a multi-level contrastive loss to improve the representation of target-domain data, including pixel-level and prototype-level contrastive learning. By combining two proposed methods, more discriminative features can be extracted and hard object boundaries can be better addressed for the target domain. The experimental results on two commonly adopted benchmarks (\textit{i.e.}, GTA5 $\rightarrow$ Cityscapes and SYNTHIA $\rightarrow$ Cityscapes) show that our method achieves competitive performance to complicated distillation methods. Notably, for the SYNTHIA$\rightarrow$ Cityscapes scenario, our method achieves the state-of-the-art performance with $57.8\%$ mIoU and $64.6\%$ mIoU on 16 classes and 13 classes. Code is available at https://github.com/ljjcoder/EHTDI.

Andrew Caines, Luca Benedetto, Shiva Taslimipoor et al. · cambridge

The recent release of very large language models such as PaLM and GPT-4 has made an unprecedented impact in the popular media and public consciousness, giving rise to a mixture of excitement and fear as to their capabilities and potential uses, and shining a light on natural language processing research which had not previously received so much attention. The developments offer great promise for education technology, and in this paper we look specifically at the potential for incorporating large language models in AI-driven language teaching and assessment systems. We consider several research areas and also discuss the risks and ethical considerations surrounding generative AI in education technology for language learners. Overall we find that larger language models offer improvements over previous models in text generation, opening up routes toward content generation which had not previously been plausible. For text generation they must be prompted carefully and their outputs may need to be reshaped before they are ready for use. For automated grading and grammatical error correction, tasks whose progress is checked on well-known benchmarks, early investigations indicate that large language models on their own do not improve on state-of-the-art results according to standard evaluation metrics. For grading it appears that linguistic features established in the literature should still be used for best performance, and for error correction it may be that the models can offer alternative feedback styles which are not measured sensitively with existing methods. In all cases, there is work to be done to experiment with the inclusion of large language models in education technology for language learners, in order to properly understand and report on their capacities and limitations, and to ensure that foreseeable risks such as misinformation and harmful bias are mitigated.

Yuan Gao, Xiang Wang, Xiangnan He et al.

Rumor detection has become an emerging and active research field in recent years. At the core is to model the rumor characteristics inherent in rich information, such as propagation patterns in social network and semantic patterns in post content, and differentiate them from the truth. However, existing works on rumor detection fall short in modeling heterogeneous information, either using one single information source only (e.g. social network, or post content) or ignoring the relations among multiple sources (e.g. fusing social and content features via simple concatenation). Therefore, they possibly have drawbacks in comprehensively understanding the rumors, and detecting them accurately. In this work, we explore contrastive self-supervised learning on heterogeneous information sources, so as to reveal their relations and characterize rumors better. Technically, we supplement the main supervised task of detection with an auxiliary self-supervised task, which enriches post representations via post self-discrimination. Specifically, given two heterogeneous views of a post (i.e. representations encoding social patterns and semantic patterns), the discrimination is done by maximizing the mutual information between different views of the same post compared to that of other posts. We devise cluster-wise and instance-wise approaches to generate the views and conduct the discrimination, considering different relations of information sources. We term this framework as Self-supervised Rumor Detection (SRD). Extensive experiments on three real-world datasets validate the effectiveness of SRD for automatic rumor detection on social media.

Guangyi Liu, Zeyu Feng, Yuan Gao et al.

Real-world text applications often involve composing a wide range of text control operations, such as editing the text w.r.t. an attribute, manipulating keywords and structure, and generating new text of desired properties. Prior work typically learns/finetunes a language model (LM) to perform individual or specific subsets of operations. Recent research has studied combining operations in a plug-and-play manner, often with costly search or optimization in the complex sequence space. This paper proposes a new efficient approach for composable text operations in the compact latent space of text. The low-dimensionality and differentiability of the text latent vector allow us to develop an efficient sampler based on ordinary differential equations (ODEs) given arbitrary plug-in operators (e.g., attribute classifiers). By connecting pretrained LMs (e.g., GPT2) to the latent space through efficient adaption, we then decode the sampled vectors into desired text sequences. The flexible approach permits diverse control operators (sentiment, tense, formality, keywords, etc.) acquired using any relevant data from different domains. Experiments show that composing those operators within our approach manages to generate or edit high-quality text, substantially improving over previous methods in terms of generation quality and efficiency.

Yuan Bi, Zhongliang Jiang, Yuan Gao et al.

Ultrasound (US) is one of the most common medical imaging modalities since it is radiation-free, low-cost, and real-time. In freehand US examinations, sonographers often navigate a US probe to visualize standard examination planes with rich diagnostic information. However, reproducibility and stability of the resulting images often suffer from intra- and inter-operator variation. Reinforcement learning (RL), as an interaction-based learning method, has demonstrated its effectiveness in visual navigating tasks; however, RL is limited in terms of generalization. To address this challenge, we propose a simulation-based RL framework for real-world navigation of US probes towards the standard longitudinal views of vessels. A UNet is used to provide binary masks from US images; thereby, the RL agent trained on simulated binary vessel images can be applied in real scenarios without further training. To accurately characterize actual states, a multi-modality state representation structure is introduced to facilitate the understanding of environments. Moreover, considering the characteristics of vessels, a novel standard view recognition approach based on the minimum bounding rectangle is proposed to terminate the searching process. To evaluate the effectiveness of the proposed method, the trained policy is validated virtually on 3D volumes of a volunteer's in-vivo carotid artery, and physically on custom-designed gel phantoms using robotic US. The results demonstrate that proposed approach can effectively and accurately navigate the probe towards the longitudinal view of vessels.

Zhongliang Jiang, Yuan Gao, Le Xie et al.

Robotic ultrasound (US) imaging aims at overcoming some of the limitations of free-hand US examinations, e.g. difficulty in guaranteeing intra- and inter-operator repeatability. However, due to anatomical and physiological variations between patients and relative movement of anatomical substructures, it is challenging to robustly generate optimal trajectories to examine the anatomies of interest, in particular, when they comprise articulated joints. To address this challenge, this paper proposes a vision-based approach allowing autonomous robotic US limb scanning. To this end, an atlas MRI template of a human arm with annotated vascular structures is used to generate trajectories and register and project them onto patients' skin surfaces for robotic US acquisition. To effectively segment and accurately reconstruct the targeted 3D vessel, we make use of spatial continuity in consecutive US frames by incorporating channel attention modules into a U-Net-type neural network. The automatic trajectory generation method is evaluated on six volunteers with various articulated joint angles. In all cases, the system can successfully acquire the planned vascular structure on volunteers' limbs. For one volunteer the MRI scan was also available, which allows the evaluation of the average radius of the scanned artery from US images, resulting in a radius estimation ($1.2\pm0.05~mm$) comparable to the MRI ground truth ($1.2\pm0.04~mm$).

Junjie Hu, Chenyou Fan, Mete Ozay et al.

We study a practical yet hasn't been explored problem: how a drone can perceive in an environment from different flight heights. Unlike autonomous driving, where the perception is always conducted from a ground viewpoint, a flying drone may flexibly change its flight height due to specific tasks, requiring the capability for viewpoint invariant perception. Tackling the such problem with supervised learning will incur tremendous costs for data annotation of different flying heights. On the other hand, current semi-supervised learning methods are not effective under viewpoint differences. In this paper, we introduce the ground-to-aerial perception knowledge transfer and propose a progressive semi-supervised learning framework that enables drone perception using only labeled data of ground viewpoint and unlabeled data of flying viewpoints. Our framework has four core components: i) a dense viewpoint sampling strategy that splits the range of vertical flight height into a set of small pieces with evenly-distributed intervals, ii) nearest neighbor pseudo-labeling that infers labels of the nearest neighbor viewpoint with a model learned on the preceding viewpoint, iii) MixView that generates augmented images among different viewpoints to alleviate viewpoint differences, and iv) a progressive distillation strategy to gradually learn until reaching the maximum flying height. We collect a synthesized and a real-world dataset, and we perform extensive experimental analyses to show that our method yields 22.2% and 16.9% accuracy improvement for the synthesized dataset and the real world. Code and datasets are available on https://github.com/FreeformRobotics/Progressive-Self-Distillation-for-Ground-to-Aerial-Perception-Knowledge-Transfer.

Xin Wang, Tao Tan, Yuan Gao et al.

Asymmetry is a crucial characteristic of bilateral mammograms (Bi-MG) when abnormalities are developing. It is widely utilized by radiologists for diagnosis. The question of 'what the symmetrical Bi-MG would look like when the asymmetrical abnormalities have been removed ?' has not yet received strong attention in the development of algorithms on mammograms. Addressing this question could provide valuable insights into mammographic anatomy and aid in diagnostic interpretation. Hence, we propose a novel framework, DisAsymNet, which utilizes asymmetrical abnormality transformer guided self-adversarial learning for disentangling abnormalities and symmetric Bi-MG. At the same time, our proposed method is partially guided by randomly synthesized abnormalities. We conduct experiments on three public and one in-house dataset, and demonstrate that our method outperforms existing methods in abnormality classification, segmentation, and localization tasks. Additionally, reconstructed normal mammograms can provide insights toward better interpretable visual cues for clinical diagnosis. The code will be accessible to the public.

Zhiwei Hu, Bo Chen, Yuan Gao et al.

The task of referring video object segmentation aims to segment the object in the frames of a given video to which the referring expressions refer. Previous methods adopt multi-stage approach and design complex pipelines to obtain promising results. Recently, the end-to-end method based on Transformer has proved its superiority. In this work, we draw on the advantages of the above methods to provide a simple and effective pipeline for RVOS. Firstly, We improve the state-of-the-art one-stage method ReferFormer to obtain mask sequences that are strongly correlated with language descriptions. Secondly, based on a reliable and high-quality keyframe, we leverage the superior performance of video object segmentation model to further enhance the quality and temporal consistency of the mask results. Our single model reaches 70.3 J &F on the Referring Youtube-VOS validation set and 63.0 on the test set. After ensemble, we achieve 64.1 on the final leaderboard, ranking 1st place on CVPR2022 Referring Youtube-VOS challenge. Code will be available at https://github.com/Zhiweihhh/cvpr2022-rvos-challenge.git.

Yuheng Li, Yuan Gao, Haoyu Dong et al.

Computed tomography (CT) is a central to three-dimensional medical imaging, yet CT-based artificial intelligence remains fragmented across task-specific models for segmentation, classification, registration, and report analysis. Here we present FlexiCT, a family of CT foundation models trained by agglomerative continual pretraining on 266,227 CT volumes from 56 publicly available datasets, forming a large-scale public resource for CT representation learning. FlexiCT uses agglomerative pretraining across three stages: two-dimensional axial pretraining, three-dimensional anatomical pretraining and report-guided semantic alignment. This training strategy supports slice-level, volume-level and vision-language analysis. Across five downstream task families (segmentation, classification, registration, vision-language understanding and clinical retrieval), FlexiCT matches or exceeds prior task-specific approaches on multiple benchmarks. Its embeddings further organize CT scans along gradients associated with various tumor stages, suggesting that CT foundation models can capture imaging features relevant to disease phenotype characterization. Code is available at https://github.com/ricklisz/FlexiCT

Ke Yan, Xiaoli Yin, Yingda Xia et al.

Liver tumor segmentation and classification are important tasks in computer aided diagnosis. We aim to address three problems: liver tumor screening and preliminary diagnosis in non-contrast computed tomography (CT), and differential diagnosis in dynamic contrast-enhanced CT. A novel framework named Pixel-Lesion-pAtient Network (PLAN) is proposed. It uses a mask transformer to jointly segment and classify each lesion with improved anchor queries and a foreground-enhanced sampling loss. It also has an image-wise classifier to effectively aggregate global information and predict patient-level diagnosis. A large-scale multi-phase dataset is collected containing 939 tumor patients and 810 normal subjects. 4010 tumor instances of eight types are extensively annotated. On the non-contrast tumor screening task, PLAN achieves 95% and 96% in patient-level sensitivity and specificity. On contrast-enhanced CT, our lesion-level detection precision, recall, and classification accuracy are 92%, 89%, and 86%, outperforming widely used CNN and transformers for lesion segmentation. We also conduct a reader study on a holdout set of 250 cases. PLAN is on par with a senior human radiologist, showing the clinical significance of our results.

Jingxiang Qu, Ryan Wen Liu, Yuan Gao et al.

Real-time transportation surveillance is an essential part of the intelligent transportation system (ITS). However, images captured under low-light conditions often suffer the poor visibility with types of degradation, such as noise interference and vague edge features, etc. With the development of imaging devices, the quality of the visual surveillance data is continually increasing, like 2K and 4K, which has more strict requirements on the efficiency of image processing. To satisfy the requirements on both enhancement quality and computational speed, this paper proposes a double domain guided real-time low-light image enhancement network (DDNet) for ultra-high-definition (UHD) transportation surveillance. Specifically, we design an encoder-decoder structure as the main architecture of the learning network. In particular, the enhancement processing is divided into two subtasks (i.e., color enhancement and gradient enhancement) via the proposed coarse enhancement module (CEM) and LoG-based gradient enhancement module (GEM), which are embedded in the encoder-decoder structure. It enables the network to enhance the color and edge features simultaneously. Through the decomposition and reconstruction on both color and gradient domains, our DDNet can restore the detailed feature information concealed by the darkness with better visual quality and efficiency. The evaluation experiments on standard and transportation-related datasets demonstrate that our DDNet provides superior enhancement quality and efficiency compared with the state-of-the-art methods. Besides, the object detection and scene segmentation experiments indicate the practical benefits for higher-level image analysis under low-light environments in ITS.

Jiehui Huang, Yuechen Zhang, Xu He et al.

Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and limited modal diversity for comprehensive world knowledge representation. To address these limitations, we introduce UnityVideo, a unified framework for world-aware video generation that jointly learns across multiple modalities (segmentation masks, human skeletons, DensePose, optical flow, and depth maps) and training paradigms. Our approach features two core components: (1) dynamic noising to unify heterogeneous training paradigms, and (2) a modality switcher with an in-context learner that enables unified processing via modular parameters and contextual learning. We contribute a large-scale unified dataset with 1.3M samples. Through joint optimization, UnityVideo accelerates convergence and significantly enhances zero-shot generalization to unseen data. We demonstrate that UnityVideo achieves superior video quality, consistency, and improved alignment with physical world constraints. Code and data can be found at: https://github.com/dvlab-research/UnityVideo

Min Peng, Chongyang Wang, Yuan Gao et al.

Video question answering (VideoQA) is challenging given its multimodal combination of visual understanding and natural language processing. While most existing approaches ignore the visual appearance-motion information at different temporal scales, it is unknown how to incorporate the multilevel processing capacity of a deep learning model with such multiscale information. Targeting these issues, this paper proposes a novel Multilevel Hierarchical Network (MHN) with multiscale sampling for VideoQA. MHN comprises two modules, namely Recurrent Multimodal Interaction (RMI) and Parallel Visual Reasoning (PVR). With a multiscale sampling, RMI iterates the interaction of appearance-motion information at each scale and the question embeddings to build the multilevel question-guided visual representations. Thereon, with a shared transformer encoder, PVR infers the visual cues at each level in parallel to fit with answering different question types that may rely on the visual information at relevant levels. Through extensive experiments on three VideoQA datasets, we demonstrate improved performances than previous state-of-the-arts and justify the effectiveness of each part of our method.

Heinz H. Bauschke, Yuan Gao

In 2023, Boţ and Nguyen introduced a new class of accelerated algorithms for finding a fixed point of a nonexpansive operator as the weak limit of a sequence. In this paper, we analyze a particular instance of their algorithm when the nonexpansive operator is assumed to be linear. Surprisingly, the Boţ-Nguyen acceleration then fits naturally into the framework of weighted mean ergodic iterations. This allows us to identify the weak limit as the projection of the starting point onto the fixed point set. Moreover, the weights involved are closely related to the beta-binomial distribution. Finally, when the parameter is equal to 4, then we obtain strong convergence of the iterates.

Fan Zhang, Haoxuan Li, Shengju Qian et al.

Multimodal Large Language Models (MLLMs) have revolutionized numerous research fields, including computer vision and affective computing. As a pivotal challenge in this interdisciplinary domain, facial expression recognition (FER) has evolved from separate, domain-specific models to more unified approaches. One promising avenue to unify FER tasks is converting conventional FER datasets into visual question-answering (VQA) formats, enabling the direct application of powerful generalist MLLMs for inference. However, despite the success of cutting-edge MLLMs in various tasks, their performance on FER tasks remains largely unexplored. To address this gap, we provide FERBench, a systematic benchmark that incorporates 20 state-of-the-art MLLMs across four widely used FER datasets. Our results reveal that, while MLLMs exhibit good classification performance, they still face significant limitations in reasoning and interpretability. To this end, we introduce post-training strategies aimed at enhancing the facial expression reasoning capabilities of MLLMs. Specifically, we curate two high-quality and large-scale datasets: UniFER-CoT-230K for cold-start initialization and UniFER-RLVR-360K for reinforcement learning with verifiable rewards (RLVR), respectively. Building upon them, we develop a unified and interpretable FER foundation model termed UniFER-7B, which outperforms many open-sourced and closed-source generalist MLLMs (e.g., Gemini-2.5-Pro and Qwen2.5-VL-72B).

Yu Guo, Yuan Gao, Yuxu Lu et al.

In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target isolated degradation types, thereby falling short in environments where multiple degrading factors coexist. To bridge this gap, our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios. In this context, we propose OneRestore, a novel transformer-based framework designed for adaptive, controllable scene restoration. The proposed framework leverages a unique cross-attention mechanism, merging degraded scene descriptors with image features, allowing for nuanced restoration. Our model allows versatile input scene descriptors, ranging from manual text embeddings to automatic extractions based on visual attributes. Our methodology is further enhanced through a composite degradation restoration loss, using extra degraded images as negative samples to fortify model constraints. Comparative results on synthetic and real-world datasets demonstrate OneRestore as a superior solution, significantly advancing the state-of-the-art in addressing complex, composite degradations.

Yuan Gao, Nobuyuki Morioka, Yu Zhang et al. · apple-ml, pku

We propose Easy End-to-End Diffusion-based Text to Speech, a simple and efficient end-to-end text-to-speech model based on diffusion. E3 TTS directly takes plain text as input and generates an audio waveform through an iterative refinement process. Unlike many prior work, E3 TTS does not rely on any intermediate representations like spectrogram features or alignment information. Instead, E3 TTS models the temporal structure of the waveform through the diffusion process. Without relying on additional conditioning information, E3 TTS could support flexible latent structure within the given audio. This enables E3 TTS to be easily adapted for zero-shot tasks such as editing without any additional training. Experiments show that E3 TTS can generate high-fidelity audio, approaching the performance of a state-of-the-art neural TTS system. Audio samples are available at https://e3tts.github.io.

Shengqin Jiang, Yuan Gao, Bowen Li et al.

Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is knowledge distillation, which steers the learning of student networks by leveraging the experience of already-trained teacher networks. However, it faces a pair of challenges: Firstly, due to its two-stage training nature, a longer training period is essential, especially as the training samples increase. Secondly, despite the proficiency of teacher networks in transmitting assimilated knowledge, they tend to overlook the latent insights gained during their learning process. To address these challenges, we introduce an online distillation learning method for remote sensing object counting. It builds an end-to-end training framework that seamlessly integrates two distinct networks into a unified one. It comprises a shared shallow module, a teacher branch, and a student branch. The shared module serving as the foundation for both branches is dedicated to learning some primitive information. The teacher branch utilizes prior knowledge to reduce the difficulty of learning and guides the student branch in online learning. In parallel, the student branch achieves parameter reduction and rapid inference capabilities by means of channel reduction. This design empowers the student branch not only to receive privileged insights from the teacher branch but also to tap into the latent reservoir of knowledge held by the teacher branch during the learning process. Moreover, we propose a relation-in-relation distillation method that allows the student branch to effectively comprehend the evolution of the relationship of intra-layer teacher features among different inter-layer features. Extensive experiments demonstrate the effectiveness of our method.

Yuan Gao, Jian Huang, Yuling Jiao

Gaussian denoising has emerged as a powerful method for constructing simulation-free continuous normalizing flows for generative modeling. Despite their empirical successes, theoretical properties of these flows and the regularizing effect of Gaussian denoising have remained largely unexplored. In this work, we aim to address this gap by investigating the well-posedness of simulation-free continuous normalizing flows built on Gaussian denoising. Through a unified framework termed Gaussian interpolation flow, we establish the Lipschitz regularity of the flow velocity field, the existence and uniqueness of the flow, and the Lipschitz continuity of the flow map and the time-reversed flow map for several rich classes of target distributions. This analysis also sheds light on the auto-encoding and cycle consistency properties of Gaussian interpolation flows. Additionally, we study the stability of these flows in source distributions and perturbations of the velocity field, using the quadratic Wasserstein distance as a metric. Our findings offer valuable insights into the learning techniques employed in Gaussian interpolation flows for generative modeling, providing a solid theoretical foundation for end-to-end error analyses of learning Gaussian interpolation flows with empirical observations.

Sijing Li, Zhongwei Qiu, Jiang Liu et al.

Accurate tumor analysis is central to clinical radiology and precision oncology, where early detection, reliable lesion characterization, and pathology-level risk assessment guide diagnosis and treatment planning. Chain-of-Thought (CoT) reasoning is particularly important in this setting because it enables step-by-step interpretation from imaging findings to clinical impressions and pathology conclusions, improving traceability and reducing diagnostic errors. Here, we target the clinical tumor analysis task and build a large-scale benchmark that operationalizes a multimodal reasoning pipeline, spanning findings, impressions, and pathology predictions. We curate TumorCoT, a large-scale dataset of 1.5M CoT-labeled VQA instructions paired with 3D CT scans, with step-aligned rationales and cross-modal alignments along the trajectory from findings to impression to pathology, enabling evaluation of both answer accuracy and reasoning consistency. We further propose TumorChain, a multimodal interleaved reasoning framework that tightly couples 3D imaging encoders, clinical text understanding, and organ-level vision-language alignment. Through cross-modal alignment and iterative interleaved causal reasoning, TumorChain grounds visual evidence, aggregates conclusions, and issues pathology predictions after multiple rounds of self-refinement, improving traceability and reducing hallucination risk. Experiments show consistent improvements over strong baselines in lesion detection, impression generation, and pathology classification, and demonstrate strong generalization on the DeepTumorVQA benchmark. These results highlight the potential of multimodal reasoning for reliable and interpretable tumor analysis in clinical practice. Detailed information about our project can be found on our project homepage at https://github.com/ZJU4HealthCare/TumorChain.

Jinke Li, Xiao He, Yang Wen et al.

As a rising task, panoptic segmentation is faced with challenges in both semantic segmentation and instance segmentation. However, in terms of speed and accuracy, existing LiDAR methods in the field are still limited. In this paper, we propose a fast and high-performance LiDAR-based framework, referred to as Panoptic-PHNet, with three attractive aspects: 1) We introduce a clustering pseudo heatmap as a new paradigm, which, followed by a center grouping module, yields instance centers for efficient clustering without object-level learning tasks. 2) A knn-transformer module is proposed to model the interaction among foreground points for accurate offset regression. 3) For backbone design, we fuse the fine-grained voxel features and the 2D Bird's Eye View (BEV) features with different receptive fields to utilize both detailed and global information. Extensive experiments on both SemanticKITTI dataset and nuScenes dataset show that our Panoptic-PHNet surpasses state-of-the-art methods by remarkable margins with a real-time speed. We achieve the 1st place on the public leaderboard of SemanticKITTI and leading performance on the recently released leaderboard of nuScenes.

Yuan Gao, Ruili Wang, Feng Hou

The recently released ChatGPT has demonstrated surprising abilities in natural language understanding and natural language generation. Machine translation relies heavily on the abilities of language understanding and generation. Thus, in this paper, we explore how to assist machine translation with ChatGPT. We adopt several translation prompts on a wide range of translations. Our experimental results show that ChatGPT with designed translation prompts can achieve comparable or better performance over commercial translation systems for high-resource language translations. We further evaluate the translation quality using multiple references, and ChatGPT achieves superior performance compared to commercial systems. We also conduct experiments on domain-specific translations, the final results show that ChatGPT is able to comprehend the provided domain keyword and adjust accordingly to output proper translations. At last, we perform few-shot prompts that show consistent improvement across different base prompts. Our work provides empirical evidence that ChatGPT still has great potential in translations.

Jingtao Tang, Yuan Gao, Tin Lun Lam

For massive large-scale tasks, a multi-robot system (MRS) can effectively improve efficiency by utilizing each robot's different capabilities, mobility, and functionality. In this paper, we focus on the multi-robot coverage path planning (mCPP) problem in large-scale planar areas with random dynamic interferers in the environment, where the robots have limited resources. We introduce a worker-station MRS consisting of multiple workers with limited resources for actual work, and one station with enough resources for resource replenishment. We aim to solve the mCPP problem for the worker-station MRS by formulating it as a fully cooperative multi-agent reinforcement learning problem. Then we propose an end-to-end decentralized online planning method, which simultaneously solves coverage planning for workers and rendezvous planning for station. Our method manages to reduce the influence of random dynamic interferers on planning, while the robots can avoid collisions with them. We conduct simulation and real robot experiments, and the comparison results show that our method has competitive performance in solving the mCPP problem for worker-station MRS in metric of task finish time.

Xin An, Jingyi Cai, Xiangyang Chen et al.

Addressing the challenges of fragmented task definitions and the heterogeneity of unstructured data in multimodal parsing, this paper proposes the Omni Parsing framework. This framework establishes a Unified Taxonomy covering documents, images, and audio-visual streams, introducing a progressive parsing paradigm that bridges perception and cognition. Specifically, the framework integrates three hierarchical levels: 1) Holistic Detection, which achieves precise spatial-temporal grounding of objects or events to establish a geometric baseline for perception; 2) Fine-grained Recognition, which performs symbolization (e.g., OCR/ASR) and attribute extraction on localized objects to complete structured entity parsing; and 3) Multi-level Interpreting, which constructs a reasoning chain from local semantics to global logic. A pivotal advantage of this framework is its evidence anchoring mechanism, which enforces a strict alignment between high-level semantic descriptions and low-level facts. This enables ``evidence-based'' logical induction, transforming unstructured signals into standardized knowledge that is locatable, enumerable, and traceable. Building on this foundation, we constructed a standardized dataset and released the Logics-Parsing-Omni model, which successfully converts complex audio-visual signals into machine-readable structured knowledge. Experiments demonstrate that fine-grained perception and high-level cognition are synergistic, effectively enhancing model reliability. Furthermore, to quantitatively evaluate these capabilities, we introduce OmniParsingBench. Code, models and the benchmark are released at https://github.com/alibaba/Logics-Parsing/tree/master/Logics-Parsing-Omni.

Tianyu Zhang, Xinglong Liang, Jarek van Dijk et al.

Synthesizing high fidelity contrast enhanced MRI is clinically valuable for safer and more efficient breast cancer screening, yet remains challenging due to complex lesion textures and heterogeneous enhancement patterns.

Ryan Wen Liu, Yuxu Lu, Yuan Gao et al.

The visible-light camera, which is capable of environment perception and navigation assistance, has emerged as an essential imaging sensor for marine surface vessels in intelligent waterborne transportation systems (IWTS). However, the visual imaging quality inevitably suffers from several kinds of degradations (e.g., limited visibility, low contrast, color distortion, etc.) under complex weather conditions (e.g., haze, rain, and low-lightness). The degraded visual information will accordingly result in inaccurate environment perception and delayed operations for navigational risk. To promote the navigational safety of vessels, many computational methods have been presented to perform visual quality enhancement under poor weather conditions. However, most of these methods are essentially specific-purpose implementation strategies, only available for one specific weather type. To overcome this limitation, we propose to develop a general-purpose multi-scene visibility enhancement method, i.e., edge reparameterization- and attention-guided neural network (ERANet), to adaptively restore the degraded images captured under different weather conditions. In particular, our ERANet simultaneously exploits the channel attention, spatial attention, and reparameterization technology to enhance the visual quality while maintaining low computational cost. Extensive experiments conducted on standard and IWTS-related datasets have demonstrated that our ERANet could outperform several representative visibility enhancement methods in terms of both imaging quality and computational efficiency. The superior performance of IWTS-related object detection and scene segmentation could also be steadily obtained after ERANet-based visibility enhancement under complex weather conditions.

Yuan Gao, Shuguo Jiang, Moran Li et al.

We aim to address Multi-Task Learning (MTL) with a large number of tasks by Multi-Task Grouping (MTG). Given N tasks, we propose to simultaneously identify the best task groups from 2^N candidates and train the model weights simultaneously in one-shot, with the high-order task-affinity fully exploited. This is distinct from the pioneering methods which sequentially identify the groups and train the model weights, where the group identification often relies on heuristics. As a result, our method not only improves the training efficiency, but also mitigates the objective bias introduced by the sequential procedures that potentially lead to a suboptimal solution. Specifically, we formulate MTG as a fully differentiable pruning problem on an adaptive network architecture determined by an underlying Categorical distribution. To categorize N tasks into K groups (represented by K encoder branches), we initially set up KN task heads, where each branch connects to all N task heads to exploit the high-order task-affinity. Then, we gradually prune the KN heads down to N by learning a relaxed differentiable Categorical distribution, ensuring that each task is exclusively and uniquely categorized into only one branch. Extensive experiments on CelebA and Taskonomy datasets with detailed ablations show the promising performance and efficiency of our method. The codes are available at https://github.com/ethanygao/DMTG.

Xin Wang, Tao Tan, Yuan Gao et al.

Precision breast cancer (BC) risk assessment is crucial for developing individualized screening and prevention. Despite the promising potential of recent mammogram (MG) based deep learning models in predicting BC risk, they mostly overlook the 'time-to-future-event' ordering among patients and exhibit limited explorations into how they track history changes in breast tissue, thereby limiting their clinical application. In this work, we propose a novel method, named OA-BreaCR, to precisely model the ordinal relationship of the time to and between BC events while incorporating longitudinal breast tissue changes in a more explainable manner. We validate our method on public EMBED and inhouse datasets, comparing with existing BC risk prediction and time prediction methods. Our ordinal learning method OA-BreaCR outperforms existing methods in both BC risk and time-to-future-event prediction tasks. Additionally, ordinal heatmap visualizations show the model's attention over time. Our findings underscore the importance of interpretable and precise risk assessment for enhancing BC screening and prevention efforts. The code will be accessible to the public.

Tom Gunter, Zirui Wang, Chong Wang et al.

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on Responsible AI and how the principles are applied throughout the model development.

Xinshun Wang, Wanying Zhang, Can Wang et al.

Graph Convolutional Networks (GCN) which typically follows a neural message passing framework to model dependencies among skeletal joints has achieved high success in skeleton-based human motion prediction task. Nevertheless, how to construct a graph from a skeleton sequence and how to perform message passing on the graph are still open problems, which severely affect the performance of GCN. To solve both problems, this paper presents a Dynamic Dense Graph Convolutional Network (DD-GCN), which constructs a dense graph and implements an integrated dynamic message passing. More specifically, we construct a dense graph with 4D adjacency modeling as a comprehensive representation of motion sequence at different levels of abstraction. Based on the dense graph, we propose a dynamic message passing framework that learns dynamically from data to generate distinctive messages reflecting sample-specific relevance among nodes in the graph. Extensive experiments on benchmark Human 3.6M and CMU Mocap datasets verify the effectiveness of our DD-GCN which obviously outperforms state-of-the-art GCN-based methods, especially when using long-term and our proposed extremely long-term protocol.

Yuan Gao, Rustem Islamov, Sebastian Stich

Modern distributed training relies heavily on communication compression to reduce the communication overhead. In this work, we study algorithms employing a popular class of contractive compressors in order to reduce communication overhead. However, the naive implementation often leads to unstable convergence or even exponential divergence due to the compression bias. Error Compensation (EC) is an extremely popular mechanism to mitigate the aforementioned issues during the training of models enhanced by contractive compression operators. Compared to the effectiveness of EC in the data homogeneous regime, the understanding of the practicality and theoretical foundations of EC in the data heterogeneous regime is limited. Existing convergence analyses typically rely on strong assumptions such as bounded gradients, bounded data heterogeneity, or large batch accesses, which are often infeasible in modern machine learning applications. We resolve the majority of current issues by proposing EControl, a novel mechanism that can regulate error compensation by controlling the strength of the feedback signal. We prove fast convergence for EControl in standard strongly convex, general convex, and nonconvex settings without any additional assumptions on the problem or data heterogeneity. We conduct extensive numerical evaluations to illustrate the efficacy of our method and support our theoretical findings.

Yuan Gao, Di Cao, Xiaohuan Xi et al.

Semantic segmentation of 3D geospatial point clouds is pivotal for remote sensing applications. However, variations in geographic patterns across regions and data acquisition strategies induce significant domain shifts, severely degrading the performance of deployed models. Existing domain adaptation methods typically rely on access to source-domain data. However, this requirement is rarely met due to data privacy concerns, regulatory policies, and data transmission limitations. This motivates the largely underexplored setting of source-free unsupervised domain adaptation (SFUDA), where only a pretrained model and unlabeled target-domain data are available. In this paper, we propose LoGo (Local-Global Dual-Consensus), a novel SFUDA framework specifically designed for geospatial point clouds. At the local level, we introduce a class-balanced prototype estimation module that abandons conventional global threshold filtering in favor of an intra-class independent anchor mining strategy. This ensures that robust feature prototypes can be generated even for sample-scarce tail classes, effectively mitigating the feature collapse caused by long-tailed distributions. At the global level, we introduce an optimal transport-based global distribution alignment module that formulates pseudo-label assignment as a global optimization problem. By enforcing global distribution constraints, this module effectively corrects the over-dominance of head classes inherent in local greedy assignments, preventing model predictions from being severely biased towards majority classes. Finally, we propose a dual-consistency pseudo-label filtering mechanism. This strategy retains only high-confidence pseudo-labels where local multi-augmented ensemble predictions align with global optimal transport assignments for self-training.

Peng Chen, Pi Bu, Jun Song et al.

Recently, large language model (LLM)-based agents have made significant advances across various fields. One of the most popular research areas involves applying these agents to video games. Traditionally, these methods have relied on game APIs to access in-game environmental and action data. However, this approach is limited by the availability of APIs and does not reflect how humans play games. With the advent of vision language models (VLMs), agents now have enhanced visual understanding capabilities, enabling them to interact with games using only visual inputs. Despite these advances, current approaches still face challenges in action-oriented tasks, particularly in action role-playing games (ARPGs), where reinforcement learning methods are prevalent but suffer from poor generalization and require extensive training. To address these limitations, we select an ARPG, ``Black Myth: Wukong'', as a research platform to explore the capability boundaries of existing VLMs in scenarios requiring visual-only input and complex action output. We define 12 tasks within the game, with 75% focusing on combat, and incorporate several state-of-the-art VLMs into this benchmark. Additionally, we will release a human operation dataset containing recorded gameplay videos and operation logs, including mouse and keyboard actions. Moreover, we propose a novel VARP (Vision Action Role-Playing) agent framework, consisting of an action planning system and a visual trajectory system. Our framework demonstrates the ability to perform basic tasks and succeed in 90% of easy and medium-level combat scenarios. This research aims to provide new insights and directions for applying multimodal agents in complex action game environments. The code and datasets will be made available at https://varp-agent.github.io/.

Wei Huang, Wei Liu, Xiaoming Zhang et al.

The early detection and precise diagnosis of liver tumors are tasks of critical clinical value, yet they pose significant challenges due to the high heterogeneity and variability of liver tumors. In this work, a precise LIver tumor DIAgnosis network on multi-phase contrast-enhance CT, named LIDIA, is proposed for real-world scenario. To fully utilize all available phases in contrast-enhanced CT, LIDIA first employs the iterative fusion module to aggregate variable numbers of image phases, thereby capturing the features of lesions at different phases for better tumor diagnosis. To effectively mitigate the high heterogeneity problem of liver tumors, LIDIA incorporates asymmetric contrastive learning to enhance the discriminability between different classes. To evaluate our method, we constructed a large-scale dataset comprising 1,921 patients and 8,138 lesions. LIDIA has achieved an average AUC of 93.6% across eight different types of lesions, demonstrating its effectiveness. Besides, LIDIA also demonstrated strong generalizability with an average AUC of 89.3% when tested on an external cohort of 828 patients.

Xun Guo, Mingwu Zheng, Liang Hou et al.

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.

Yan-Jie Zhou, Wei Liu, Yuan Gao et al.

Skin diseases are among the most prevalent health issues, and accurate computer-aided diagnosis methods are of importance for both dermatologists and patients. However, most of the existing methods overlook the essential domain knowledge required for skin disease diagnosis. A novel multi-task model, namely DermImitFormer, is proposed to fill this gap by imitating dermatologists' diagnostic procedures and strategies. Through multi-task learning, the model simultaneously predicts body parts and lesion attributes in addition to the disease itself, enhancing diagnosis accuracy and improving diagnosis interpretability. The designed lesion selection module mimics dermatologists' zoom-in action, effectively highlighting the local lesion features from noisy backgrounds. Additionally, the presented cross-interaction module explicitly models the complicated diagnostic reasoning between body parts, lesion attributes, and diseases. To provide a more robust evaluation of the proposed method, a large-scale clinical image dataset of skin diseases with significantly more cases than existing datasets has been established. Extensive experiments on three different datasets consistently demonstrate the state-of-the-art recognition performance of the proposed approach.

Luyi Han, Tao Tan, Tianyu Zhang et al.

Adversarial learning helps generative models translate MRI from source to target sequence when lacking paired samples. However, implementing MRI synthesis with adversarial learning in clinical settings is challenging due to training instability and mode collapse. To address this issue, we leverage intermediate sequences to estimate the common latent space among multi-sequence MRI, enabling the reconstruction of distinct sequences from the common latent space. We propose a generative model that compresses discrete representations of each sequence to estimate the Gaussian distribution of vector-quantized common (VQC) latent space between multiple sequences. Moreover, we improve the latent space consistency with contrastive learning and increase model stability by domain augmentation. Experiments using BraTS2021 dataset show that our non-adversarial model outperforms other GAN-based methods, and VQC latent space aids our model to achieve (1) anti-interference ability, which can eliminate the effects of noise, bias fields, and artifacts, and (2) solid semantic representation ability, with the potential of one-shot segmentation. Our code is publicly available.

Chunli Li, Xiaoming Zhang, Yuan Gao et al.

Esophageal varices (EV), a serious health concern resulting from portal hypertension, are traditionally diagnosed through invasive endoscopic procedures. Despite non-contrast computed tomography (NC-CT) imaging being a less expensive and non-invasive imaging modality, it has yet to gain full acceptance as a primary clinical diagnostic tool for EV evaluation. To overcome existing diagnostic challenges, we present the Multi-Organ-cOhesion-Network (MOON), a novel framework enhancing the analysis of critical organ features in NC-CT scans for effective assessment of EV. Drawing inspiration from the thorough assessment practices of radiologists, MOON establishes a cohesive multiorgan analysis model that unifies the imaging features of the related organs of EV, namely esophagus, liver, and spleen. This integration significantly increases the diagnostic accuracy for EV. We have compiled an extensive NC-CT dataset of 1,255 patients diagnosed with EV, spanning three grades of severity. Each case is corroborated by endoscopic diagnostic results. The efficacy of MOON has been substantiated through a validation process involving multi-fold cross-validation on 1,010 cases and an independent test on 245 cases, exhibiting superior diagnostic performance compared to methods focusing solely on the esophagus (for classifying severe grade: AUC of 0.864 versus 0.803, and for moderate to severe grades: AUC of 0.832 versus 0.793). To our knowledge, MOON is the first work to incorporate a synchronized multi-organ NC-CT analysis for EV assessment, providing a more acceptable and minimally invasive alternative for patients compared to traditional endoscopy.

Yixuan Zhu, Jiaqi Feng, Wenzhao Zheng et al.

Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and actions remain underexplored, especially for general-purpose scenarios and various forms of actions. To bridge this gap, we introduce Astra, an interactive general world model that generates real-world futures for diverse scenarios (e.g., autonomous driving, robot grasping) with precise action interactions (e.g., camera motion, robot action). We propose an autoregressive denoising architecture and use temporal causal attention to aggregate past observations and support streaming outputs. We use a noise-augmented history memory to avoid over-reliance on past frames to balance responsiveness with temporal coherence. For precise action control, we introduce an action-aware adapter that directly injects action signals into the denoising process. We further develop a mixture of action experts that dynamically route heterogeneous action modalities, enhancing versatility across diverse real-world tasks such as exploration, manipulation, and camera control. Astra achieves interactive, consistent, and general long-term video prediction and supports various forms of interactions. Experiments across multiple datasets demonstrate the improvements of Astra in fidelity, long-range prediction, and action alignment over existing state-of-the-art world models.

Yuanqiao Zhang, Tiantian He, Yuan Gao et al.

In this paper, we present Federated Robust Curvature Optimization (FedRCO), a novel second-order optimization framework designed to improve convergence speed and reduce communication cost in Federated Learning systems under statistical heterogeneity. Existing second-order optimization methods are often computationally expensive and numerically unstable in distributed settings. In contrast, FedRCO addresses these challenges by integrating an efficient approximate curvature optimizer with a provable stability mechanism. Specifically, FedRCO incorporates three key components: (1) a Gradient Anomaly Monitor that detects and mitigates exploding gradients in real-time, (2) a Fail-Safe Resilience protocol that resets optimization states upon numerical instability, and (3) a Curvature-Preserving Adaptive Aggregation strategy that safely integrates global knowledge without erasing the local curvature geometry. Theoretical analysis shows that FedRCO can effectively mitigate instability and prevent unbounded updates while preserving optimization efficiency. Extensive experiments show that FedRCO achieves superior robustness against diverse non-IID scenarios while achieving higher accuracy and faster convergence than both state-of-the-art first-order and second-order methods.

Kailai Feng, Yuxiang Wei, Bo Chen et al.

Diffusion models have made significant progress in both text-to-image (T2I) generation and text-guided image editing. However, these models are typically built with billions of parameters, leading to high latency and increased deployment challenges. While on-device diffusion models improve efficiency, they largely focus on T2I generation and lack support for image editing. In this paper, we propose DreamLite, a compact unified on-device diffusion model (0.39B) that supports both T2I generation and text-guided image editing within a single network. DreamLite is built on a pruned mobile U-Net backbone and unifies conditioning through in-context spatial concatenation in the latent space. It concatenates images horizontally as input, using a (target | blank) configuration for generation tasks and (target | source) for editing tasks. To stabilize the training of this compact model, we introduce a task-progressive joint pretraining strategy that sequentially targets T2I, editing, and joint tasks. After high-quality SFT and reinforcement learning, DreamLite achieves GenEval (0.72) for image generation and ImgEdit (4.11) for image editing, outperforming existing on-device models and remaining competitive with several server-side models. By employing step distillation, we further reduce denoising processing to just 4 steps, enabling our DreamLite could generate or edit a 1024 x 1024 image in less than 1s on a Xiaomi 14 smartphone. To the best of our knowledge, DreamLite is the first unified on-device diffusion model that supports both image generation and image editing.

Junfeng Fang, Xinglin Li, Yongduo Sui et al.

Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC.