Ziyang Wang

Kairui Fu, Tao Zhang, Shuwen Xiao et al.

Semantic identifiers (SIDs) have gained increasing attention in generative retrieval (GR) for recommendation due to their meaningful semantic discriminability. However, current studies in this field primarily (1) offer limited investigation into the construction strategies for better SIDs, and (2) their SID assessment typically relies on costly GR training. To address these challenges, we propose FORGE, a comprehensive benchmark for FOrming semantic identifieRs for Generative rEtrieval. Specifically, FORGE provides a taxonomy of the SID construction process from several perspectives and validates their impact on downstream GR through offline experiments across diverse settings. Notably, these empirical findings have led to a 0.35% increase in transaction count via online A/B experiments in the Guess You Like section of Taobao. The corresponding SID construction strategies have since been deployed at full scale on Taobao, demonstrating their practical effectiveness. To avoid expensive SID assessment that requires full GR training, we propose two novel SID evaluation metrics that are highly correlated with recommendation performance, enabling convenient evaluations without any GR training. Furthermore, to facilitate the community, we release AL-GR, the industrial dataset used in our experiments, comprising 14 billion interactions and 250 million items with the corresponding multimodal features collected from Taobao. All the code and data are available at https://github.com/selous123/al_sid.

Ziyang Wang, Yi-Lin Sung, Feng Cheng et al.

The canonical approach to video-text retrieval leverages a coarse-grained or fine-grained alignment between visual and textual information. However, retrieving the correct video according to the text query is often challenging as it requires the ability to reason about both high-level (scene) and low-level (object) visual clues and how they relate to the text query. To this end, we propose a Unified Coarse-to-fine Alignment model, dubbed UCoFiA. Specifically, our model captures the cross-modal similarity information at different granularity levels. To alleviate the effect of irrelevant visual clues, we also apply an Interactive Similarity Aggregation module (ISA) to consider the importance of different visual features while aggregating the cross-modal similarity to obtain a similarity score for each granularity. Finally, we apply the Sinkhorn-Knopp algorithm to normalize the similarities of each level before summing them, alleviating over- and under-representation issues at different levels. By jointly considering the crossmodal similarity of different granularity, UCoFiA allows the effective unification of multi-grained alignments. Empirically, UCoFiA outperforms previous state-of-the-art CLIP-based methods on multiple video-text retrieval benchmarks, achieving 2.4%, 1.4% and 1.3% improvements in text-to-video retrieval R@1 on MSR-VTT, Activity-Net, and DiDeMo, respectively. Our code is publicly available at https://github.com/Ziyang412/UCoFiA.

Jiarong Ye, Yin-Ting Yeh, Yuan Xue et al.

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device coupled with label-free Raman Spectroscopy holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning approach applied to recognize the virus based on its Raman spectrum, which is used as a fingerprint. We present such a machine learning approach for analyzing Raman spectra of human and avian viruses. A Convolutional Neural Network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A vs. type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and non-enveloped viruses, and 99% accuracy for differentiating avian coronavirus (infectious bronchitis virus, IBV) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups (for example, amide, amino acid, carboxylic acid), we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses.

Chengyi Zhang, Zi Ye, Ziyang Wang

Reliable visual understanding in robot-assisted and minimally invasive surgery (RMIS/MIS) demands more than accurate masks: in clinical practice, clinicians pose language-like questions about procedural context, visibility, artefacts, and the presence of anatomical structures and surgical instruments, often under degraded views caused by occlusion, smoke, bleeding, and specular highlights. We present \textbf{RoboSurg-VQA}, a segmentation-aware visual question answering (VQA) benchmark built by repurposing public surgical segmentation datasets under a shared schema. Each frame is paired with a fixed set of clinically motivated questions spanning procedure context, anatomy (including region), imaging modality/view, surgical artefacts, image quality, and basic visibility and spatial attributes, with closed answer sets to enable consistent evaluation. To scale annotation, we generate candidate answers via constrained prompting with automatic validity and consistency checks, followed by human auditing to improve plausibility and label consistency. We report benchmark statistics, sanity baselines, and common evaluation challenges under challenging surgical conditions. The code will be available on https://github.com/ziyangwang007/Robosurg-VQA.

Jian-Qing Zheng, Ziyang Wang, Baoru Huang et al.

Deformable image registration, estimating the spatial transformation between different images, is an important task in medical imaging. Many previous studies have used learning-based methods for multi-stage registration to perform 3D image registration to improve performance. The performance of the multi-stage approach, however, is limited by the size of the receptive field where complex motion does not occur at a single spatial scale. We propose a new registration network combining recursive network architecture and mutual attention mechanism to overcome these limitations. Compared with the state-of-the-art deep learning methods, our network based on the recursive structure achieves the highest accuracy in lung Computed Tomography (CT) data set (Dice score of 92\% and average surface distance of 3.8mm for lungs) and one of the most accurate results in abdominal CT data set with 9 organs of various sizes (Dice score of 55\% and average surface distance of 7.8mm). We also showed that adding 3 recursive networks is sufficient to achieve the state-of-the-art results without a significant increase in the inference time.

Yuanlei Zheng, Pei Fu, Hang Li et al.

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive. We propose Doc-$V^*$, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation. Doc-$V^*$ begins with a thumbnail overview, then actively navigates via semantic retrieval and targeted page fetching, and aggregates evidence in a structured working memory for grounded reasoning. Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-$V^*$ balances answer accuracy with evidence-seeking efficiency. Across five benchmarks, Doc-$V^*$ outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to \textbf{47.9\%} over RAG baseline. Other results reveal effective evidence aggregation with selective attention, not increased input pages.

Ming Zhang, Shuai Dou, Ziyang Wang et al.

Automatic medical question summarization can significantly help the system to understand consumer health questions and retrieve correct answers. The Seq2Seq model based on maximum likelihood estimation (MLE) has been applied in this task, which faces two general problems: the model can not capture well question focus and and the traditional MLE strategy lacks the ability to understand sentence-level semantics. To alleviate these problems, we propose a novel question focus-driven contrastive learning framework (QFCL). Specially, we propose an easy and effective approach to generate hard negative samples based on the question focus, and exploit contrastive learning at both encoder and decoder to obtain better sentence level representations. On three medical benchmark datasets, our proposed model achieves new state-of-the-art results, and obtains a performance gain of 5.33, 12.85 and 3.81 points over the baseline BART model on three datasets respectively. Further human judgement and detailed analysis prove that our QFCL model learns better sentence representations with the ability to distinguish different sentence meanings, and generates high-quality summaries by capturing question focus.

Ziyang Wang, Tianze Li, Jian-Qing Zheng et al.

Due to the lack of quality annotation in medical imaging community, semi-supervised learning methods are highly valued in image semantic segmentation tasks. In this paper, an advanced consistency-aware pseudo-label-based self-ensembling approach is presented to fully utilize the power of Vision Transformer(ViT) and Convolutional Neural Network(CNN) in semi-supervised learning. Our proposed framework consists of a feature-learning module which is enhanced by ViT and CNN mutually, and a guidance module which is robust for consistency-aware purposes. The pseudo labels are inferred and utilized recurrently and separately by views of CNN and ViT in the feature-learning module to expand the data set and are beneficial to each other. Meanwhile, a perturbation scheme is designed for the feature-learning module, and averaging network weight is utilized to develop the guidance module. By doing so, the framework combines the feature-learning strength of CNN and ViT, strengthens the performance via dual-view co-training, and enables consistency-aware supervision in a semi-supervised manner. A topological exploration of all alternative supervision modes with CNN and ViT are detailed validated, demonstrating the most promising performance and specific setting of our method on semi-supervised medical image segmentation tasks. Experimental results show that the proposed method achieves state-of-the-art performance on a public benchmark data set with a variety of metrics. The code is publicly available.

Jian-Qing Zheng, Ziyang Wang, Baoru Huang et al.

Image registration is important for medical imaging, the estimation of the spatial transformation between different images. Many previous studies have used learning-based methods for coarse-to-fine registration to efficiently perform 3D image registration. The coarse-to-fine approach, however, is limited when dealing with the different motions of nearby objects. Here we propose a novel Motion-Aware (MA) structure that captures the different motions in a region. The MA structure incorporates a novel Residual Aligner (RA) module which predicts the multi-head displacement field used to disentangle the different motions of multiple neighbouring objects. Compared with other deep learning methods, the network based on the MA structure and RA module achieve one of the most accurate unsupervised inter-subject registration on the 9 organs of assorted sizes in abdominal CT scans, with the highest-ranked registration of the veins (Dice Similarity Coefficient / Average surface distance: 62\%/4.9mm for the vena cava and 34\%/7.9mm for the portal and splenic vein), with a half-sized structure and more efficient computation. Applied to the segmentation of lungs in chest CT scans, the new network achieves results which were indistinguishable from the best-ranked networks (94\%/3.0mm). Additionally, the theorem on predicted motion pattern and the design of MA structure are validated by further analysis.

Ziyang Wang

Satellite constellations are transforming space systems from isolated spacecraft into networked, software-defined platforms capable of on-orbit perception, decision making, and adaptation. Yet much of the existing AI studies remains centered on single-satellite inference, while constellation-scale autonomy introduces fundamentally new algorithmic requirements: learning and coordination under dynamic inter-satellite connectivity, strict SWaP-C limits, radiation-induced faults, non-IID data, concept drift, and safety-critical operational constraints. This survey consolidates the emerging field of on-orbit space AI through three complementary paradigms: (i) {federated learning} for cross-satellite training, personalization, and secure aggregation; (ii) {multi-agent algorithms} for cooperative planning, resource allocation, scheduling, formation control, and collision avoidance; and (iii) {collaborative sensing and distributed inference} for multi-satellite fusion, tracking, split/early-exit inference, and cross-layer co-design with constellation networking. We provide a system-level view and a taxonomy that unifies collaboration architectures, temporal mechanisms, and trust models. To support community development and keep this review actionable over time, we continuously curate relevant papers and resources at https://github.com/ziyangwang007/AI4Space.

Ziyang Wang, Yuxuan Cosmi Lin, Kunyan Zhang et al.

Optical spectroscopy is indispensable for research and development in nanoscience and nanotechnology, microelectronics, energy, and advanced manufacturing. Advanced optical spectroscopy tools often require both specifically designed high-end instrumentation and intricate data analysis techniques. Beyond the common analytical tools, deep learning methods are well suited for interpreting high-dimensional and complicated spectroscopy data. They offer great opportunities to extract subtle and deep information about optical properties of materials with simpler optical setups, which would otherwise require sophisticated instrumentation. In this work, we propose a computational ellipsometry approach based on a conventional tabletop optical microscope and a deep learning model called EllipsoNet. Without any prior knowledge about the multilayer substrates, EllipsoNet can predict the complex refractive indices of thin films on top of these nontrivial substrates from experimentally measured optical reflectance spectra with high accuracies. This task was not feasible previously with traditional reflectometry or ellipsometry methods. Fundamental physical principles, such as the Kramers-Kronig relations, are spontaneously learned by the model without any further training. This approach enables in-operando optical characterization of functional materials within complex photonic structures or optoelectronic devices.

Wenbiao Li, Ziyang Wang, Yunfang Wu

For readability assessment, traditional methods mainly employ machine learning classifiers with hundreds of linguistic features. Although the deep learning model has become the prominent approach for almost all NLP tasks, it is less explored for readability assessment. In this paper, we propose a BERT-based model with feature projection and length-balanced loss (BERT-FP-LBL) for readability assessment. Specially, we present a new difficulty knowledge guided semi-supervised method to extract topic features to complement the traditional linguistic features. From the linguistic features, we employ projection filtering to extract orthogonal features to supplement BERT representations. Furthermore, we design a new length-balanced loss to handle the greatly varying length distribution of data. Our model achieves state-of-the-art performances on two English benchmark datasets and one dataset of Chinese textbooks, and also achieves the near-perfect accuracy of 99\% on one English dataset. Moreover, our proposed model obtains comparable results with human experts in consistency test.

Ziyang Wang, Irina Voiculescu

Deep learning models, e.g. supervised Encoder-Decoder style networks, exhibit promising performance in medical image segmentation, but come with a high labelling cost. We propose TriSegNet, a semi-supervised semantic segmentation framework. It uses triple-view feature learning on a limited amount of labelled data and a large amount of unlabeled data. The triple-view architecture consists of three pixel-level classifiers and a low-level shared-weight learning module. The model is first initialized with labelled data. Label processing, including data perturbation, confidence label voting and unconfident label detection for annotation, enables the model to train on labelled and unlabeled data simultaneously. The confidence of each model gets improved through the other two views of the feature learning. This process is repeated until each model reaches the same confidence level as its counterparts. This strategy enables triple-view learning of generic medical image datasets. Bespoke overlap-based and boundary-based loss functions are tailored to the different stages of the training. The segmentation results are evaluated on four publicly available benchmark datasets including Ultrasound, CT, MRI, and Histology images. Repeated experiments demonstrate the effectiveness of the proposed network compared against other semi-supervised algorithms, across a large set of evaluation measures.

Teer Song, Yue Zhang, Yu Tian et al.

To better preserve an individual's identity, face restoration has evolved from reference-free to reference-based approaches, which leverage high-quality reference images of the same identity to enhance identity fidelity in the restored outputs. However, most existing methods implicitly assume that the reference and degraded input are age-aligned, limiting their effectiveness in real-world scenarios where only cross-age references are available, such as historical photo restoration. This paper proposes MeInTime, a diffusion-based face restoration method that extends reference-based restoration from same-age to cross-age settings. Given one or few reference images along with an age prompt corresponding to the degraded input, MeInTime achieves faithful restoration with both identity fidelity and age consistency. Specifically, we decouple the modeling of identity and age conditions. During training, we focus solely on effectively injecting identity features through a newly introduced attention mechanism and introduce Gated Residual Fusion modules to facilitate the integration between degraded features and identity representations. At inference, we propose Age-Aware Gradient Guidance, a training-free sampling strategy, using an age-driven direction to iteratively nudge the identity-aware denoising latent toward the desired age semantic manifold. Extensive experiments demonstrate that MeInTime outperforms existing face restoration methods in both identity preservation and age consistency. Our code is available at: https://github.com/teer4/MeInTime

Ce Zhang, Taixi Lu, Md Mohaiminul Islam et al.

We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory queues, state-space layers, etc.), our approach uses a frame/clip-level visual captioner (e.g., BLIP2, LaViLa, LLaVA) coupled with a Large Language Model (GPT-3.5, GPT-4) leading to a simple yet surprisingly effective LVQA framework. Specifically, we decompose short and long-range modeling aspects of LVQA into two stages. First, we use a short-term visual captioner to generate textual descriptions of short video clips (0.5-8s in length) densely sampled from a long input video. Afterward, an LLM aggregates the densely extracted short-term captions to perform long-range temporal reasoning needed to understand the whole video and answer a question. To analyze what makes our simple framework so effective, we thoroughly evaluate various components of our system. Our empirical analysis reveals that the choice of the visual captioner and LLM is critical for good LVQA performance. Furthermore, we show that a specialized prompt that asks the LLM first to summarize the noisy short-term visual captions and then answer a given input question leads to a significant LVQA performance boost. On EgoSchema, which is best known as a very long-form video question-answering benchmark, our method achieves 50.3% accuracy, outperforming the previous best-performing approach by 18.1% (absolute gain). In addition, our approach outperforms the previous state-of-the-art by 4.1% and 3.1% on NeXT-QA and IntentQA. We also extend LLoVi to grounded LVQA and show that it outperforms all prior methods on the NeXT-GQA dataset. We will release our code at https://github.com/CeeZh/LLoVi.

David Wan, Han Wang, Ziyang Wang et al.

Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation, where reliability requires grounding model outputs in heterogeneous input sources and verifying individual factual claims. However, existing multimodal grounding benchmarks and evaluation methods focus on simplified, observation-based scenarios or limited modalities and fail to assess attribution in complex multimodal reasoning. We introduce MuRGAt (Multimodal Reasoning with Grounded Attribution), a benchmark for evaluating fact-level multimodal attribution in settings that require reasoning beyond direct observation. Given inputs spanning video, audio, and other modalities, MuRGAt requires models to generate answers with explicit reasoning and precise citations, where each citation specifies both modality and temporal segments. To enable reliable assessment, we introduce an automatic evaluation framework that strongly correlates with human judgments. Benchmarking with human and automated scores reveals that even strong MLLMs frequently hallucinate citations despite correct reasoning. Moreover, we observe a key trade-off: increasing reasoning depth or enforcing structured grounding often degrades accuracy, highlighting a significant gap between internal reasoning and verifiable attribution.

Feng Cheng, Ziyang Wang, Yi-Lin Sung et al.

We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually arriving datasets, (iii) handle inputs from unknown datasets during inference, and (iv) enable knowledge sharing across similar dataset domains. Given a set of continually streaming VidQA datasets, we sequentially train dataset-specific adapters for each dataset while freezing the parameters of a large pretrained video-language backbone. During inference, given a video-question sample from an unknown domain, our method first uses the proposed non-parametric router function to compute a probability for each adapter, reflecting how relevant that adapter is to the current video-question input instance. Subsequently, the proposed dynamic adapter merging scheme aggregates all the adapter weights into a new adapter instance tailored for that particular test sample to compute the final VidQA prediction, mitigating the impact of inaccurate router predictions and facilitating knowledge sharing across domains. Our DAM model outperforms prior state-of-the-art continual learning approaches by 9.1% while exhibiting 1.9% less forgetting on 6 VidQA datasets spanning various domains. We further extend DAM to continual image classification and image QA and outperform prior methods by a large margin. The code is publicly available at: https://github.com/klauscc/DAM

Ce Zhang, Yan-Bo Lin, Ziyang Wang et al.

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilities of multimodal LLMs (MLLMs) still significantly lag, especially for complex video-language tasks. To address this issue, we present SiLVR, a Simple Language-based Video Reasoning framework that decomposes complex video understanding into two stages. In the first stage, SiLVR transforms raw video into language-based representations using multisensory inputs, such as short clip captions and audio/speech subtitles. In the second stage, language descriptions are fed into a powerful reasoning LLM to solve complex video-language understanding tasks. To handle long-context multisensory inputs, we use an adaptive token reduction scheme, which dynamically determines the temporal granularity with which to sample the tokens. Our simple, modular, and training-free video reasoning framework achieves the best-reported results on Video-MME (long), Video-MMMU (comprehension), Video-MMLU, CGBench, and EgoLife. Furthermore, our empirical study focused on video reasoning capabilities shows that, despite not being explicitly trained on video, strong reasoning LLMs can effectively aggregate multisensory input information from video, speech, and audio for complex temporal, causal, long-context, and knowledge acquisition reasoning tasks in video. Code is available at https://github.com/CeeZh/SILVR.

Yiyuan Ge, Zhihao Chen, Ziyang Wang et al.

The development of deep learning has facilitated the application of person re-identification (ReID) technology in intelligent security. Visible-infrared person re-identification (VI-ReID) aims to match pedestrians across infrared and visible modality images enabling 24-hour surveillance. Current studies relying on unsupervised modality transformations as well as inefficient embedding constraints to bridge the spectral differences between infrared and visible images, however, limit their potential performance. To tackle the limitations of the above approaches, this paper introduces a simple yet effective Spectral Enhancement and Pseudo-anchor Guidance Network, named SEPG-Net. Specifically, we propose a more homogeneous spectral enhancement scheme based on frequency domain information and greyscale space, which avoids the information loss typically caused by inefficient modality transformations. Further, a Pseudo Anchor-guided Bidirectional Aggregation (PABA) loss is introduced to bridge local modality discrepancies while better preserving discriminative identity embeddings. Experimental results on two public benchmark datasets demonstrate the superior performance of SEPG-Net against other state-of-the-art methods. The code is available at https://github.com/1024AILab/ReID-SEPG.

Jian-Qing Zheng, Yuanhan Mo, Yang Sun et al.

In medical imaging, the diffusion models have shown great potential for synthetic image generation tasks. However, these approaches often lack the interpretable connections between the generated and real images and can create anatomically implausible structures or illusions. To address these limitations, we propose the Deformation-Recovery Diffusion Model (DRDM), a novel diffusion-based generative model that emphasises morphological transformation through deformation fields rather than direct image synthesis. DRDM introduces a topology-preserving deformation field generation strategy, which randomly samples and integrates multi-scale Deformation Velocity Fields (DVFs). DRDM is trained to learn to recover unrealistic deformation components, thus restoring randomly deformed images to a realistic distribution. This formulation enables the generation of diverse yet anatomically plausible deformations that preserve structural integrity, thereby improving data augmentation and synthesis for downstream tasks such as few-shot learning and image registration. Experiments on cardiac Magnetic Resonance Imaging and pulmonary Computed Tomography show that DRDM is capable of creating diverse, large-scale deformations, while maintaining anatomical plausibility of deformation fields. Additional evaluations on 2D image segmentation and 3D image registration tasks indicate notable performance gains, underscoring DRDM's potential to enhance both image manipulation and generative modelling in medical imaging applications. Project page: https://jianqingzheng.github.io/def_diff_rec/

Jie Mei, Chenyu Lin, Yu Qiu et al.

Lung cancer is a leading cause of cancer-related deaths globally. PET-CT is crucial for imaging lung tumors, providing essential metabolic and anatomical information, while it faces challenges such as poor image quality, motion artifacts, and complex tumor morphology. Deep learning-based models are expected to address these problems, however, existing small-scale and private datasets limit significant performance improvements for these methods. Hence, we introduce a large-scale PET-CT lung tumor segmentation dataset, termed PCLT20K, which comprises 21,930 pairs of PET-CT images from 605 patients. Furthermore, we propose a cross-modal interactive perception network with Mamba (CIPA) for lung tumor segmentation in PET-CT images. Specifically, we design a channel-wise rectification module (CRM) that implements a channel state space block across multi-modal features to learn correlated representations and helps filter out modality-specific noise. A dynamic cross-modality interaction module (DCIM) is designed to effectively integrate position and context information, which employs PET images to learn regional position information and serves as a bridge to assist in modeling the relationships between local features of CT images. Extensive experiments on a comprehensive benchmark demonstrate the effectiveness of our CIPA compared to the current state-of-the-art segmentation methods. We hope our research can provide more exploration opportunities for medical image segmentation. The dataset and code are available at https://github.com/mj129/CIPA.

Zhihao Chen, Yiyuan Ge, Yanyan Lv et al.

The study of Cloth-Changing Person Re-identification (CC-ReID) focuses on retrieving specific pedestrians when their clothing has changed, typically under the assumption that the entire pedestrian images are visible. Pedestrian images in real-world scenarios, however, are often partially obscured by obstacles, presenting a significant challenge to existing CC-ReID systems. In this paper, we introduce a more challenging task termed Occluded Cloth-Changing Person Re-Identification (OC4-ReID), which simultaneously addresses two challenges of clothing changes and occlusion. Concretely, we construct two new datasets, Occ-LTCC and Occ-PRCC, based on original CC-ReID datasets to include random occlusions of key pedestrians components (e.g., head, torso). Moreover, a novel benchmark is proposed for OC4-ReID incorporating a Train-Test Micro Granularity Screening (T2MGS) module to mitigate the influence of occlusion and proposing a Part-Robust Triplet (PRT) loss for partial features learning. Comprehensive experiments on the proposed datasets, as well as on two CC-ReID benchmark datasets demonstrate the superior performance of proposed method against other state-of-the-art methods. The codes and datasets are available at: https://github.com/1024AILab/OC4-ReID.

Xingyue Huang, Rishabh, Gregor Franke et al.

Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and programming, where ground-truth correctness can be automatically evaluated. However, extending this success to other reasoning-intensive domains remains challenging due to the scarcity of high-quality, verifiable datasets and the high cost of human supervision. In this work, we introduce the Loong Project: an open-source framework for scalable synthetic data generation and verification across a diverse range of reasoning-intensive domains. The framework consists of two key components: (1) LoongBench, a curated seed dataset containing 8,729 human-vetted examples across 12 domains (e.g., Advanced Mathematics, Chemistry, Logic), each paired with executable code and rich metadata; and (2) LoongEnv, a modular synthetic data generation environment that supports multiple prompting strategies to produce new question-answer-code triples. Together, these components form an agent-environment loop that enables reinforcement learning, where an LLM-based agent is rewarded for generating Chain-of-Thought (CoT) solutions that align with code-executed answers. Empirically, we benchmark LoongBench on a broad suite of both open-source and proprietary LLMs to evaluate domain coverage and reveal performance bottlenecks. In addition, we conduct a comprehensive analysis of synthetic data generated by LoongEnv, examining correctness, difficulty, and diversity. Code and documentation are available at https://github.com/camel-ai/loong.

Ziyang Wang, Jian-Qing Zheng, Yichi Zhang et al.

In recent advancements in medical image analysis, Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have set significant benchmarks. While the former excels in capturing local features through its convolution operations, the latter achieves remarkable global context understanding by leveraging self-attention mechanisms. However, both architectures exhibit limitations in efficiently modeling long-range dependencies within medical images, which is a critical aspect for precise segmentation. Inspired by the Mamba architecture, known for its proficiency in handling long sequences and global contextual information with enhanced computational efficiency as a State Space Model (SSM), we propose Mamba-UNet, a novel architecture that synergizes the U-Net in medical image segmentation with Mamba's capability. Mamba-UNet adopts a pure Visual Mamba (VMamba)-based encoder-decoder structure, infused with skip connections to preserve spatial information across different scales of the network. This design facilitates a comprehensive feature learning process, capturing intricate details and broader semantic contexts within medical images. We introduce a novel integration mechanism within the VMamba blocks to ensure seamless connectivity and information flow between the encoder and decoder paths, enhancing the segmentation performance. We conducted experiments on publicly available ACDC MRI Cardiac segmentation dataset, and Synapse CT Abdomen segmentation dataset. The results show that Mamba-UNet outperforms several types of UNet in medical image segmentation under the same hyper-parameter setting. The source code and baseline implementations are available.

Shulian Zhang, Yong Guo, Long Peng et al.

Video Face Enhancement (VFE) aims to restore high-quality facial regions from degraded video sequences, enabling a wide range of practical applications. Despite substantial progress in the field, current methods that primarily rely on video super-resolution and generative frameworks continue to face three fundamental challenges: (1) computational inefficiency caused by iterative multi-step denoising in diffusion models; (2) faithfully modeling intricate facial textures while preserving temporal consistency; and (3) limited model generalization due to the lack of high-quality face video training data. To address these challenges, we propose VividFace, a novel and efficient one-step diffusion framework for VFE. Built upon the pretrained WANX video generation model, VividFace reformulates the traditional multi-step diffusion process as a single-step flow matching paradigm that directly maps degraded inputs to high-quality outputs with significantly reduced inference time. To enhance facial detail recovery, we introduce a Joint Latent-Pixel Face-Focused Training strategy that constructs spatiotemporally aligned facial masks to guide optimization toward critical facial regions in both latent and pixel spaces. Furthermore, we develop an MLLM-driven automated filtering pipeline that produces MLLM-Face90, a meticulously curated high-quality face video dataset, ensuring models learn from photorealistic facial textures. Extensive experiments demonstrate that VividFace achieves superior performance in perceptual quality, identity preservation, and temporal consistency across both synthetic and real-world benchmarks. We will publicly release our code, models, and dataset to support future research.

Teer Song, Yue Zhang, Yu Tian et al.

Recent progress in face restoration has shifted from visual fidelity to identity fidelity, driving a transition from reference-free to reference-based paradigms that condition restoration on reference images of the same person. However, these methods assume the reference and degraded input are age-aligned. When only cross-age references are available, as in historical restoration or missing-person retrieval, they fail to maintain age fidelity. To address this limitation, we propose TimeWeaver, the first reference-based face restoration framework supporting cross-age references. Given arbitrary reference images and a target-age prompt, TimeWeaver produces restorations with both identity fidelity and age consistency. Specifically, we decouple identity and age conditioning across training and inference. During training, the model learns an age-robust identity representation by fusing a global identity embedding with age-suppressed facial tokens via a transformer-based ID-Fusion module. During inference, two training-free techniques, Age-Aware Gradient Guidance and Token-Targeted Attention Boost, steer sampling toward desired age semantics, enabling precise adherence to the target-age prompt. Extensive experiments show that TimeWeaver surpasses existing methods in visual quality, identity preservation, and age consistency.

Qundong Shi, Jie Zhou, Biyuan Lin et al.

The development of audio foundation models has accelerated rapidly since the emergence of GPT-4o. However, the lack of comprehensive evaluation has become a critical bottleneck for further progress in the field, particularly in audio generation. Current audio evaluation faces three major challenges: (1) audio evaluation lacks a unified framework, with datasets and code scattered across various sources, hindering fair and efficient cross-model comparison;(2) audio codecs, as a key component of audio foundation models, lack a widely accepted and holistic evaluation methodology; (3) existing speech benchmarks are heavily reliant on English, making it challenging to objectively assess models' performance on Chinese. To address the first issue, we introduce UltraEval-Audio, a unified evaluation framework for audio foundation models, specifically designed for both audio understanding and generation tasks. UltraEval-Audio features a modular architecture, supporting 10 languages and 14 core task categories, while seamlessly integrating 24 mainstream models and 36 authoritative benchmarks. To enhance research efficiency, the framework provides a one-command evaluation feature, accompanied by real-time public leaderboards. For the second challenge, UltraEval-Audio adopts a novel comprehensive evaluation scheme for audio codecs, evaluating performance across three key dimensions: semantic accuracy, timbre fidelity, and acoustic quality. To address the third issue, we propose two new Chinese benchmarks, SpeechCMMLU and SpeechHSK, designed to assess Chinese knowledge proficiency and language fluency. We wish that UltraEval-Audio will provide both academia and industry with a transparent, efficient, and fair platform for comparison of audio models. Our code, benchmarks, and leaderboards are available at https://github.com/OpenBMB/UltraEval-Audio.

Ziyang Wang, Yue Zhang, Shoubin Yu et al.

Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more of continuous visual experience. In ultra-long video settings, relevant information is sparsely distributed across hours or days, making memory a fundamental challenge: models must accumulate information over time, recall prior states, track temporal order, and abstract recurring patterns. However, existing week-long video benchmarks are primarily designed for perception and recognition, such as moment localization or global summarization, rather than reasoning that requires integrating evidence across multiple days. To address this gap, we introduce EgoMemReason, a comprehensive benchmark that systematically evaluates week-long egocentric video understanding through memory-driven reasoning. EgoMemReason evaluates three complementary memory types: entity memory, tracking how object states evolve and change across days; event memory, recalling and ordering activities separated by hours or days; and behavior memory, abstracting recurring patterns from sparse, repeated observations over the whole week period. EgoMemReason comprises 500 questions across three memory types and six core challenges, with an average of 5.1 video segments of evidence per question and 25.9 hours of memory backtracking. We evaluate EgoMemReason on 17 methods across MLLMs and agentic frameworks, revealing that even the best model achieves only 39.6% overall accuracy. Further analysis shows that the three memory types fail for distinct reasons and that performance degrades as evidence spans longer temporal horizons, revealing that long-horizon memory remains far from solved. We believe EgoMemReason establishes a strong foundation for evaluating and advancing long-context, memory-aware multimodal systems.

Bei Li, Ziyang Wang, Hui Liu et al.

Recently, deep models have shown tremendous improvements in neural machine translation (NMT). However, systems of this kind are computationally expensive and memory intensive. In this paper, we take a natural step towards learning strong but light-weight NMT systems. We proposed a novel group-permutation based knowledge distillation approach to compressing the deep Transformer model into a shallow model. The experimental results on several benchmarks validate the effectiveness of our method. Our compressed model is 8X shallower than the deep model, with almost no loss in BLEU. To further enhance the teacher model, we present a Skipping Sub-Layer method to randomly omit sub-layers to introduce perturbation into training, which achieves a BLEU score of 30.63 on English-German newstest2014. The code is publicly available at https://github.com/libeineu/GPKD.

Bei Li, Ziyang Wang, Hui Liu et al.

Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT is an open question. In this paper, we investigate the behavior of a well-tuned deep Transformer system. We find that stacking layers is helpful in improving the representation ability of NMT models and adjacent layers perform similarly. This inspires us to develop a shallow-to-deep training method that learns deep models by stacking shallow models. In this way, we successfully train a Transformer system with a 54-layer encoder. Experimental results on WMT'16 English-German and WMT'14 English-French translation tasks show that it is $1.4$ $\times$ faster than training from scratch, and achieves a BLEU score of $30.33$ and $43.29$ on two tasks. The code is publicly available at https://github.com/libeineu/SDT-Training/.

Guanyi Du, Lintao Wang, Kun Hu et al.

Sign language production from symbolic notation offers a scalable route to accessible sign animation. We present KANMultiSign, a multi-scale sequence generator that translates HamNoSys notation into two-dimensional human pose sequences. Our framework makes two complementary contributions. First, we introduce a coarse-to-fine generation strategy with multi-scale supervision: the model is first guided by an intermediate body--hand--face scaffold to encourage global structural coherence, and then refines fine-grained hand articulation to improve finger-level detail. Second, we investigate integrating Kolmogorov--Arnold Network modules into a Transformer backbone, using learnable univariate function primitives to model the highly non-linear mapping from discrete phonological symbols to continuous body kinematics with a compact parameterization. Experiments on multiple public corpora spanning Polish, German, Greek, and French sign languages show consistent reductions in dynamic time warping based joint error compared with a strong notation-to-pose baseline, while using substantially fewer parameters. Controlled ablations further indicate that KAN-based variants substantially reduce parameter count while maintaining competitive performance when coupled with multi-scale supervision, rather than serving as the main driver of accuracy gains. These findings position multi-scale supervision as the key mechanism for improving notation-conditioned pose generation, with KAN offering a compact alternative for efficient modeling. Our code will be publicly available.

Chao Ma, Ziyang Wang

Medical image segmentation is essential in diagnostics, treatment planning, and healthcare, with deep learning offering promising advancements. Notably, the convolutional neural network (CNN) excels in capturing local image features, whereas the Vision Transformer (ViT) adeptly models long-range dependencies through multi-head self-attention mechanisms. Despite their strengths, both the CNN and ViT face challenges in efficiently processing long-range dependencies in medical images, often requiring substantial computational resources. This issue, combined with the high cost and limited availability of expert annotations, poses significant obstacles to achieving precise segmentation. To address these challenges, this study introduces Semi-Mamba-UNet, which integrates a purely visual Mamba-based U-shaped encoder-decoder architecture with a conventional CNN-based UNet into a semi-supervised learning (SSL) framework. This innovative SSL approach leverages both networks to generate pseudo-labels and cross-supervise one another at the pixel level simultaneously, drawing inspiration from consistency regularisation techniques. Furthermore, we introduce a self-supervised pixel-level contrastive learning strategy that employs a pair of projectors to enhance the feature learning capabilities further, especially on unlabelled data. Semi-Mamba-UNet was comprehensively evaluated on two publicly available segmentation dataset and compared with seven other SSL frameworks with both CNN- or ViT-based UNet as the backbone network, highlighting the superior performance of the proposed method. The source code of Semi-Mamba-Unet, all baseline SSL frameworks, the CNN- and ViT-based networks, and the two corresponding datasets are made publicly accessible.

Tianli Tao, Ziyang Wang, Delong Yang et al.

Longitudinal brain MRI is essential for lifespan study, yet high attrition rates often lead to missing data, complicating analysis. Deep generative models have been explored, but most rely solely on image intensity, leading to two key limitations: 1) the fidelity or trustworthiness of the generated brain images are limited, making downstream studies questionable; 2) the usage flexibility is restricted due to fixed guidance rooted in the model structure, restricting full ability to versatile application scenarios. To address these challenges, we introduce DF-DiffCom, a Kolmogorov-Arnold Networks (KAN)-enhanced diffusion model that smartly leverages deformation fields for trustworthy longitudinal brain image completion. Trained on OASIS-3, DF-DiffCom outperforms state-of-the-art methods, improving PSNR by 5.6% and SSIM by 0.12. More importantly, its modality-agnostic nature allows smooth extension to varied MRI modalities, even to attribute maps such as brain tissue segmentation results.

Ziyang Wang, Chao Ma

Medical image segmentation is increasingly reliant on deep learning techniques, yet the promising performance often come with high annotation costs. This paper introduces Weak-Mamba-UNet, an innovative weakly-supervised learning (WSL) framework that leverages the capabilities of Convolutional Neural Network (CNN), Vision Transformer (ViT), and the cutting-edge Visual Mamba (VMamba) architecture for medical image segmentation, especially when dealing with scribble-based annotations. The proposed WSL strategy incorporates three distinct architecture but same symmetrical encoder-decoder networks: a CNN-based UNet for detailed local feature extraction, a Swin Transformer-based SwinUNet for comprehensive global context understanding, and a VMamba-based Mamba-UNet for efficient long-range dependency modeling. The key concept of this framework is a collaborative and cross-supervisory mechanism that employs pseudo labels to facilitate iterative learning and refinement across the networks. The effectiveness of Weak-Mamba-UNet is validated on a publicly available MRI cardiac segmentation dataset with processed scribble annotations, where it surpasses the performance of a similar WSL framework utilizing only UNet or SwinUNet. This highlights its potential in scenarios with sparse or imprecise annotations. The source code is made publicly accessible.

Yunchuan Guan, Yu Liu, Ke Zhou et al.

Recent advances in generative modeling enable neural networks to generate weights without relying on gradient-based optimization. However, current methods are limited by issues of over-coupling and long-horizon. The former tightly binds weight generation with task-specific objectives, thereby limiting the flexibility of the learned optimizer. The latter leads to inefficiency and low accuracy during inference, caused by the lack of local constraints. In this paper, we propose Lo-Hp, a decoupled two-stage weight generation framework that enhances flexibility through learning various optimization policies. It adopts a hybrid-policy sub-trajectory balance objective, which integrates on-policy and off-policy learning to capture local optimization policies. Theoretically, we demonstrate that learning solely local optimization policies can address the long-horizon issue while enhancing the generation of global optimal weights. In addition, we validate Lo-Hp's superior accuracy and inference efficiency in tasks that require frequent weight updates, such as transfer learning, few-shot learning, domain generalization, and large language model adaptation.

Sanwoo Lee, Yida Cai, Desong Meng et al.

Advances in automated essay scoring (AES) have traditionally relied on labeled essays, requiring tremendous cost and expertise for their acquisition. Recently, large language models (LLMs) have achieved great success in various tasks, but their potential is less explored in AES. In this paper, we show that our zero-shot prompting framework, Multi Trait Specialization (MTS), elicits LLMs' ample potential for essay scoring. In particular, we automatically decompose writing proficiency into distinct traits and generate scoring criteria for each trait. Then, an LLM is prompted to extract trait scores from several conversational rounds, each round scoring one of the traits based on the scoring criteria. Finally, we derive the overall score via trait averaging and min-max scaling. Experimental results on two benchmark datasets demonstrate that MTS consistently outperforms straightforward prompting (Vanilla) in average QWK across all LLMs and datasets, with maximum gains of 0.437 on TOEFL11 and 0.355 on ASAP. Additionally, with the help of MTS, the small-sized Llama2-13b-chat substantially outperforms ChatGPT, facilitating an effective deployment in real applications.

Gui Ling, Ziyang Wang, Yuliang Yan et al.

Large language models (LLMs) have garnered significant attention for their remarkable capabilities across various domains, whose vast parameter scales present challenges for practical deployment. Structured pruning is an effective method to balance model performance with efficiency, but performance restoration under computational resource constraints is a principal challenge in pruning LLMs. Therefore, we present a low-cost and fast structured pruning method for LLMs named SlimGPT based on the Optimal Brain Surgeon framework. We propose Batched Greedy Pruning for rapid and near-optimal pruning, which enhances the accuracy of head-wise pruning error estimation through grouped Cholesky decomposition and improves the pruning efficiency of FFN via Dynamic Group Size, thereby achieving approximate local optimal pruning results within one hour. Besides, we explore the limitations of layer-wise pruning from the perspective of error accumulation and propose Incremental Pruning Ratio, a non-uniform pruning strategy to reduce performance degradation. Experimental results on the LLaMA benchmark show that SlimGPT outperforms other methods and achieves state-of-the-art results.

Ziyang Wang

Artificial Intelligence (AI) is transforming domains from healthcare and agriculture to finance and industry. As progress on Earth meets growing constraints, the next frontier is outer space, where AI can enable autonomous, resilient operations under extreme uncertainty and limited human oversight. This paper introduces Space AI as a unified interdisciplinary field at the intersection of artificial intelligence and space science and technology. We consolidate historical developments and contemporary progress, and propose a systematic framework that organises Space AI into four mission contexts: 1 AI on Earth, covering intelligent mission planning, spacecraft design optimisation, simulation, and ground-based data analytics; 2 AI in Orbit, focusing on satellite and station autonomy, space robotics, on-board/near-real-time data processing, communication optimisation, and orbital safety; 3 AI in Deep Space, enabling autonomous navigation, adaptive scientific discovery, resource mapping, and long-duration human-AI collaboration under communication constraints; and 4 AI for Multi-Planetary Life, supporting in-situ resource utilisation, habitat and infrastructure construction, life-support and ecological management, and resilient interplanetary networks. Ultimately, Space AI can accelerate humanity's capability to explore and operate in space, while translating advances in sensing, robotics, optimisation, and trustworthy AI into broad societal impact on Earth.

Ziyang Wang, Jian-Qing Zheng, Chao Ma et al.

Image registration, a critical process in medical imaging, involves aligning different sets of medical imaging data into a single unified coordinate system. Deep learning networks, such as the Convolutional Neural Network (CNN)-based VoxelMorph, Vision Transformer (ViT)-based TransMorph, and State Space Model (SSM)-based MambaMorph, have demonstrated effective performance in this domain. The recent Visual State Space Model (VMamba), which incorporates a cross-scan module with SSM, has exhibited promising improvements in modeling global-range dependencies with efficient computational cost in computer vision tasks. This paper hereby introduces an exploration of VMamba with image registration, named VMambaMorph. This novel hybrid VMamba-CNN network is designed specifically for 3D image registration. Utilizing a U-shaped network architecture, VMambaMorph computes the deformation field based on target and source volumes. The VMamba-based block with 2D cross-scan module is redesigned for 3D volumetric feature processing. To overcome the complex motion and structure on multi-modality images, we further propose a fine-tune recursive registration framework. We validate VMambaMorph using a public benchmark brain MR-CT registration dataset, comparing its performance against current state-of-the-art methods. The results indicate that VMambaMorph achieves competitive registration quality. The code for VMambaMorph with all baseline methods is available on GitHub.

Xizi Wang, Feng Cheng, Ziyang Wang et al.

Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt. Recent work has focused on enabling Video LLMs to perform video temporal grounding via next-token prediction of temporal timestamps. However, accurately localizing timestamps in videos remains challenging for Video LLMs when relying solely on temporal token prediction. Our proposed TimeRefine addresses this challenge in two ways. First, instead of directly predicting the start and end timestamps, we reformulate the temporal grounding task as a temporal refining task: the model first makes rough predictions and then refines them by predicting offsets to the target segment. This refining process is repeated multiple times, through which the model progressively self-improves its temporal localization accuracy. Second, to enhance the model's temporal perception capabilities, we incorporate an auxiliary prediction head that penalizes the model more if a predicted segment deviates further from the ground truth, thus encouraging the model to make closer and more accurate predictions. Our plug-and-play method can be integrated into most LLM-based temporal grounding approaches. The experimental results demonstrate that TimeRefine achieves 3.6% and 5.0% mIoU improvements on the ActivityNet and Charades-STA datasets, respectively. Code and pretrained models will be released.

Ziyang Wang, Jiangfeng Xiao, Chuan Xiao et al.

Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune, a structured pruning framework applied after pretraining that jointly prunes FFN channels and KV head groups under a single global budget. Instead of learning importance scores without constraints and applying the budget only after training, GRASPrune learns lightweight gate scores with a projected straight-through estimator that enforces a hard mask satisfying the budget at every step while keeping the backbone weights frozen. After the mask is fixed, we calibrate scaling factors on the retained units to mitigate scale mismatch caused by pruning, and fold these factors into the pruned weights to obtain a smaller dense checkpoint with no extra parameters at inference. On LLaMA-2-7B, GRASPrune removes 50% of parameters and achieves 12.18 perplexity on WikiText-2 while maintaining competitive average zero-shot accuracy on five benchmarks, using four epochs on 512 unlabeled calibration sequences on a single NVIDIA A100 80GB GPU without any full model fine-tuning.

Ziyang Wang, Jaehong Yoon, Shoubin Yu et al.

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and fine-tuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT) with extensive video data and long Chain-of-Thought (CoT) annotations, making them costly and hard to scale. To address this, we present Video-RTS, a new approach to improve video reasoning capability with drastically improved data efficiency by combining data-efficient RL with a video-adaptive test-time scaling (TTS) strategy. Building on observations about the data scaling, we skip the resource-intensive SFT step and employ efficient pure-RL training with output-based rewards, requiring no additional annotations or extensive fine-tuning. Furthermore, to utilize computational resources more efficiently, we introduce a sparse-to-dense video TTS strategy that improves inference by iteratively adding frames based on output consistency. We validate our approach on multiple video reasoning benchmarks, showing that Video-RTS surpasses existing video reasoning models by 2.4% in accuracy using only 3.6% training samples. Specifically, Video-RTS achieves a 4.2% improvement on Video-Holmes, a recent and challenging video reasoning benchmark. Notably, our pure RL training and adaptive video TTS offer complementary strengths, enabling Video-RTS's strong reasoning performance.

Tianli Tao, Ziyang Wang, Han Zhang et al.

Brain tumors delay the standard preprocessing workflow for further examination. Brain inpainting offers a viable, although difficult, solution for tumor tissue processing, which is necessary to improve the precision of the diagnosis and treatment. Most conventional U-Net-based generative models, however, often face challenges in capturing the complex, nonlinear latent representations inherent in brain imaging. In order to accomplish high-quality healthy brain tissue reconstruction, this work proposes DiffKAN-Inpainting, an innovative method that blends diffusion models with the Kolmogorov-Arnold Networks architecture. During the denoising process, we introduce the RePaint method and tumor information to generate images with a higher fidelity and smoother margin. Both qualitative and quantitative results demonstrate that as compared to the state-of-the-art methods, our proposed DiffKAN-Inpainting inpaints more detailed and realistic reconstructions on the BraTS dataset. The knowledge gained from ablation study provide insights for future research to balance performance with computing cost.

Kaiwen Zuo, Zelin Liu, Raman Dutt et al.

Large Vision-Language Models (LVLMs) augmented with Retrieval-Augmented Generation (RAG) are increasingly employed in medical AI to enhance factual grounding through external clinical image-text retrieval. However, this reliance creates a significant attack surface. We propose MedThreatRAG, a novel multimodal poisoning framework that systematically probes vulnerabilities in medical RAG systems by injecting adversarial image-text pairs. A key innovation of our approach is the construction of a simulated semi-open attack environment, mimicking real-world medical systems that permit periodic knowledge base updates via user or pipeline contributions. Within this setting, we introduce and emphasize Cross-Modal Conflict Injection (CMCI), which embeds subtle semantic contradictions between medical images and their paired reports. These mismatches degrade retrieval and generation by disrupting cross-modal alignment while remaining sufficiently plausible to evade conventional filters. While basic textual and visual attacks are included for completeness, CMCI demonstrates the most severe degradation. Evaluations on IU-Xray and MIMIC-CXR QA tasks show that MedThreatRAG reduces answer F1 scores by up to 27.66% and lowers LLaVA-Med-1.5 F1 rates to as low as 51.36%. Our findings expose fundamental security gaps in clinical RAG systems and highlight the urgent need for threat-aware design and robust multimodal consistency checks. Finally, we conclude with a concise set of guidelines to inform the safe development of future multimodal medical RAG systems.

Zida Liang, Changfa Wu, Dunxian Huang et al.

Recommendation systems are essential tools in modern e-commerce, facilitating personalized user experiences by suggesting relevant products. Recent advancements in generative models have demonstrated potential in enhancing recommendation systems; however, these models often exhibit limitations in optimizing retrieval tasks, primarily due to their reliance on autoregressive generation mechanisms. Conventional approaches introduce sequential dependencies that impede efficient retrieval, as they are inherently unsuitable for generating multiple items without positional constraints within a single request session. To address these limitations, we propose TBGRecall, a framework integrating Next Session Prediction (NSP), designed to enhance generative retrieval models for e-commerce applications. Our framework reformulation involves partitioning input samples into multi-session sequences, where each sequence comprises a session token followed by a set of item tokens, and then further incorporate multiple optimizations tailored to the generative task in retrieval scenarios. In terms of training methodology, our pipeline integrates limited historical data pre-training with stochastic partial incremental training, significantly improving training efficiency and emphasizing the superiority of data recency over sheer data volume. Our extensive experiments, conducted on public benchmarks alongside a large-scale industrial dataset from TaoBao, show TBGRecall outperforms the state-of-the-art recommendation methods, and exhibits a clear scaling law trend. Ultimately, NSP represents a significant advancement in the effectiveness of generative recommendation systems for e-commerce applications.

Shoubin Yu, Yue Zhang, Ziyang Wang et al.

Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diversity of input modalities and task complexity. For instance, medical diagnosis requires precise reasoning over structured clinical tables, while financial forecasting depends on interpreting plot-based data to make informed predictions. To tackle this challenge, we introduce MEXA, a training-free framework that performs modality- and task-aware aggregation of multiple expert models to enable effective multimodal reasoning across diverse and distinct domains. MEXA dynamically selects expert models based on the input modality and the task-specific reasoning demands (i.e., skills). Each expert model, specialized in a modality task pair, generates interpretable textual reasoning outputs. MEXA then aggregates and reasons over these outputs using a Large Reasoning Model (LRM) to produce the final answer. This modular design allows flexible and transparent multimodal reasoning across diverse domains without additional training overhead. We extensively evaluate our approach on diverse multimodal benchmarks, including Video Reasoning, Audio Reasoning, 3D Understanding, and Medical QA. MEXA consistently delivers performance improvements over strong multimodal baselines, highlighting the effectiveness and broad applicability of our expert-driven selection and aggregation in diverse multimodal reasoning tasks.

Zikai Xiao, Ziyang Wang, Wen Ma et al.

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored. From the decoding perspective, we identify the Posterior Salience Attenuation (PSA) phenomenon, where the salience ratio correlates with long-text performance degradation. Notably, despite the attenuation, gold tokens still occupy high-ranking positions in the decoding space. Motivated by it, we propose the training-free Positional Contrastive Decoding (PCD) that contrasts the logits derived from long-aware attention with those from designed local-aware attention, enabling the model to focus on the gains introduced by large-scale short-to-long training. Through the analysis of long-term decay simulation, we demonstrate that PCD effectively alleviates attention score degradation. Experimental results show that PCD achieves state-of-the-art performance on long-context benchmarks.

Ziyang Wang, Sanwoo Lee, Hsiu-Yuan Huang et al.

Prompt-based methods have achieved promising results in most few-shot text classification tasks. However, for readability assessment tasks, traditional prompt methods lackcrucial linguistic knowledge, which has already been proven to be essential. Moreover, previous studies on utilizing linguistic features have shown non-robust performance in few-shot settings and may even impair model performance.To address these issues, we propose a novel prompt-based tuning framework that incorporates rich linguistic knowledge, called Feature Prompt Tuning (FPT). Specifically, we extract linguistic features from the text and embed them into trainable soft prompts. Further, we devise a new loss function to calibrate the similarity ranking order between categories. Experimental results demonstrate that our proposed method FTP not only exhibits a significant performance improvement over the prior best prompt-based tuning approaches, but also surpasses the previous leading methods that incorporate linguistic features. Also, our proposed model significantly outperforms the large language model gpt-3.5-turbo-16k in most cases. Our proposed method establishes a new architecture for prompt tuning that sheds light on how linguistic features can be easily adapted to linguistic-related tasks.

Wen Ma, Jiaxiang Liu, Zikai Xiao et al.

Accurate 3D dental imaging is vital for diagnosis and treatment planning, yet CBCT's high radiation dose and cost limit its accessibility. Reconstructing 3D volumes from a single low-dose panoramic X-ray is a promising alternative but remains challenging due to geometric inconsistencies and limited accuracy. We propose HiCT, a two-stage framework that first generates geometrically consistent multi-view projections from a single panoramic image using a video diffusion model, and then reconstructs high-fidelity CBCT from the projections using a ray-based dynamic attention network and an X-ray sampling strategy. To support this, we built XCT, a large-scale dataset combining public CBCT data with 500 paired PX-CBCT cases. Extensive experiments show that HiCT achieves state-of-the-art performance, delivering accurate and geometrically consistent reconstructions for clinical use.

Zhihao Chen, Yiyuan Ge, Ziyang Wang

Diffusion-based visuomotor policies excel at modeling action distributions but are inference-inefficient, since recursively denoising from noise to policy requires many steps and heavy UNet backbones, which hinders deployment on resource-constrained robots. Flow matching alleviates the sampling burden by learning a one-step vector field, yet prior implementations still inherit large UNet-style architectures. In this work, we present KAN-We-Flow, a flow-matching policy that draws on recent advances in Receptance Weighted Key Value (RWKV) and Kolmogorov-Arnold Networks (KAN) from vision to build a lightweight and highly expressive backbone for 3D manipulation. Concretely, we introduce an RWKV-KAN block: an RWKV first performs efficient time/channel mixing to propagate task context, and a subsequent GroupKAN layer applies learnable spline-based, groupwise functional mappings to perform feature-wise nonlinear calibration of the action mapping on RWKV outputs. Moreover, we introduce an Action Consistency Regularization (ACR), a lightweight auxiliary loss that enforces alignment between predicted action trajectories and expert demonstrations via Euler extrapolation, providing additional supervision to stabilize training and improve policy precision. Without resorting to large UNets, our design reduces parameters by 86.8\%, maintains fast runtime, and achieves state-of-the-art success rates on Adroit, Meta-World, and DexArt benchmarks. Our project page can be viewed in \href{https://zhihaochen-2003.github.io/KAN-We-Flow.github.io/}{\textcolor{red}{link}}