Kaiwen Zhang

Yongzhen Wang, Xuefeng Yan, Kaiwen Zhang et al.

Adverse weather conditions such as haze, rain, and snow often impair the quality of captured images, causing detection networks trained on normal images to generalize poorly in these scenarios. In this paper, we raise an intriguing question - if the combination of image restoration and object detection, can boost the performance of cutting-edge detectors in adverse weather conditions. To answer it, we propose an effective yet unified detection paradigm that bridges these two subtasks together via dynamic enhancement learning to discern objects in adverse weather conditions, called TogetherNet. Different from existing efforts that intuitively apply image dehazing/deraining as a pre-processing step, TogetherNet considers a multi-task joint learning problem. Following the joint learning scheme, clean features produced by the restoration network can be shared to learn better object detection in the detection network, thus helping TogetherNet enhance the detection capacity in adverse weather conditions. Besides the joint learning architecture, we design a new Dynamic Transformer Feature Enhancement module to improve the feature extraction and representation capabilities of TogetherNet. Extensive experiments on both synthetic and real-world datasets demonstrate that our TogetherNet outperforms the state-of-the-art detection approaches by a large margin both quantitatively and qualitatively. Source code is available at https://github.com/yz-wang/TogetherNet.

Jia Guo, Jiawei Du, Shengzhu Yang et al.

Current retinal foundation models remain constrained by curated research datasets that lack authentic clinical context, and require extensive task-specific optimization for each application, limiting their deployment efficiency in low-resource settings. Here, we show that these barriers can be overcome by building clinical native intelligence directly from real-world medical practice. Our key insight is that large-scale telemedicine programs, where expert centers provide remote consultations across distributed facilities, represent a natural reservoir for learning clinical image interpretation. We present ReVision, a retinal foundation model that learns from the natural alignment between 485,980 color fundus photographs and their corresponding diagnostic reports, accumulated through a decade-long telemedicine program spanning 162 medical institutions across China. Through extensive evaluation across 27 ophthalmic benchmarks, we demonstrate that ReVison enables deployment efficiency with minimal local resources. Without any task-specific training, ReVision achieves zero-shot disease detection with an average AUROC of 0.946 across 12 public benchmarks and 0.952 on 3 independent clinical cohorts. When minimal adaptation is feasible, ReVision matches extensively fine-tuned alternatives while requiring orders of magnitude fewer trainable parameters and labeled examples. The learned representations also transfer effectively to new clinical sites, imaging domains, imaging modalities, and systemic health prediction tasks. In a prospective reader study with 33 ophthalmologists, ReVision's zero-shot assistance improved diagnostic accuracy by 14.8% across all experience levels. These results demonstrate that clinical native intelligence can be directly extracted from clinical archives without any further annotation to build medical AI systems suited to various low-resource settings.

Lingdong Kong, Wesley Yang, Jianbiao Mei et al.

World modeling has become a cornerstone in AI research, enabling agents to understand, represent, and predict the dynamic environments they inhabit. While prior work largely emphasizes generative methods for 2D image and video data, they overlook the rapidly growing body of work that leverages native 3D and 4D representations such as RGB-D imagery, occupancy grids, and LiDAR point clouds for large-scale scene modeling. At the same time, the absence of a standardized definition and taxonomy for ``world models'' has led to fragmented and sometimes inconsistent claims in the literature. This survey addresses these gaps by presenting the first comprehensive review explicitly dedicated to 3D and 4D world modeling and generation. We establish precise definitions, introduce a structured taxonomy spanning video-based (VideoGen), occupancy-based (OccGen), and LiDAR-based (LiDARGen) approaches, and systematically summarize datasets and evaluation metrics tailored to 3D/4D settings. We further discuss practical applications, identify open challenges, and highlight promising research directions, aiming to provide a coherent and foundational reference for advancing the field. A systematic summary of existing literature is available at https://github.com/worldbench/survey

Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu et al.

Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon predictions and integrating trajectory planning. This is because conventional video diffusion models rely on global joint distribution modeling of fixed-length frame sequences rather than sequentially constructing localized distributions at each timestep. In this work, we propose Epona, an autoregressive diffusion world model that enables localized spatiotemporal distribution modeling through two key innovations: 1) Decoupled spatiotemporal factorization that separates temporal dynamics modeling from fine-grained future world generation, and 2) Modular trajectory and video prediction that seamlessly integrate motion planning with visual modeling in an end-to-end framework. Our architecture enables high-resolution, long-duration generation while introducing a novel chain-of-forward training strategy to address error accumulation in autoregressive loops. Experimental results demonstrate state-of-the-art performance with 7.4\% FVD improvement and minutes longer prediction duration compared to prior works. The learned world model further serves as a real-time motion planner, outperforming strong end-to-end planners on NAVSIM benchmarks. Code will be publicly available at \href{https://github.com/Kevin-thu/Epona/}{https://github.com/Kevin-thu/Epona/}.

Xinzhe Zheng, Sijie Ji, Yipeng Pan et al.

Inertial tracking is vital for robotic IoT and has gained popularity thanks to the ubiquity of low-cost inertial measurement units and deep learning-powered tracking algorithms. Existing works, however, have not fully utilized IMU measurements, particularly magnetometers, nor have they maximized the potential of deep learning to achieve the desired accuracy. To address these limitations, we introduce NeurIT, which elevates tracking accuracy to a new level. NeurIT employs a Time-Frequency Block-recurrent Transformer (TF-BRT) at its core, combining both RNN and Transformer to learn representative features in both time and frequency domains. To fully utilize IMU information, we strategically employ body-frame differentiation of magnetometers, considerably reducing the tracking error. We implement NeurIT on a customized robotic platform and conduct evaluation in various indoor environments. Experimental results demonstrate that NeurIT achieves a mere 1-meter tracking error over a 300-meter distance. Notably, it significantly outperforms state-of-the-art baselines by 48.21% on unseen data. Moreover, NeurIT demonstrates robustness in large urban complexes and performs comparably to the visual-inertial approach (Tango Phone) in vision-favored conditions while surpassing it in feature-sparse settings. We believe NeurIT takes an important step forward toward practical neural inertial tracking for ubiquitous and scalable tracking of robotic things. NeurIT is open-sourced here: https://github.com/aiot-lab/NeurIT.

Kaiwen Zhang, Liming Jiang, Angtian Wang et al.

Visual storytelling requires generating multi-shot videos with cinematic quality and long-range consistency. Inspired by human memory, we propose StoryMem, a paradigm that reformulates long-form video storytelling as iterative shot synthesis conditioned on explicit visual memory, transforming pre-trained single-shot video diffusion models into multi-shot storytellers. This is achieved by a novel Memory-to-Video (M2V) design, which maintains a compact and dynamically updated memory bank of keyframes from historical generated shots. The stored memory is then injected into single-shot video diffusion models via latent concatenation and negative RoPE shifts with only LoRA fine-tuning. A semantic keyframe selection strategy, together with aesthetic preference filtering, further ensures informative and stable memory throughout generation. Moreover, the proposed framework naturally accommodates smooth shot transitions and customized story generation applications. To facilitate evaluation, we introduce ST-Bench, a diverse benchmark for multi-shot video storytelling. Extensive experiments demonstrate that StoryMem achieves superior cross-shot consistency over previous methods while preserving high aesthetic quality and prompt adherence, marking a significant step toward coherent minute-long video storytelling.

Kaiwen Zhang, Yifan Zhou, Xudong Xu et al.

Diffusion models have achieved remarkable image generation quality surpassing previous generative models. However, a notable limitation of diffusion models, in comparison to GANs, is their difficulty in smoothly interpolating between two image samples, due to their highly unstructured latent space. Such a smooth interpolation is intriguing as it naturally serves as a solution for the image morphing task with many applications. In this work, we present DiffMorpher, the first approach enabling smooth and natural image interpolation using diffusion models. Our key idea is to capture the semantics of the two images by fitting two LoRAs to them respectively, and interpolate between both the LoRA parameters and the latent noises to ensure a smooth semantic transition, where correspondence automatically emerges without the need for annotation. In addition, we propose an attention interpolation and injection technique and a new sampling schedule to further enhance the smoothness between consecutive images. Extensive experiments demonstrate that DiffMorpher achieves starkly better image morphing effects than previous methods across a variety of object categories, bridging a critical functional gap that distinguished diffusion models from GANs.

Michael Duchesne, Kaiwen Zhang, Chamseddine Talhi

Federated Learning (FL) has emerged as a prominent privacy-preserving technique for enabling use cases like confidential clinical machine learning. FL operates by aggregating models trained by remote devices which owns the data. Thus, FL enables the training of powerful global models using crowd-sourced data from a large number of learners, without compromising their privacy. However, the aggregating server is a single point of failure when generating the global model. Moreover, the performance of the model suffers when the data is not independent and identically distributed (non-IID data) on all remote devices. This leads to vastly different models being aggregated, which can reduce the performance by as much as 50% in certain scenarios. In this paper, we seek to address the aforementioned issues while retaining the benefits of FL. We propose MultiConfederated Learning: a decentralized FL framework which is designed to handle non-IID data. Unlike traditional FL, MultiConfederated Learning will maintain multiple models in parallel (instead of a single global model) to help with convergence when the data is non-IID. With the help of transfer learning, learners can converge to fewer models. In order to increase adaptability, learners are allowed to choose which updates to aggregate from their peers.

Kaiwen Zhang, Guanjun Liu

Recovering concurrency structure directly from source code is difficult because shared-resource identity and protection relations are often obscured by aliasing, ownership, and API-specific idioms. We therefore study a specification-driven, model-first verification architecture for LLM-assisted concurrent program construction. Instead of verifying arbitrary source code, a large language model first synthesizes a verification-oriented concurrency artifact from a natural-language requirement or system specification. The first formalism, the Concurrency Intermediate Representation (Cir), is a statement-level, alias-free model in which shared resources are globally named, protection relations are explicit, and each statement carries a stable identifier. The second formalism, the Concurrency Verification Net (Cvn), is a weighted place/transition Petri net with a finite global store and three-valued guards for data-dependent branching. A validated Cir artifact is translated mechanically to Cvn, explored exhaustively, and any counterexample is mapped back to statement identifiers to guide targeted repair. To reduce the risk of bug-free but behavior-dropping repairs, acceptance additionally applies a lightweight goal-reachability check over designated critical outcomes. We formalize both representations, prove translation-correspondence results for deadlock and signal-loss analysis, define a two-layer checking architecture with 61 static rules and 5 analysis predicates, and evaluate the pipeline on 9 representative bounded-concurrency patterns. The results show that the method supports iterative bug detection and repair on Cir artifacts and that goal reachability helps filter semantically incomplete repairs. The trust boundary of the present work is the generated Cir artifact rather than arbitrary source code.

Kaiwen Zhang, Guanjun Liu

Safe Rust guarantees memory safety through strict compile-time constraints: ownership can be transferred, borrowing can temporarily guarantee either shared read-only or exclusive write access, and ownership and borrowing are scoped by lifetime. Automatically synthesizing correct and safe Rust code is challenging, as the generated code must not only satisfy ownership, borrowing, and lifetime constraints, but also meet type and interface requirements at compile time. This work proposes a synthesis method based on our newly defined Pushdown Colored Petri Net (PCPN) that models these compilation constraints directly from public API signatures to synthesize valid call sequences. Token colors encode dynamic resource states together with a scope level indicating the lifetime region in which a borrow is valid. The pushdown stack tracks the entering or leaving of lifetime parameter via pushing and popping tokens. A transition is enabled only when type matching and interface obligations both hold and the required resource states are available. Based on the bisimulation theory, we prove that the enabling and firing rules of PCPN are consistent with the compile-time check of these three constraints. We develop an automatic synthesis tool based on PCPN and the experimental results show that the synthesized codes are all correct.

Yanlin Li, Minghui Guo, Kaiwen Zhang et al.

In real-world multimodal applications, systems usually need to comprehend arbitrarily combined and interleaved multimodal inputs from users, while also generating outputs in any interleaved multimedia form. This capability defines the goal of any-to-any interleaved multimodal learning under a unified paradigm of understanding and generation, posing new challenges and opportunities for advancing Multimodal Large Language Models (MLLMs). To foster and benchmark this capability, this paper introduces the UniM benchmark, the first Unified Any-to-Any Interleaved Multimodal dataset. UniM contains 31K high-quality instances across 30 domains and 7 representative modalities: text, image, audio, video, document, code, and 3D, each requiring multiple intertwined reasoning and generation capabilities. We further introduce the UniM Evaluation Suite, which assesses models along three dimensions: Semantic Correctness & Generation Quality, Response Structure Integrity, and Interleaved Coherence. In addition, we propose UniMA, an agentic baseline model equipped with traceable reasoning for structured interleaved generation. Comprehensive experiments demonstrate the difficulty of UniM and highlight key challenges and directions for advancing unified any-to-any multimodal intelligence. The project page is https://any2any-mllm.github.io/unim.

Xiaoqing Liu, Jitai Han, Hua Yan et al.

Placental abruption is a severe complication during pregnancy, and its early accurate diagnosis is crucial for ensuring maternal and fetal safety. Traditional ultrasound diagnostic methods heavily rely on physician experience, leading to issues such as subjective bias and diagnostic inconsistencies. This paper proposes an improved model, EH-YOLOv11n (Enhanced Hemorrhage-YOLOv11n), based on small-sample learning, aiming to achieve automatic detection of hematoma features in placental ultrasound images. The model enhances performance through multidimensional optimization: it integrates wavelet convolution and coordinate convolution to strengthen frequency and spatial feature extraction; incorporates a cascaded group attention mechanism to suppress ultrasound artifacts and occlusion interference, thereby improving bounding box localization accuracy. Experimental results demonstrate a detection accuracy of 78%, representing a 2.5% improvement over YOLOv11n and a 13.7% increase over YOLOv8. The model exhibits significant superiority in precision-recall curves, confidence scores, and occlusion scenarios. Combining high accuracy with real-time processing, this model provides a reliable solution for computer-aided diagnosis of placental abruption, holding significant clinical application value.

Narasimha Raghavan Veeraragavan, Kaiwen Zhang

Sharding has emerged as one of the common techniques to address the scalability problems of blockchain systems. To this end, various sharding techniques for blockchain systems have been proposed in the literature. When sharded blockchains process personal data, the data controllers and the data processors associated with the sharded blockchains need to be compliant with the General Data Protection Regulation (GDPR). To this end, this article makes the first attempt to address the following key question: to what extent the existing techniques developed by different communities such as the distributed computing community, the distributed systems community, the database community, identity and access control community and the dependability community can be used by the data controllers and data processors for complying with the GDPR requirements of data subject rights in sharded blockchains? As part of answering this question, this article argues that there is a need for cross-disciplinary research towards finding optimal solutions for implementing the data subject rights in sharded blockchains.