arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 361 records · Page 20Linked to original sources

arXiv2025

Can Test-Time Scaling Improve World Foundation Model?

World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical intelligence, including autonomous driving and robotics. However, these models require substantial computational resources for pretraining and are further constrained by available data during post-training. As such, scaling computation at test time emerges as both a critical and practical alternative to traditional model enlargement or re-training. In this work, we introduce SWIFT, a test-time scaling framework tailored for WFMs. SWIFT integrates our extensible WFM evaluation toolkit with process-level inference strategies, including fast tokenization, probability-based Top-K pruning, and efficient beam search. Empirical results on the COSMOS model demonstrate that test-time scaling exists even in a compute-optimal way. Our findings reveal that test-time scaling laws hold for WFMs and that SWIFT provides a scalable and effective pathway for improving WFM inference without retraining or increasing model size. Project page: https://scalingwfm.github.io/.

cs.CV↗

arXiv2025

Heterogeneous optimized Schwarz Methods for heat conduction in composites with thermal contact resistance

Heat transfer in composites is critical in engineering, where imperfect layer contact causes thermal contact resistance (TCR), leading to interfacial temperature discontinuity. We propose solving this numerically using the optimized Schwarz method (OSM), which decouples the heterogeneous problem into homogeneous subproblems. This avoids ill-conditioned systems from monolithic solving due to high contrast and interface jumps. Both energy estimate and Fourier analysis are used to prove the convergence of this algorithm when the standard Robin condition is applied to transmit information between subdomains. To achieve fast convergence, instead of the standard Robin, the scaled Robin transmission condition is proposed, and the involved free parameter is rigorously optimized. The results reveal several new findings due to the presence of TCR: first, the larger the TCR, the faster the OSM converges; second, mesh-independent convergence is achieved in the asymptotic sense, in contrast to the mesh-dependent results without TCR; and last, the heterogeneity contrast benefits the convergence, with a larger contrast leading to faster convergence. Interestingly, different from the case without TCR, the thermal conductivity also benefits the convergence, similar to the effect of heterogeneity. Numerical experiments confirm the theoretical findings and demonstrate the method's potential for nonlinear problems on irregular domains.

math.NA↗

arXiv2025

Efficient Multi-Slide Visual-Language Feature Fusion for Placental Disease Classification

Accurate prediction of placental diseases via whole slide images (WSIs) is critical for preventing severe maternal and fetal complications. However, WSI analysis presents significant computational challenges due to the massive data volume. Existing WSI classification methods encounter critical limitations: (1) inadequate patch selection strategies that either compromise performance or fail to sufficiently reduce computational demands, and (2) the loss of global histological context resulting from patch-level processing approaches. To address these challenges, we propose an Efficient multimodal framework for Patient-level placental disease Diagnosis, named EmmPD. Our approach introduces a two-stage patch selection module that combines parameter-free and learnable compression strategies, optimally balancing computational efficiency with critical feature preservation. Additionally, we develop a hybrid multimodal fusion module that leverages adaptive graph learning to enhance pathological feature representation and incorporates textual medical reports to enrich global contextual understanding. Extensive experiments conducted on both a self-constructed patient-level Placental dataset and two public datasets demonstrating that our method achieves state-of-the-art diagnostic performance. The code is available at https://github.com/ECNU-MultiDimLab/EmmPD.

cs.CV↗

arXiv2025

Generalized Turan number with given size

Generalized Turán problem with given size, denoted as $\mathrm{mex}(m,K_r,F)$, determines the maximum number of $K_r$-copies in an $F$-free graph with $m$ edges. We prove that for $r\ge 3$ and $α\in(\frac 2 r,1]$, any graph $G$ with $m$ edges and $Ω(m^{\frac{αr}{2}})$ $K_r$-copies has a subgraph of order $n_0=Ω(m^\fracα{2})$, which contains $Ω(n_0^{\frac{i(r-2)α}{(2-α)r-2}})$ $K_i$-copies for each $i = 2, \ldots, r$. This implies an upper bound of $\mathrm{mex}(m, K_r, F)$ when an upper bound of $\mathrm{ex}(n,K_r,F)$ is known. Furthermore, we establish an improved upper bound of $\mathrm{mex}(m, K_r, F)$ by $\mathrm{ex}(n, F)$ and $\min_{v_0 \in V(F)} \mathrm{ex}(n, K_r, F - v_0)$. As a corollary, we show $\mathrm{mex}(m, K_r, K_{s,t}) = Θ( m^{\frac{rs - \binom{r}{2}}{2s-1}} )$ for $r \geq 3$, $s \geq 2r-2$ and $t \geq (s-1)! + 1$, and obtain non-trivial bounds for other graph classes such as complete $r$-partite graphs and $K_s \vee C_\ell$, etc.

math.CO↗

arXiv2025

MamV2XCalib: V2X-based Target-less Infrastructure Camera Calibration with State Space Model

As cooperative systems that leverage roadside cameras to assist autonomous vehicle perception become increasingly widespread, large-scale precise calibration of infrastructure cameras has become a critical issue. Traditional manual calibration methods are often time-consuming, labor-intensive, and may require road closures. This paper proposes MamV2XCalib, the first V2X-based infrastructure camera calibration method with the assistance of vehicle-side LiDAR. MamV2XCalib only requires autonomous vehicles equipped with LiDAR to drive near the cameras to be calibrated in the infrastructure, without the need for specific reference objects or manual intervention. We also introduce a new targetless LiDAR-camera calibration method, which combines multi-scale features and a 4D correlation volume to estimate the correlation between vehicle-side point clouds and roadside images. We model the temporal information and estimate the rotation angles with Mamba, effectively addressing calibration failures in V2X scenarios caused by defects in the vehicle-side data (such as occlusions) and large differences in viewpoint. We evaluate MamV2XCalib on the V2X-Seq and TUMTraf-V2X real-world datasets, demonstrating the effectiveness and robustness of our V2X-based automatic calibration approach. Compared to previous LiDAR-camera methods designed for calibration on one car, our approach achieves better and more stable calibration performance in V2X scenarios with fewer parameters. The code is available at https://github.com/zhuyaoye/MamV2XCalib.

cs.CV↗

arXiv2025

EventVAD: Training-Free Event-Aware Video Anomaly Detection

Video Anomaly Detection~(VAD) focuses on identifying anomalies within videos. Supervised methods require an amount of in-domain training data and often struggle to generalize to unseen anomalies. In contrast, training-free methods leverage the intrinsic world knowledge of large language models (LLMs) to detect anomalies but face challenges in localizing fine-grained visual transitions and diverse events. Therefore, we propose EventVAD, an event-aware video anomaly detection framework that combines tailored dynamic graph architectures and multimodal LLMs through temporal-event reasoning. Specifically, EventVAD first employs dynamic spatiotemporal graph modeling with time-decay constraints to capture event-aware video features. Then, it performs adaptive noise filtering and uses signal ratio thresholding to detect event boundaries via unsupervised statistical features. The statistical boundary detection module reduces the complexity of processing long videos for MLLMs and improves their temporal reasoning through event consistency. Finally, it utilizes a hierarchical prompting strategy to guide MLLMs in performing reasoning before determining final decisions. We conducted extensive experiments on the UCF-Crime and XD-Violence datasets. The results demonstrate that EventVAD with a 7B MLLM achieves state-of-the-art (SOTA) in training-free settings, outperforming strong baselines that use 7B or larger MLLMs.

cs.CV↗

arXiv2025

Ultra-clean interface between high k dielectric and 2D MoS2

Atomically thin transition metal dichalcogenides (TMDs) are promising candidates for next-generation transistor channels due to their superior scaling properties. However, the integration of ultra-thin gate dielectrics remains a challenge, as conventional oxides such as SiO2, Al2O3, and HfO2 tend to unintentionally dope 2D TMDs and introduce interfacial defect states, leading to undesirable field-effect transistor (FET) performance and unstable threshold voltages. Here, we demonstrate that zirconium oxide (ZrO2), a high-k dielectric compatible with semiconductor processing, forms an ultra-clean interface with monolayer MoS2. Using soft and hard X-ray photoelectron spectroscopy and density functional theory, we find that ZrO2 does not measurably interact with MoS2, in contrast to significant doping observed for SiO2 and HfO2 substrates. As a result, back-gated monolayer MoS2 FETs fabricated with ZrO2 dielectrics exhibit stable and positive threshold voltages (0.36 plus/minus 0.3 V), low subthreshold swing (75 mV per decade), and high ON currents exceeding 400 microamperes. We further demonstrate p-type WSe2 FETs with ON currents greater than 200 microamperes per micrometer by suppressing electron doping with ZrO2 dielectrics. Atomic-resolution imaging confirms a defect-free ZrO2/MoS2 interface, which enables top-gate FETs with an equivalent oxide thickness of 0.86 nanometers and subthreshold swing of 80 mV per decade. Moreover, the ultraclean ZrO2/MoS2 interface allows for effective threshold voltage modulation in top-gate FETs via gate metal work function engineering. These findings establish ZrO2 as a highly promising, industry-compatible high-k dielectric for scalable 2D TMD-based electronics.

cond-mat.mtrl-sci↗

arXiv2025

Phase-selective tripartite entanglement and asymmetric Einstein-Podolsky-Rosen steering in squeezed optomechanics

The generation and manipulation of multipartite entanglement and EPR steering in macroscopic systems not only play a fundamental role in exploring the nature of quantum mechanics, but are also at the core of current developments of various nascent quantum technologies. Here we report a theoretical method using squeezing-phase-controlled quantum noise flows to selectively generate and manipulate quantum entanglement and asymmetric EPR steering in a nonlinear $χ^{(2)}$ whispering-gallery-mode (WGM) optomechanical resonator. We show that by pumping the $χ^{(2)}$ nonlinear medium with two-photon optical fields and broadband squeezed lights, a pair of counterpropagating squeezed optical modes could be introduced to the WGM resonator, each coupled with an independent squeezed vacuum reservoir. This configuration could enable squeezing-phase-controlled light-reservoir interaction for each squeezed optical mode, providing a flexible tool for tailoring asymmetric optical noise flows in the counterpropagating modes. Based on this unique feature, it is found that with the injection of asymmetric noise flows, the generation of various types of bipartite and tripartite entanglement become phase-dependent and thus they can be produced in an asymmetric way. More excitingly, it is also found that by further properly adjusting the squeezing parameters, the overall asymmetry of EPR steering can also be stepwise driven from no-way regime, one-way regime to two-way regime. These findings, holding promise for preparing rich types of entangled quantum resources with asymmetric features, may have potential applications in the area of secure quantum information processing such as quantum secure direct communication and one-way quantum computing.

quant-ph↗

arXiv2025

MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes

4D Gaussian Splatting (4DGS) has recently emerged as a promising technique for capturing complex dynamic 3D scenes with high fidelity. It utilizes a 4D Gaussian representation and a GPU-friendly rasterizer, enabling rapid rendering speeds. Despite its advantages, 4DGS faces significant challenges, notably the requirement of millions of 4D Gaussians, each with extensive associated attributes, leading to substantial memory and storage cost. This paper introduces a memory-efficient framework for 4DGS. We streamline the color attribute by decomposing it into a per-Gaussian direct color component with only 3 parameters and a shared lightweight alternating current color predictor. This approach eliminates the need for spherical harmonics coefficients, which typically involve up to 144 parameters in classic 4DGS, thereby creating a memory-efficient 4D Gaussian representation. Furthermore, we introduce an entropy-constrained Gaussian deformation technique that uses a deformation field to expand the action range of each Gaussian and integrates an opacity-based entropy loss to limit the number of Gaussians, thus forcing our model to use as few Gaussians as possible to fit a dynamic scene well. With simple half-precision storage and zip compression, our framework achieves a storage reduction by approximately 190$\times$ and 125$\times$ on the Technicolor and Neural 3D Video datasets, respectively, compared to the original 4DGS. Meanwhile, it maintains comparable rendering speeds and scene representation quality, setting a new standard in the field. Code is available at https://github.com/Xinjie-Q/MEGA.

cs.CV↗

arXiv2025

A High Magnifications Histopathology Image Dataset for Oral Squamous Cell Carcinoma Diagnosis and Prognosis

Oral Squamous Cell Carcinoma (OSCC) is a prevalent and aggressive malignancy where deep learning-based computer-aided diagnosis and prognosis can enhance clinical assessments.However, existing publicly available OSCC datasets often suffer from limited patient cohorts and a restricted focus on either diagnostic or prognostic tasks, limiting the development of comprehensive and generalizable models. To bridge this gap, we introduce Multi-OSCC, a new histopathology image dataset comprising 1,325 OSCC patients, integrating both diagnostic and prognostic information to expand existing public resources. Each patient is represented by six high resolution histopathology images captured at x200, x400, and x1000 magnifications-two per magnification-covering both the core and edge tumor regions.The Multi-OSCC dataset is richly annotated for six critical clinical tasks: recurrence prediction (REC), lymph node metastasis (LNM), tumor differentiation (TD), tumor invasion (TI), cancer embolus (CE), and perineural invasion (PI). To benchmark this dataset, we systematically evaluate the impact of different visual encoders, multi-image fusion techniques, stain normalization, and multi-task learning frameworks. Our analysis yields several key insights: (1) The top-performing models achieve excellent results, with an Area Under the Curve (AUC) of 94.72% for REC and 81.23% for TD, while all tasks surpass 70% AUC; (2) Stain normalization benefits diagnostic tasks but negatively affects recurrence prediction; (3) Multi-task learning incurs a 3.34% average AUC degradation compared to single-task models in our multi-task benchmark, underscoring the challenge of balancing multiple tasks in our dataset. To accelerate future research, we publicly release the Multi-OSCC dataset and baseline models at https://github.com/guanjinquan/OSCC-PathologyImageDataset.

eess.IV↗

arXiv2025

Efficient Multi-Camera Tokenization with Triplanes for End-to-End Driving

Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization. Accordingly, tokenizing sensor data efficiently is paramount to ensuring the real-time feasibility of such architectures on embedded hardware. To this end, we present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D neural reconstruction and rendering to produce sensor tokens that are agnostic to the number of input cameras and their resolution, while explicitly accounting for their geometry around an AV. Experiments on a large-scale AV dataset and state-of-the-art neural simulator demonstrate that our approach yields significant savings over current image patch-based tokenization strategies, producing up to 72% fewer tokens, resulting in up to 50% faster policy inference while achieving the same open-loop motion planning accuracy and improved offroad rates in closed-loop driving simulations.

cs.CV↗

arXiv2025

DNN-based Methods of Jointly Sensing Number and Directions of Targets via a Green Massive H2AD MIMO Receiver

As a green MIMO structure, the heterogeneous hybrid analog-digital H2AD MIMO architecture has been shown to own a great potential to replace the massive or extremely large-scale fully-digital MIMO in the future wireless networks to address the three challenging problems faced by the latter: high energy consumption, high circuit cost, and high complexity. However, how to intelligently sense the number and direction of multi-emitters via such a structure is still an open hard problem. To address this, we propose a two-stage sensing framework that jointly estimates the number and direction values of multiple targets. Specifically, three target number sensing methods are designed: an improved eigen-domain clustering (EDC) framework, an enhanced deep neural network (DNN) based on five key statistical features, and an improved one-dimensional convolutional neural network (1D-CNN) utilizing full eigenvalues. Subsequently, a low-complexity and high-accuracy DOA estimation is achieved via the introduced online micro-clustering (OMC-DOA) method. Furthermore, we derive the Cramér-Rao lower bound (CRLB) for the H2AD under multiple-source conditions as a theoretical performance benchmark. Simulation results show that the developed three methods achieve 100\% number of targets sensing at moderate-to-high SNRs, while the improved 1D-CNN exhibits superior under extremely-low SNR conditions. The introduced OMC-DOA outperforms existing clustering and fusion-based DOA methods in multi-source environments.

eess.SP↗

arXiv2025

E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models

Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enabler is the real-time, accurate estimation of core 3D attributes (camera parameters, point clouds, depth maps, and 3D point tracks) from unstructured or streaming imagery. Inspired by the success of large foundation models in language and 2D vision, a new class of end-to-end 3D geometric foundation models (GFMs) has emerged, directly predicting dense 3D representations in a single feed-forward pass, eliminating the need for slow or unavailable precomputed camera parameters. Since late 2023, the field has exploded with diverse variants, but systematic evaluation is lacking. In this work, we present the first comprehensive benchmark for 3D GFMs, covering five core tasks: sparse-view depth estimation, video depth estimation, 3D reconstruction, multi-view pose estimation, novel view synthesis, and spanning both standard and challenging out-of-distribution datasets. Our standardized toolkit automates dataset handling, evaluation protocols, and metric computation to ensure fair, reproducible comparisons. We evaluate 16 state-of-the-art GFMs, revealing their strengths and limitations across tasks and domains, and derive key insights to guide future model scaling and optimization. All code, evaluation scripts, and processed data will be publicly released to accelerate research in 3D spatial intelligence.

cs.CV↗

arXiv2025

Omni-Fusion of Spatial and Spectral for Hyperspectral Image Segmentation

Medical Hyperspectral Imaging (MHSI) has emerged as a promising tool for enhanced disease diagnosis, particularly in computational pathology, offering rich spectral information that aids in identifying subtle biochemical properties of tissues. Despite these advantages, effectively fusing both spatial-dimensional and spectral-dimensional information from MHSIs remains challenging due to its high dimensionality and spectral redundancy inherent characteristics. To solve the above challenges, we propose a novel spatial-spectral omni-fusion network for hyperspectral image segmentation, named as Omni-Fuse. Here, we introduce abundant cross-dimensional feature fusion operations, including a cross-dimensional enhancement module that refines both spatial and spectral features through bidirectional attention mechanisms, a spectral-guided spatial query selection to select the most spectral-related spatial feature as the query, and a two-stage cross-dimensional decoder which dynamically guide the model to focus on the selected spatial query. Despite of numerous attention blocks, Omni-Fuse remains efficient in execution. Experiments on two microscopic hyperspectral image datasets show that our approach can significantly improve the segmentation performance compared with the state-of-the-art methods, with over 5.73 percent improvement in DSC. Code available at: https://github.com/DeepMed-Lab-ECNU/Omni-Fuse.

cs.CV↗

arXiv2025

HiLa: Hierarchical Vision-Language Collaboration for Cancer Survival Prediction

Survival prediction using whole-slide images (WSIs) is crucial in cancer re-search. Despite notable success, existing approaches are limited by their reliance on sparse slide-level labels, which hinders the learning of discriminative repre-sentations from gigapixel WSIs. Recently, vision language (VL) models, which incorporate additional language supervision, have emerged as a promising solu-tion. However, VL-based survival prediction remains largely unexplored due to two key challenges. First, current methods often rely on only one simple lan-guage prompt and basic cosine similarity, which fails to learn fine-grained associ-ations between multi-faceted linguistic information and visual features within WSI, resulting in inadequate vision-language alignment. Second, these methods primarily exploit patch-level information, overlooking the intrinsic hierarchy of WSIs and their interactions, causing ineffective modeling of hierarchical interac-tions. To tackle these problems, we propose a novel Hierarchical vision-Language collaboration (HiLa) framework for improved survival prediction. Specifically, HiLa employs pretrained feature extractors to generate hierarchical visual features from WSIs at both patch and region levels. At each level, a series of language prompts describing various survival-related attributes are constructed and aligned with visual features via Optimal Prompt Learning (OPL). This ap-proach enables the comprehensive learning of discriminative visual features cor-responding to different survival-related attributes from prompts, thereby improv-ing vision-language alignment. Furthermore, we introduce two modules, i.e., Cross-Level Propagation (CLP) and Mutual Contrastive Learning (MCL) to maximize hierarchical cooperation by promoting interactions and consistency be-tween patch and region levels. Experiments on three TCGA datasets demonstrate our SOTA performance.

cs.CV↗

arXiv2025

In-Context Meta LoRA Generation

Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms of storage and inference. Moreover, existing parameter generation methods fail to capture the correlations among these tasks, making multi-task LoRA parameter generation challenging. To address these limitations, we propose In-Context Meta LoRA (ICM-LoRA), a novel approach that efficiently achieves task-specific customization of large language models (LLMs). Specifically, we use training data from all tasks to train a tailored generator, Conditional Variational Autoencoder (CVAE). CVAE takes task descriptions as inputs and produces task-aware LoRA weights as outputs. These LoRA weights are then merged with LLMs to create task-specialized models without the need for additional fine-tuning. Furthermore, we utilize in-context meta-learning for knowledge enhancement and task mapping, to capture the relationship between tasks and parameter distributions. As a result, our method achieves more accurate LoRA parameter generation for diverse tasks using CVAE. ICM-LoRA enables more accurate LoRA parameter reconstruction than current parameter reconstruction methods and is useful for implementing task-specific enhancements of LoRA parameters. At the same time, our method occupies 283MB, only 1\% storage compared with the original LoRA.

cs.CL↗

arXiv2025

Multimodal, Multi-Disease Medical Imaging Foundation Model (MerMED-FM)

Current artificial intelligence models for medical imaging are predominantly single modality and single disease. Attempts to create multimodal and multi-disease models have resulted in inconsistent clinical accuracy. Furthermore, training these models typically requires large, labour-intensive, well-labelled datasets. We developed MerMED-FM, a state-of-the-art multimodal, multi-specialty foundation model trained using self-supervised learning and a memory module. MerMED-FM was trained on 3.3 million medical images from over ten specialties and seven modalities, including computed tomography (CT), chest X-rays (CXR), ultrasound (US), pathology patches, color fundus photography (CFP), optical coherence tomography (OCT) and dermatology images. MerMED-FM was evaluated across multiple diseases and compared against existing foundational models. Strong performance was achieved across all modalities, with AUROCs of 0.988 (OCT); 0.982 (pathology); 0.951 (US); 0.943 (CT); 0.931 (skin); 0.894 (CFP); 0.858 (CXR). MerMED-FM has the potential to be a highly adaptable, versatile, cross-specialty foundation model that enables robust medical imaging interpretation across diverse medical disciplines.

eess.IV↗

arXiv2025

Privacy-Preserving Video Anomaly Detection: A Survey

Video Anomaly Detection (VAD) aims to automatically analyze spatiotemporal patterns in surveillance videos collected from open spaces to detect anomalous events that may cause harm, such as fighting, stealing, and car accidents. However, vision-based surveillance systems such as closed-circuit television often capture personally identifiable information. The lack of transparency and interpretability in video transmission and usage raises public concerns about privacy and ethics, limiting the real-world application of VAD. Recently, researchers have focused on privacy concerns in VAD by conducting systematic studies from various perspectives including data, features, and systems, making Privacy-Preserving Video Anomaly Detection (P2VAD) a hotspot in the AI community. However, current research in P2VAD is fragmented, and prior reviews have mostly focused on methods using RGB sequences, overlooking privacy leakage and appearance bias considerations. To address this gap, this article is the first to systematically reviews the progress of P2VAD, defining its scope and providing an intuitive taxonomy. We outline the basic assumptions, learning frameworks, and optimization objectives of various approaches, analyzing their strengths, weaknesses, and potential correlations. Additionally, we provide open access to research resources such as benchmark datasets and available code. Finally, we discuss key challenges and future opportunities from the perspectives of AI development and P2VAD deployment, aiming to guide future work in the field.

cs.CV↗