arXiv subjects

Yan Zhou

Publications and source records attributed to Yan Zhou.

At least 55 records · Page 3Linked to original sources

arXiv2025

UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation

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

cs.CV↗

arXiv2025

CellScout: Visual Analytics for Mining Biomarkers in Cell State Discovery

Cell state discovery is crucial for understanding biological systems and enhancing medical outcomes. A key aspect of this process is identifying distinct biomarkers that define specific cell states. However, difficulties arise from the co-discovery process of cell states and biomarkers: biologists often use dimensionality reduction to visualize cells in a two-dimensional space. Then they usually interpret visually clustered cells as distinct states, from which they seek to identify unique biomarkers. However, this assumption is often invalid due to internal inconsistencies in a cluster, making the process trial-and-error and highly uncertain. Therefore, biologists urgently need effective tools to help uncover the hidden association relationships between different cell populations and their potential biomarkers. To address this problem, we first designed a machine-learning algorithm based on the Mixture-of-Experts (MoE) technique to identify meaningful associations between cell populations and biomarkers. We further developed a visual analytics system, CellScout, in collaboration with biologists, to help them explore and refine these association relationships to advance cell state discovery. We validated our system through expert interviews, from which we further selected a representative case to demonstrate its effectiveness in discovering new cell states.

cs.HC↗

arXiv2025

Nanofluidic logic based on chiral skyrmion flows

Particle-like chiral magnetic skyrmions can flow in nanotracks and behave like chiral fluids. Using interacting flows to perform logical operations is an important topic in microfluidics and nanofluidics. Here, we report a basic nanofluidic logic computing system based on chiral magnetic skyrmions flowing in parallel pipelines connected by an H-shaped junction. The flow behaviors could be manipulated by adjusting the spin polarization angle, which controls the intrinsic skyrmion Hall angle. We demonstrate that within certain range of the spin polarization angle, fully developed skyrmion flows could lead to fluidic logical operations, which significantly reduce the complexity of skyrmion logic as there is no need for deterministic creation, precise control, and detection of a single isolated skyrmion. Our results suggest that the chiral flow behaviors of magnetic quasiparticles may offer possibilities for spintronic and nanofluidic functions.

cond-mat.mes-hall↗

arXiv2025

POEM: Explore Unexplored Reliable Samples to Enhance Test-Time Adaptation

Test-time adaptation (TTA) aims to transfer knowledge from a source model to unknown test data with potential distribution shifts in an online manner. Many existing TTA methods rely on entropy as a confidence metric to optimize the model. However, these approaches are sensitive to the predefined entropy threshold, influencing which samples are chosen for model adaptation. Consequently, potentially reliable target samples are often overlooked and underutilized. For instance, a sample's entropy might slightly exceed the threshold initially, but fall below it after the model is updated. Such samples can provide stable supervised information and offer a normal range of gradients to guide model adaptation. In this paper, we propose a general approach, \underline{POEM}, to promote TTA via ex\underline{\textbf{p}}loring the previously unexpl\underline{\textbf{o}}red reliabl\underline{\textbf{e}} sa\underline{\textbf{m}}ples. Additionally, we introduce an extra Adapt Branch network to strike a balance between extracting domain-agnostic representations and achieving high performance on target data. Comprehensive experiments across multiple architectures demonstrate that POEM consistently outperforms existing TTA methods in both challenging scenarios and real-world domain shifts, while remaining computationally efficient. The effectiveness of POEM is evaluated through extensive analyses and thorough ablation studies. Moreover, the core idea behind POEM can be employed as an augmentation strategy to boost the performance of existing TTA approaches. The source code is publicly available at \emph{https://github.com/ycarobot/POEM}

cs.LG↗

arXiv2025

DT-NeRF: A Diffusion and Transformer-Based Optimization Approach for Neural Radiance Fields in 3D Reconstruction

This paper proposes a Diffusion Model-Optimized Neural Radiance Field (DT-NeRF) method, aimed at enhancing detail recovery and multi-view consistency in 3D scene reconstruction. By combining diffusion models with Transformers, DT-NeRF effectively restores details under sparse viewpoints and maintains high accuracy in complex geometric scenes. Experimental results demonstrate that DT-NeRF significantly outperforms traditional NeRF and other state-of-the-art methods on the Matterport3D and ShapeNet datasets, particularly in metrics such as PSNR, SSIM, Chamfer Distance, and Fidelity. Ablation experiments further confirm the critical role of the diffusion and Transformer modules in the model's performance, with the removal of either module leading to a decline in performance. The design of DT-NeRF showcases the synergistic effect between modules, providing an efficient and accurate solution for 3D scene reconstruction. Future research may focus on further optimizing the model, exploring more advanced generative models and network architectures to enhance its performance in large-scale dynamic scenes.

cs.CV↗

arXiv2025

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation

Recently, interactive digital human video generation has attracted widespread attention and achieved remarkable progress. However, building such a practical system that can interact with diverse input signals in real time remains challenging to existing methods, which often struggle with heavy computational cost and limited controllability. In this work, we introduce an autoregressive video generation framework that enables interactive multimodal control and low-latency extrapolation in a streaming manner. With minimal modifications to a standard large language model (LLM), our framework accepts multimodal condition encodings including audio, pose, and text, and outputs spatially and semantically coherent representations to guide the denoising process of a diffusion head. To support this, we construct a large-scale dialogue dataset of approximately 20,000 hours from multiple sources, providing rich conversational scenarios for training. We further introduce a deep compression autoencoder with up to 64$\times$ reduction ratio, which effectively alleviates the long-horizon inference burden of the autoregressive model. Extensive experiments on duplex conversation, multilingual human synthesis, and interactive world model highlight the advantages of our approach in low latency, high efficiency, and fine-grained multimodal controllability.

cs.CV↗

arXiv2025

Smart Charging Impact Analysis using Clustering Methods and Real-world Distribution Feeders

The anticipated widespread adoption of electric vehicles (EVs) necessitates a critical evaluation of existing power distribution infrastructures, as EV integration imposes additional stress on distribution networks that can lead to component overloading and power quality degradation. Implementing smart charging mechanisms can mitigate these adverse effects and defer or even avoid upgrades. This study assesses the performance of two smart charging strategies - Time of Use (TOU) pricing and Load Balancing (LB) on seven representative real-world feeders identified using k-means clustering. A time series-based steady-state load flow analysis was conducted on these feeders to simulate the impact of EV charging under both strategies across four different EV enrollment scenarios and three representative days to capture seasonal load characteristics. A grid upgrade strategy has been proposed to strengthen the power grid to support EV integration with minimal cost. Results demonstrate that both TOU and LB strategies effectively manage the additional EV load with reduced upgrade requirement and cost to existing infrastructure compared to the case without smart charging strategies and LB outperforms TOU when the customer enrollment levels are high. These findings support the viability of smart charging in facilitating EV integration while maintaining distribution network reliability and reducing investment cost.

eess.SY↗

arXiv2025

A Physics-Driven Neural Network with Parameter Embedding for Generating Quantitative MR Maps from Weighted Images

We propose a deep learning-based approach that integrates MRI sequence parameters to improve the accuracy and generalizability of quantitative image synthesis from clinical weighted MRI. Our physics-driven neural network embeds MRI sequence parameters -- repetition time (TR), echo time (TE), and inversion time (TI) -- directly into the model via parameter embedding, enabling the network to learn the underlying physical principles of MRI signal formation. The model takes conventional T1-weighted, T2-weighted, and T2-FLAIR images as input and synthesizes T1, T2, and proton density (PD) quantitative maps. Trained on healthy brain MR images, it was evaluated on both internal and external test datasets. The proposed method achieved high performance with PSNR values exceeding 34 dB and SSIM values above 0.92 for all synthesized parameter maps. It outperformed conventional deep learning models in accuracy and robustness, including data with previously unseen brain structures and lesions. Notably, our model accurately synthesized quantitative maps for these unseen pathological regions, highlighting its superior generalization capability. Incorporating MRI sequence parameters via parameter embedding allows the neural network to better learn the physical characteristics of MR signals, significantly enhancing the performance and reliability of quantitative MRI synthesis. This method shows great potential for accelerating qMRI and improving its clinical utility.

eess.IV↗

arXiv2025

DiffCap: Diffusion-based Real-time Human Motion Capture using Sparse IMUs and a Monocular Camera

Combining sparse IMUs and a monocular camera is a new promising setting to perform real-time human motion capture. This paper proposes a diffusion-based solution to learn human motion priors and fuse the two modalities of signals together seamlessly in a unified framework. By delicately considering the characteristics of the two signals, the sequential visual information is considered as a whole and transformed into a condition embedding, while the inertial measurement is concatenated with the noisy body pose frame by frame to construct a sequential input for the diffusion model. Firstly, we observe that the visual information may be unavailable in some frames due to occlusions or subjects moving out of the camera view. Thus incorporating the sequential visual features as a whole to get a single feature embedding is robust to the occasional degenerations of visual information in those frames. On the other hand, the IMU measurements are robust to occlusions and always stable when signal transmission has no problem. So incorporating them frame-wisely could better explore the temporal information for the system. Experiments have demonstrated the effectiveness of the system design and its state-of-the-art performance in pose estimation compared with the previous works. Our codes are available for research at https://shaohua-pan.github.io/diffcap-page.

cs.CV↗

arXiv2025

Can Multimodal Large Language Models Understand Spatial Relations?

Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or allowing questions to be answered using only the model's prior knowledge without image understanding. To address these issues, we introduce SpatialMQA, a human-annotated spatial relation reasoning benchmark based on COCO2017, which enables MLLMs to focus more on understanding images in the objective world. To ensure data quality, we design a well-tailored annotation procedure, resulting in SpatialMQA consisting of 5,392 samples. Based on this benchmark, a series of closed- and open-source MLLMs are implemented and the results indicate that the current state-of-the-art MLLM achieves only 48.14% accuracy, far below the human-level accuracy of 98.40%. Extensive experimental analyses are also conducted, suggesting the future research directions. The benchmark and codes are available at https://github.com/ziyan-xiaoyu/SpatialMQA.git.

cs.CV↗

arXiv2025

When Small Guides Large: Cross-Model Co-Learning for Test-Time Adaptation

Test-time Adaptation (TTA) adapts a given model to testing domain data with potential domain shifts through online unsupervised learning, yielding impressive performance. However, to date, existing TTA methods primarily focus on single-model adaptation. In this work, we investigate an intriguing question: how does cross-model knowledge influence the TTA process? Our findings reveal that, in TTA's unsupervised online setting, each model can provide complementary, confident knowledge to the others, even when there are substantial differences in model size. For instance, a smaller model like MobileViT (10.6M parameters) can effectively guide a larger model like ViT-Base (86.6M parameters). In light of this, we propose COCA, a Cross-Model Co-Learning framework for TTA, which mainly consists of two main strategies. 1) Co-adaptation adaptively integrates complementary knowledge from other models throughout the TTA process, reducing individual model biases. 2) Self-adaptation enhances each model's unique strengths via unsupervised learning, enabling diverse adaptation to the target domain. Extensive experiments show that COCA, which can also serve as a plug-and-play module, significantly boosts existing SOTAs, on models with various sizes--including ResNets, ViTs, and Mobile-ViTs--via cross-model co-learned TTA. For example, with Mobile-ViT's guidance, COCA raises ViT-Base's average adaptation accuracy on ImageNet-C from 51.7% to 64.5%. The code is publicly available at https://github.com/ycarobot/COCA.

cs.CV↗

arXiv2025

Ultrafast and reliable domain-wall and skyrmion logic in a chirally coupled ferrimagnet

Unlocking the spin degree of freedom in addition to the electron's charge, spin-based logic offers an in-memory computing architecture beyond-CMOS technology. Here, we encode information into chiral spin textures (e.g., chiral domain-wall and skyrmion) and achieve an ultrafast and reliable all-electrical logic by exploiting the Dzyaloshinskii-Moriya interaction-induced chiral coupling. Taking advantage of fast spin dynamics in antiferromagnetically coupled systems, we achieved a fast domain-wall motion passing through the logic gate, exceeding 1 kilometre per second, yielding an operation time of 50 picoseconds for a 50 nanometres-long logic gate. Furthermore, we present a fast logic operation with skyrmion bubbles in a racetrack that exhibits a topologically protected computation scheme. Our work demonstrates a viable approach for advanced microchips with high operation frequency and ultralow power consumption, paving the way for next-generation computing technologies.

cond-mat.mes-hall↗

arXiv2025

MamNet: A Novel Hybrid Model for Time-Series Forecasting and Frequency Pattern Analysis in Network Traffic

The abnormal fluctuations in network traffic may indicate potential security threats or system failures. Therefore, efficient network traffic prediction and anomaly detection methods are crucial for network security and traffic management. This paper proposes a novel network traffic prediction and anomaly detection model, MamNet, which integrates time-domain modeling and frequency-domain feature extraction. The model first captures the long-term dependencies of network traffic through the Mamba module (time-domain modeling), and then identifies periodic fluctuations in the traffic using Fourier Transform (frequency-domain feature extraction). In the feature fusion layer, multi-scale information is integrated to enhance the model's ability to detect network traffic anomalies. Experiments conducted on the UNSW-NB15 and CAIDA datasets demonstrate that MamNet outperforms several recent mainstream models in terms of accuracy, recall, and F1-Score. Specifically, it achieves an improvement of approximately 2% to 4% in detection performance for complex traffic patterns and long-term trend detection. The results indicate that MamNet effectively captures anomalies in network traffic across different time scales and is suitable for anomaly detection tasks in network security and traffic management. Future work could further optimize the model structure by incorporating external network event information, thereby improving the model's adaptability and stability in complex network environments.

cs.LG↗

arXiv2025

All-electric control of skyrmion-bimeron transition in van der Waals heterostructures

Two-dimensional van der Waals materials offer a versatile platform for manipulating atomic-scale topological spin textures. In this study, using first-principles and micromagnetic calculations, we demonstrate a reversible transition between magnetic skyrmions and bimerons in a MoTeI/In_2Se_3 multiferroic heterostructure. The physical origin lies in the reorientation of the easy axis of magnetic anisotropy, triggered by the reversal of ferroelectric polarization. We show that the transition operates effectively under both static and dynamic conditions, exhibiting remarkable stability and flexibility. Notably, this transition can be achieved entirely through electric control, without requiring any external magnetic field. Furthermore, we propose a binary encoding scheme based on the skyrmion-bimeron transition, presenting a promising path toward energy-efficient spintronic applications.

cond-mat.mtrl-sci↗

arXiv2025

Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model

The emergence of GPT-4o-like large multimodal models (LMMs) has raised the exploration of integrating text, vision, and speech modalities to support more flexible multimodal interaction. Existing LMMs typically concatenate representation of modalities along the sequence dimension and feed them into a large language model (LLM) backbone. While sequence-dimension concatenation is straightforward for modality integration, it often relies heavily on large-scale data to learn modality alignments. In this paper, we aim to model the relationships between modalities more purposefully, thereby achieving more efficient and flexible modality alignments. To this end, we propose Stream-Omni, a large language-vision-speech model with efficient modality alignments, which can simultaneously support interactions under various modality combinations. Stream-Omni employs LLM as the backbone and aligns the vision and speech to the text based on their relationships. For vision that is semantically complementary to text, Stream-Omni uses sequence-dimension concatenation to achieve vision-text alignment. For speech that is semantically consistent with text, Stream-Omni introduces a CTC-based layer-dimension mapping to achieve speech-text alignment. In this way, Stream-Omni can achieve modality alignments with less data (especially speech), enabling the transfer of text capabilities to other modalities. Experiments on various benchmarks demonstrate that Stream-Omni achieves strong performance on visual understanding, speech interaction, and vision-grounded speech interaction tasks. Owing to the layer-dimensional mapping, Stream-Omni can simultaneously provide intermediate text outputs (such as ASR transcriptions and model responses) during speech interaction, offering users a comprehensive multimodal experience.

cs.AI↗

arXiv2025

PBench: Workload Synthesizer with Real Statistics for Cloud Analytics Benchmarking

Cloud service providers commonly use standard benchmarks like TPC-H and TPC-DS to evaluate and optimize cloud data analytics systems. However, these benchmarks rely on fixed query patterns and fail to capture the real execution statistics of production cloud workloads. Although some cloud database vendors have recently released real workload traces, these traces alone do not qualify as benchmarks, as they typically lack essential components like the original SQL queries and their underlying databases. To overcome this limitation, this paper introduces a new problem of workload synthesis with real statistics, which aims to generate synthetic workloads that closely approximate real execution statistics, including key performance metrics and operator distributions, in real cloud workloads. To address this problem, we propose PBench, a novel workload synthesizer that constructs synthetic workloads by judiciously selecting and combining workload components (i.e., queries and databases) from existing benchmarks. This paper studies the key challenges in PBench. First, we address the challenge of balancing performance metrics and operator distributions by introducing a multi-objective optimization-based component selection method. Second, to capture the temporal dynamics of real workloads, we design a timestamp assignment method that progressively refines workload timestamps. Third, to handle the disparity between the original workload and the candidate workload, we propose a component augmentation approach that leverages large language models (LLMs) to generate additional workload components while maintaining statistical fidelity. We evaluate PBench on real cloud workload traces, demonstrating that it reduces approximation error by up to 6x compared to state-of-the-art methods.

cs.DB↗

arXiv2025

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data

Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not without its own challenges. Synthetic data produced by generative models trained on source data may inadvertently reveal information about outliers. Techniques specifically designed for preserving privacy, such as introducing noise to satisfy differential privacy, often incur unpredictable and significant losses in utility. In this work we show that, with the right mechanism of synthetic data generation, we can achieve strong privacy protection without significant utility loss. Synthetic data generators producing contracting data patterns, such as Synthetic Minority Over-sampling Technique (SMOTE), can enhance a differentially private data generator, leveraging the strengths of both. We prove in theory and through empirical demonstration that this SMOTE-DP technique can produce synthetic data that not only ensures robust privacy protection but maintains utility in downstream learning tasks.

cs.LG↗

arXiv2025

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous work has shown that current LLM-based agents execute numerous malicious tasks even without being attacked, indicating a deficiency in agentic use safety alignment during the post-training phase. To address this gap, we propose AgentAlign, a novel framework that leverages abstract behavior chains as a medium for safety alignment data synthesis. By instantiating these behavior chains in simulated environments with diverse tool instances, our framework enables the generation of highly authentic and executable instructions while capturing complex multi-step dynamics. The framework further ensures model utility by proportionally synthesizing benign instructions through non-malicious interpretations of behavior chains, precisely calibrating the boundary between helpfulness and harmlessness. Evaluation results on AgentHarm demonstrate that fine-tuning three families of open-source models using our method substantially improves their safety (35.8% to 79.5% improvement) while minimally impacting or even positively enhancing their helpfulness, outperforming various prompting methods. The dataset and code have both been open-sourced.

cs.CR↗