Searcharxiv⌕ Search

arXiv subjects

Yingjie Chen

Publications and source records attributed to Yingjie Chen.

At least 19 recordsLinked to original sources
arXiv2026

MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery

Monocular 3D hand and body mesh recovery often suffers from severe occlusion and ambiguity. Traditional deterministic methods typically regress a single optimal solution, leading to overconfident predictions. In this paper, we introduce an exploration--exploitation paradigm for ambiguous mesh recovery with multi-hypothesis learning and selection. Specifically, during exploration, based on our probabilistic formulation and entropy maximization, we propose a novel multi-hypothesis method referred to as MHE-Former. It is a Transformer-based multi-hypothesis framework, ensuring high training efficiency and label friendliness while generating plausible and diverse hypotheses. During exploitation, we propose Hypothesis Selection, a context-aware process for multiple predictions. Especially leveraging VLM's powerful visual understanding and reasoning capabilities, it allows users to choose the most plausible and desired estimate with additional evidence and natural language intent. Extensive experiments demonstrate that our framework achieves state-of-the-art performance in accuracy and diversity across multiple datasets. The user preference study further shows the practicality of our hypothesis selection process.

cs.CV↗
arXiv2026

Dual-decomposition multi-GPU particle-in-cell method for cylindrical plasmas: Batched Fourier-mode multigrid and balanced particle slabs

Three-dimensional electrostatic particle-in-cell (PIC) simulations combine irregular particle operations with a globally coupled Poisson solve, whose preferred parallel decompositions conflict. We introduce a dual-decomposition multi-GPU method: complete azimuthal Fourier modes are owned during the field solve, whereas spatial slabs own particles. Exact full-spectrum diagonalization and batched matrix-free geometric multigrid keep collectives outside the V-cycle, after which every GPU reconstructs the full field. Peer migration, cell reordering, warp-aggregated deposition, and capacity-constrained dynamic cuts restore particle locality and balance. CPU/GPU Poisson solutions agree to relative L2 errors below 6.9e-16; all 65 physical modes on eight V100 GPUs are solved in 9.350 ms with relative errors below 8.2e-15. For an identical 512*128*400 problem containing 707,788,800 particles per species, the complete PIC loop reaches 0.149108 s per step and strong-scales from five to eight GPUs with 91.81% efficiency. A separate cross-resolution production study shows approximately threefold aggregate particle-update and Poisson-cell throughput relative to a single RTX 5090 calculation; this measures refined-problem capability rather than a hardware speedup or formal convergence order.

physics.plasm-ph↗
arXiv2026

AlgoPlasma: Open Algorithms for Plasma Modeling

AlgoPlasma is an open-source library in which core numerical algorithms for plasma modeling are implemented as modular, well-documented, and independently testable components. Rather than offering a complete simulation code, it allows researchers to select, adapt, and assemble the required components into application-specific workflows. The current release is centered on particle-based simulation, while AlgoPlasma is designed to encompass a broader range of approaches to plasma modeling. It provides components for particle initialization and advancement, particle--grid coupling, field solution, collision modeling, parallel data exchange, input/output, and selected fluid updates. Documentation links mathematical formulations to source implementations, interfaces, and usage, while verification and validation cases evaluate numerical accuracy and physical behavior. AlgoPlasma thus establishes a shared algorithmic foundation for plasma modeling, transforming repeatedly reimplemented numerical methods into open, reusable, tested, and explainable components for research, verification, education, and collaborative development.

physics.plasm-ph↗
arXiv2026

Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation

Recent advances in video synthesis have enabled realistic integration of real individuals, driving demand for identity-aware generation. While emerging methods support joint appearance and voice injection in audio-visual models, they primarily focus on single-subject settings. Multimodal identity integration across multiple subjects remains limited, and precise alignment between visual and vocal identities in multi-subject scenarios remains underexplored. We present Identity-as-Presence, a unified framework for joint personalized audio-video generation. An automated data curation pipeline constructs identity-labeled audio-visual pairs for single- and multi-subject scenes. A unified identity injection mechanism then binds paired appearance and voice through shared cross-modal identity binding and subject-anchored captions. A multi-stage training strategy further leverages large-scale unimodal data alongside scarce paired clips to mitigate modality imbalance. Experiments show superior audio quality, video fidelity, and audio-visual consistency, with stronger multi-subject binding than the compared methods. For more details and qualitative results, please refer to our webpage: \href{https://chen-yingjie.github.io/projects/Identity-as-Presence}{Identity-as-Presence}.

cs.CV↗
arXiv2026

Free-Molecular Face-Flux Preprocessing for Reduced Neutral-Continuity Modeling in Hall Thrusters: Particle-Based Reference and Deterministic SN-DFEM Realization

Neutral gas transport directly affects the ionization source, propellant utilization, and low-frequency discharge oscillations in Hall thrusters. High-fidelity particle-based neutral models or DSMC methods can describe rarefied gas transport, but they are computationally expensive; in contrast, reduced neutral-continuity models are cheaper but require a closure for the neutral velocity or face-normal flux. Under a low-pressure collisionless approximation, this work adopts a free-molecular preprocessing strategy to provide a reference density field and the mean-velocity or face-normal-flux closure used by the reduced neutral-continuity equation in a manner consistent with the underlying transport model.On this basis, a particle-based free-molecular faceflux preprocessor is used as a stochastic reference, and an SN-DFEM deterministic free-molecular preprocessor is proposed to generate the corresponding reference density, velocity moments, and face-normal fluxes within a unified free-molecular transport framework. Results show that the SN-DFEM preprocessor preserves the main neutral-density and velocity structures and reduces the statistical error in face-flux closure by about three orders of magnitude in the baseline continuity-recovery test. A prescribed moderate ionization-loss case further demonstrates the extension of the framework to free-molecular preprocessing with volumetric neutral removal.

physics.plasm-ph↗
arXiv2026

MBench: A Comprehensive Benchmark on Memory Capability for Video World Models

Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences. However, a fundamental gap persists between visually plausible video generation and the functional requirements of a world model, particularly in maintaining a stable and reasonable internal state over extended temporal horizons. While existing benchmarks primarily emphasize visual quality, motion coherence, and text-video alignment, they largely overlook memory, the core capability of a world model to preserve consistency across long-term horizons and complex interactions. To address this gap, we present \textbf{MBench}, a comprehensive benchmark dedicated to quantifying and evaluating the memory capability of video world models. We systematically decompose the memory capability of video world models into three hierarchical and complementary core dimensions: entity consistency, environment consistency, and causal consistency, which are further refined into 12 quantifiable sub-dimensions for comprehensive characterization of long-term memory. Our benchmark is built upon rigorously curated real-captured long videos, and evaluated by rule-based quantitative matrices and VLM to enable objective and comprehensive consistency assessment. Extensive evaluations of mainstream state-of-the-art video world models reveal critical systemic limitations of existing methods in long-term state retention, providing a standardized benchmark and clear research direction to advance the field.

cs.CV↗
arXiv2026

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often constrained by fixed modality configurations and task-specific architectures, leaving cross-modal interactions and the scaling laws of multimodal-conditioned synthesis largely underexplored. A key bottleneck is the scarcity of large-scale modality-aligned motion data, limiting generalization across diverse control signals. In this work, we introduce OmniHuMo, a large-scale, high-quality dataset comprising over 5,000 hours of motion and 3.2 million sequences with precisely aligned multimodal annotations (e.g., text, speech, music, and trajectory). Leveraging OmniHuMo, we propose AnyMo, a unified multimodal framework combining a Residual FSQ-based motion tokenizer with a scalable masked modeling transformer, enabling high-quality motion synthesis under arbitrary modality combinations. Extensive experiments show that AnyMo achieves high-fidelity synthesis while offering flexible control over both spatial and stylistic attributes.

cs.CV↗
arXiv2026

OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation

Recent advancements in audio-video joint generation models have demonstrated impressive capabilities in content creation. However, generating high-fidelity human-centric videos in complex, real-world physical scenes remains a significant challenge. We identify that the root cause lies in the structural deficiencies of existing datasets across three dimensions: limited global scene and camera diversity, sparse interaction modeling (both person-person and person-object), and insufficient individual attribute alignment. To bridge these gaps, we present OmniHuman, a large-scale, multi-scene dataset designed for fine-grained human modeling. OmniHuman provides a hierarchical annotation covering video-level scenes, frame-level interactions, and individual-level attributes. To facilitate this, we develop a fully automated pipeline for high-quality data collection and multi-modal annotation. Complementary to the dataset, we establish the OmniHuman Benchmark (OHBench), a three-level evaluation system that provides a scientific diagnosis for human-centric audio-video synthesis. Crucially, OHBench introduces metrics that are highly consistent with human perception, filling the gaps in existing benchmarks by providing a comprehensive diagnosis across global scenes, relational interactions, and individual attributes.

cs.CV↗
arXiv2025

McSc: Motion-Corrective Preference Alignment for Video Generation with Self-Critic Hierarchical Reasoning

Text-to-video (T2V) generation has achieved remarkable progress in producing high-quality videos aligned with textual prompts. However, aligning synthesized videos with nuanced human preference remains challenging due to the subjective and multifaceted nature of human judgment. Existing video preference alignment methods rely on costly human annotations or utilize proxy metrics to predict preference, which lacks the understanding of human preference logic. Moreover, they usually directly align T2V models with the overall preference distribution, ignoring potential conflict dimensions like motion dynamics and visual quality, which may bias models towards low-motion content. To address these issues, we present Motion-corrective alignment with Self-critic hierarchical Reasoning (McSc), a three-stage reinforcement learning framework for robust preference modeling and alignment. Firstly, Self-critic Dimensional Reasoning (ScDR) trains a generative reward model (RM) to decompose preferences into per-dimension assessments, using self-critic reasoning chains for reliable learning. Secondly, to achieve holistic video comparison, we introduce Hierarchical Comparative Reasoning (HCR) for structural multi-dimensional reasoning with hierarchical reward supervision. Finally, using RM-preferred videos, we propose Motion-corrective Direct Preference Optimization (McDPO) to optimize T2V models, while dynamically re-weighting alignment objective to mitigate bias towards low-motion content. Experiments show that McSc achieves superior performance in human preference alignment and generates videos with high-motion dynamic.

cs.CV↗
arXiv2025

FMEnets: Flow, Material, and Energy networks for non-ideal plug flow reactor design

We propose FMEnets, a physics-informed machine learning framework for the design and analysis of non-ideal plug flow reactors. FMEnets integrates the fundamental governing equations (Navier-Stokes for fluid flow, material balance for reactive species transport, and energy balance for temperature distribution) into a unified multi-scale network model. The framework is composed of three interconnected sub-networks with independent optimizers that enable both forward and inverse problem-solving. In the forward mode, FMEnets predicts velocity, pressure, species concentrations, and temperature profiles using only inlet and outlet information. In the inverse mode, FMEnets utilizes sparse multi-residence-time measurements to simultaneously infer unknown kinetic parameters and states. FMEnets can be implemented either as FME-PINNs, which employ conventional multilayer perceptrons, or as FME-KANs, based on Kolmogorov-Arnold Networks. Comprehensive ablation studies highlight the critical role of the FMEnets architecture in achieving accurate predictions. Specifically, FME-KANs are more robust to noise than FME-PINNs, although both representations are comparable in accuracy and speed in noise-free conditions. The proposed framework is applied to three different sets of reaction scenarios and is compared with finite element simulations. FMEnets effectively captures the complex interactions, achieving relative errors less than 2.5% for the unknown kinetic parameters. The new network framework not only provides a computationally efficient alternative for reactor design and optimization, but also opens new avenues for integrating empirical correlations, limited and noisy experimental data, and fundamental physical equations to guide reactor design.

cs.LG↗
arXiv2025

Trend-Aware Supervision: On Learning Invariance for Semi-Supervised Facial Action Unit Intensity Estimation

With the increasing need for facial behavior analysis, semi-supervised AU intensity estimation using only keyframe annotations has emerged as a practical and effective solution to relieve the burden of annotation. However, the lack of annotations makes the spurious correlation problem caused by AU co-occurrences and subject variation much more prominent, leading to non-robust intensity estimation that is entangled among AUs and biased among subjects. We observe that trend information inherent in keyframe annotations could act as extra supervision and raising the awareness of AU-specific facial appearance changing trends during training is the key to learning invariant AU-specific features. To this end, we propose \textbf{T}rend-\textbf{A}ware \textbf{S}upervision (TAS), which pursues three kinds of trend awareness, including intra-trend ranking awareness, intra-trend speed awareness, and inter-trend subject awareness. TAS alleviates the spurious correlation problem by raising trend awareness during training to learn AU-specific features that represent the corresponding facial appearance changes, to achieve intensity estimation invariance. Experiments conducted on two commonly used AU benchmark datasets, BP4D and DISFA, show the effectiveness of each kind of awareness. And under trend-aware supervision, the performance can be improved without extra computational or storage costs during inference.

cs.CV↗
arXiv2025

Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation

Motion-controllable image animation is a fundamental task with a wide range of potential applications. Recent works have made progress in controlling camera or object motion via various motion representations, while they still struggle to support collaborative camera and object motion control with adaptive control granularity. To this end, we introduce 3D-aware motion representation and propose an image animation framework, called Perception-as-Control, to achieve fine-grained collaborative motion control. Specifically, we construct 3D-aware motion representation from a reference image, manipulate it based on interpreted user instructions, and perceive it from different viewpoints. In this way, camera and object motions are transformed into intuitive and consistent visual changes. Then, our framework leverages the perception results as motion control signals, enabling it to support various motion-related video synthesis tasks in a unified and flexible way. Experiments demonstrate the superiority of the proposed approach. For more details and qualitative results, please refer to our anonymous project webpage: https://chen-yingjie.github.io/projects/Perception-as-Control.

cs.CV↗
arXiv2024

I2CANSAY:Inter-Class Analogical Augmentation and Intra-Class Significance Analysis for Non-Exemplar Online Task-Free Continual Learning

Online task-free continual learning (OTFCL) is a more challenging variant of continual learning which emphasizes the gradual shift of task boundaries and learns in an online mode. Existing methods rely on a memory buffer composed of old samples to prevent forgetting. However,the use of memory buffers not only raises privacy concerns but also hinders the efficient learning of new samples. To address this problem, we propose a novel framework called I2CANSAY that gets rid of the dependence on memory buffers and efficiently learns the knowledge of new data from one-shot samples. Concretely, our framework comprises two main modules. Firstly, the Inter-Class Analogical Augmentation (ICAN) module generates diverse pseudo-features for old classes based on the inter-class analogy of feature distributions for different new classes, serving as a substitute for the memory buffer. Secondly, the Intra-Class Significance Analysis (ISAY) module analyzes the significance of attributes for each class via its distribution standard deviation, and generates the importance vector as a correction bias for the linear classifier, thereby enhancing the capability of learning from new samples. We run our experiments on four popular image classification datasets: CoRe50, CIFAR-10, CIFAR-100, and CUB-200, our approach outperforms the prior state-of-the-art by a large margin.

cs.CV↗
arXiv2024

Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition

Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects. In this paper, we propose a causal inference framework for subject-invariant facial action unit recognition. To illustrate the causal effect existing in AU recognition task, we formulate the causalities among facial images, subjects, latent AU semantic relations, and estimated AU occurrence probabilities via a structural causal model. By constructing such a causal diagram, we clarify the causal effect among variables and propose a plug-in causal intervention module, CIS, to deconfound the confounder \emph{Subject} in the causal diagram. Extensive experiments conducted on two commonly used AU benchmark datasets, BP4D and DISFA, show the effectiveness of our CIS, and the model with CIS inserted, CISNet, has achieved state-of-the-art performance.

cs.CV↗
arXiv2024

M2fNet: Multi-modal Forest Monitoring Network on Large-scale Virtual Dataset

Forest monitoring and education are key to forest protection, education and management, which is an effective way to measure the progress of a country's forest and climate commitments. Due to the lack of a large-scale wild forest monitoring benchmark, the common practice is to train the model on a common outdoor benchmark (e.g., KITTI) and evaluate it on real forest datasets (e.g., CanaTree100). However, there is a large domain gap in this setting, which makes the evaluation and deployment difficult. In this paper, we propose a new photorealistic virtual forest dataset and a multimodal transformer-based algorithm for tree detection and instance segmentation. To the best of our knowledge, it is the first time that a multimodal detection and segmentation algorithm is applied to large-scale forest scenes. We believe that the proposed dataset and method will inspire the simulation, computer vision, education, and forestry communities towards a more comprehensive multi-modal understanding.

cs.GR↗
arXiv2024

LiDAR-Forest Dataset: LiDAR Point Cloud Simulation Dataset for Forestry Application

The popularity of LiDAR devices and sensor technology has gradually empowered users from autonomous driving to forest monitoring, and research on 3D LiDAR has made remarkable progress over the years. Unlike 2D images, whose focused area is visible and rich in texture information, understanding the point distribution can help companies and researchers find better ways to develop point-based 3D applications. In this work, we contribute an unreal-based LiDAR simulation tool and a 3D simulation dataset named LiDAR-Forest, which can be used by various studies to evaluate forest reconstruction, tree DBH estimation, and point cloud compression for easy visualization. The simulation is customizable in tree species, LiDAR types and scene generation, with low cost and high efficiency.

cs.RO↗
arXiv2024

TrajVis: a visual clinical decision support system to translate artificial intelligence trajectory models in the precision management of chronic kidney disease

Objective: Our objective is to develop and validate TrajVis, an interactive tool that assists clinicians in using artificial intelligence (AI) models to leverage patients' longitudinal electronic medical records (EMR) for personalized precision management of chronic disease progression. Methods: We first perform requirement analysis with clinicians and data scientists to determine the visual analytics tasks of the TrajVis system as well as its design and functionalities. A graph AI model for chronic kidney disease (CKD) trajectory inference named DEPOT is used for system development and demonstration. TrajVis is implemented as a full-stack web application with synthetic EMR data derived from the Atrium Health Wake Forest Baptist Translational Data Warehouse and the Indiana Network for Patient Care research database. A case study with a nephrologist and a user experience survey of clinicians and data scientists are conducted to evaluate the TrajVis system. Results: The TrajVis clinical information system is composed of four panels: the Patient View for demographic and clinical information, the Trajectory View to visualize the DEPOT-derived CKD trajectories in latent space, the Clinical Indicator View to elucidate longitudinal patterns of clinical features and interpret DEPOT predictions, and the Analysis View to demonstrate personal CKD progression trajectories. System evaluations suggest that TrajVis supports clinicians in summarizing clinical data, identifying individualized risk predictors, and visualizing patient disease progression trajectories, overcoming the barriers of AI implementation in healthcare. Conclusion: TrajVis bridges the gap between the fast-growing AI/ML modeling and the clinical use of such models for personalized and precision management of chronic diseases.

cs.HC↗
arXiv2023

TrialView: An AI-powered Visual Analytics System for Temporal Event Data in Clinical Trials

Randomized controlled trials (RCT) are the gold standards for evaluating the efficacy and safety of therapeutic interventions in human subjects. In addition to the pre-specified endpoints, trial participants' experience reveals the time course of the intervention. Few analytical tools exist to summarize and visualize the individual experience of trial participants. Visual analytics allows integrative examination of temporal event patterns of patient experience, thus generating insights for better care decisions. Towards this end, we introduce TrialView, an information system that combines graph artificial intelligence (AI) and visual analytics to enhance the dissemination of trial data. TrialView offers four distinct yet interconnected views: Individual, Cohort, Progression, and Statistics, enabling an interactive exploration of individual and group-level data. The TrialView system is a general-purpose analytical tool for a broad class of clinical trials. The system is powered by graph AI, knowledge-guided clustering, explanatory modeling, and graph-based agglomeration algorithms. We demonstrate the system's effectiveness in analyzing temporal event data through a case study.

cs.HC↗