arXiv subjects

Chao Yuan

Publications and source records attributed to Chao Yuan.

At least 19 recordsLinked to original sources

arXiv2026

HCMS: Head-Chunked Multi-Stream Pipeline for Communication-Computation Overlap in Long-Sequence Parallel Attention

All-to-all based sequence parallelism methods execute communication and computation strictly in serial when processing medium-long sequences, resulting in hardware resource underutilization. This paper proposes Head-Chunked Multi-Stream Pipeline (HCMS), which exploits the computational independence of multi-head attention by partitioning attention heads into multiple chunks and achieving fine-grained communication-computation overlap through dual CUDA streams. HCMS is orthogonally compatible with existing optimizations such as FlashAttention and SDPA, requires no modification to underlying kernels, supports uneven partitioning while maintaining numerical equivalence. Experiments validate the effectiveness across four GPU platforms at 2-8 GPU scales: for typical video generation sequence lengths of 31K-56K tokens, HCMS achieves 10\%-17.5\% speedup over the Ulysses baseline and 5\%-14.5\% speedup over Ring Attention; end-to-end acceleration of 6.8\% is achieved on the Wan2.2 model. Theoretical analysis shows that HCMS benefits are positively correlated with communication ratio $\rho$, and its use is recommended when $\rho>20\%$.

cs.DC↗

arXiv2026

Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation

In text-to-image person retrieval tasks, the diversity of natural language expressions and the implicitness of visual semantics often lead to the problem of Expression Drift, where semantically equivalent texts exhibit significant feature discrepancies in the embedding space due to phrasing variations, thereby degrading the robustness of image-text alignment. This paper proposes a semantic compensation framework (MVR) driven by Large Language Models (LLMs), which enhances cross-modal representation consistency through multi-view semantic reformulation and feature compensation. The core methodology comprises three components: Multi-View Reformulation (MVR): A dual-branch prompting strategy combines key feature guidance (extracting visually critical components via feature similarity) and diversity-aware rewriting to generate semantically equivalent yet distributionally diverse textual variants; Textual Feature Robustness Enhancement: A training-free latent space compensation mechanism suppresses noise interference through multi-view feature mean-pooling and residual connections, effectively capturing "Semantic Echoes"; Visual Semantic Compensation: VLM generates multi-perspective image descriptions, which are further enhanced through shared text reformulation to address visual semantic gaps. Experiments demonstrate that our method can improve the accuracy of the original model well without training and performs SOTA on three text-to-image person retrieval datasets.

cs.CV↗

arXiv2026

Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index

Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism leads to explosive O(N^2) memory consumption and high first-frame latency. To address these issues, we implement system-level inference optimizations for a causal autoregressive video generation pipeline. We adapt the Self-Forcing causal autoregressive framework to sequence parallel inference and implement a sequence-parallel variant of the causal rotary position embedding which we refer to as Causal-RoPE SP. This adaptation enables localized computation and reduces cross-rank communication in sequence parallel execution. In addition, computation and communication pipelines are optimized through operator fusion and RoPE precomputation. Experiments conducted on an eight GPU A800 cluster show that the optimized system achieves comparable generation quality, sub-second first-frame latency, and near real-time inference speed. For generating five second 480P videos, a 1.58x speedup is achieved, thereby providing effective support for real-time interactive applications.

cs.CV↗

arXiv2025

UniComp: Rethinking Video Compression Through Informational Uniqueness

Distinct from attention-based compression methods, this paper presents an information uniqueness driven video compression framework, termed UniComp, which aims to maximize the information fidelity of video representations under constrained computational budgets. Starting from the information-theoretic perspective, we formulate the vision compression as an optimization problem that minimizes conditional entropy (reconstruction error) between retained and full tokens. To achieve this, we introduce the notion of information uniqueness to measure intrinsic redundancy among tokens to link with reconstruction error. Based on uniqueness, we design three modules-Frame Group Fusion, Token Allocation, and Spatial Dynamic Compression-that progressively perform semantic frame grouping, adaptive resource allocation, and fine-grained spatial compression. Extensive experiments demonstrate that UniComp consistently outperforms existing compression methods in preserving essential visual tokens under limited computational budgets, highlighting the pivotal role of information uniqueness in token compression efficacy.

cs.CV↗

arXiv2025

OmniPerson: Unified Identity-Preserving Pedestrian Generation

Person re-identification (ReID) suffers from a lack of large-scale high-quality training data due to challenges in data privacy and annotation costs. While previous approaches have explored pedestrian generation for data augmentation, they often fail to ensure identity consistency and suffer from insufficient controllability, thereby limiting their effectiveness in dataset augmentation. To address this, We introduce OmniPerson, the first unified identity-preserving pedestrian generation pipeline for visible/infrared image/video ReID tasks. Our contributions are threefold: 1) We proposed OmniPerson, a unified generation model, offering holistic and fine-grained control over all key pedestrian attributes. Supporting RGB/IR modality image/video generation with any number of reference images, two kinds of person poses, and text. Also including RGB-to-IR transfer and image super-resolution abilities.2) We designed Multi-Refer Fuser for robust identity preservation with any number of reference images as input, making OmniPerson could distill a unified identity from a set of multi-view reference images, ensuring our generated pedestrians achieve high-fidelity pedestrian generation.3) We introduce PersonSyn, the first large-scale dataset for multi-reference, controllable pedestrian generation, and present its automated curation pipeline which transforms public, ID-only ReID benchmarks into a richly annotated resource with the dense, multi-modal supervision required for this task. Experimental results demonstrate that OmniPerson achieves SoTA in pedestrian generation, excelling in both visual fidelity and identity consistency. Furthermore, augmenting existing datasets with our generated data consistently improves the performance of ReID models. We will open-source the full codebase, pretrained model, and the PersonSyn dataset.

cs.CV↗

arXiv2025

DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures

The rise of 3D generative models has enabled automatic 3D geometry and texture synthesis from multimodal inputs (e.g., text or images). However, these methods often ignore physical constraints and manufacturability considerations. In this work, we address the challenge of producing 3D designs that are both lightweight and self-supporting. We present DensiCrafter, a framework for generating lightweight, self-supporting 3D hollow structures by optimizing the density field. Starting from coarse voxel grids produced by Trellis, we interpret these as continuous density fields to optimize and introduce three differentiable, physically constrained, and simulation-free loss terms. Additionally, a mass regularization penalizes unnecessary material, while a restricted optimization domain preserves the outer surface. Our method seamlessly integrates with pretrained Trellis-based models (e.g., Trellis, DSO) without any architectural changes. In extensive evaluations, we achieve up to 43% reduction in material mass on the text-to-3D task. Compared to state-of-the-art baselines, our method could improve the stability and maintain high geometric fidelity. Real-world 3D-printing experiments confirm that our hollow designs can be reliably fabricated and could be self-supporting.

cs.CV↗

arXiv2025

Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) technique could associate the pedestrian images across visible and infrared modalities in the practical scenarios of background illumination changes. However, a substantial gap inherently exists between these two modalities. Besides, existing methods primarily rely on intermediate representations to align cross-modal features of the same person. The intermediate feature representations are usually create by generating intermediate images (kind of data enhancement), or fusing intermediate features (more parameters, lack of interpretability), and they do not make good use of the intermediate features. Thus, we propose a novel VI-ReID framework via Modality-Transition Representation Learning (MTRL) with a middle generated image as a transmitter from visible to infrared modals, which are fully aligned with the original visible images and similar to the infrared modality. After that, using a modality-transition contrastive loss and a modality-query regularization loss for training, which could align the cross-modal features more effectively. Notably, our proposed framework does not need any additional parameters, which achieves the same inference speed to the backbone while improving its performance on VI-ReID task. Extensive experimental results illustrate that our model significantly and consistently outperforms existing SOTAs on three typical VI-ReID datasets.

cs.CV↗

arXiv2025

Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection

Out-of-distribution (OOD) detection is essential for deploying deep learning models in open-world environments. Existing approaches, such as energy-based scoring and gradient-projection methods, typically rely on high-dimensional representations to separate in-distribution (ID) and OOD samples. We introduce P-OCS (Perturbations in the Orthogonal Complement Subspace), a lightweight and theoretically grounded method that operates in the orthogonal complement of the principal subspace defined by ID features. P-OCS applies a single projected perturbation restricted to this complementary subspace, enhancing subtle ID-OOD distinctions while preserving the geometry of ID representations. We show that a one-step update is sufficient in the small-perturbation regime and provide convergence guarantees for the resulting detection score. Experiments across multiple architectures and datasets demonstrate that P-OCS achieves state-of-the-art OOD detection with negligible computational cost and without requiring model retraining, access to OOD data, or changes to model architecture.

stat.ML↗

arXiv2025

Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification

Cross-resolution person re-identification (CR-ReID) remains challenging in practical surveillance, where camera quality and capture distance lead to substantial resolution gaps between low-resolution (LR) queries and high-resolution (HR) gallery images. Prior approaches commonly rely on super-resolution (SR) or resolution-invariant representation learning, which often increases system complexity and may not directly address the feature mismatch induced by resolution degradation. In this work, we report a new empirical finding from a dedicated analysis in which identity-specific variation is averaged out: the HR--LR feature discrepancy produced by standard ReID backbones exhibits a consistent, resolution-related semantic direction in the embedding space. We further support this observation with statistical analyses based on Canonical Correlation Analysis (CCA) and Pearson correlation analysis. Motivated by this finding, we propose Vector Panning Feature Alignment (VPFA), a lightweight post-hoc module that learns to pan LR features along the learned resolution direction to obtain pseudo-HR representations. VPFA operates after feature extraction and can be integrated into existing ReID systems with negligible overhead. Extensive experiments on multiple CR-ReID benchmarks show that VPFA achieves state-of-the-art performance while improving efficiency compared to SR-based or jointly trained alternatives.

cs.CV↗

arXiv2025

DATE: Dynamic Absolute Time Enhancement for Long Video Understanding

Long video understanding remains a fundamental challenge for multimodal large language models (MLLMs), particularly in tasks requiring precise temporal reasoning and event localization. Existing approaches typically adopt uniform frame sampling and rely on implicit position encodings to model temporal order. However, these methods struggle with long-range dependencies, leading to critical information loss and degraded temporal comprehension. In this paper, we propose Dynamic Absolute Time Enhancement (DATE) that enhances temporal awareness in MLLMs through the Timestamp Injection Mechanism (TIM) and a semantically guided Temporal-Aware Similarity Sampling (TASS) strategy. Specifically, we interleave video frame embeddings with textual timestamp tokens to construct a continuous temporal reference system. We further reformulate the video sampling problem as a vision-language retrieval task and introduce a two-stage algorithm to ensure both semantic relevance and temporal coverage: enriching each query into a descriptive caption to better align with the vision feature, and sampling key event with a similarity-driven temporally regularized greedy strategy. Our method achieves remarkable improvements w.r.t. absolute time understanding and key event localization, resulting in state-of-the-art performance among 7B and 72B models on hour-long video benchmarks. Particularly, our 7B model even exceeds many 72B models on some benchmarks.

cs.CV↗

arXiv2025

INSEva: A Comprehensive Chinese Benchmark for Large Language Models in Insurance

Insurance, as a critical component of the global financial system, demands high standards of accuracy and reliability in AI applications. While existing benchmarks evaluate AI capabilities across various domains, they often fail to capture the unique characteristics and requirements of the insurance domain. To address this gap, we present INSEva, a comprehensive Chinese benchmark specifically designed for evaluating AI systems' knowledge and capabilities in insurance. INSEva features a multi-dimensional evaluation taxonomy covering business areas, task formats, difficulty levels, and cognitive-knowledge dimension, comprising 38,704 high-quality evaluation examples sourced from authoritative materials. Our benchmark implements tailored evaluation methods for assessing both faithfulness and completeness in open-ended responses. Through extensive evaluation of 8 state-of-the-art Large Language Models (LLMs), we identify significant performance variations across different dimensions. While general LLMs demonstrate basic insurance domain competency with average scores above 80, substantial gaps remain in handling complex, real-world insurance scenarios. The benchmark will be public soon.

cs.CL↗

arXiv2025

Neighbor-Based Feature and Index Enhancement for Person Re-Identification

Person re-identification (Re-ID) aims to match the same pedestrian in a large gallery with different cameras and views. Enhancing the robustness of the extracted feature representations is a main challenge in Re-ID. Existing methods usually improve feature representation by improving model architecture, but most methods ignore the potential contextual information, which limits the effectiveness of feature representation and retrieval performance. Neighborhood information, especially the potential information of multi-order neighborhoods, can effectively enrich feature expression and improve retrieval accuracy, but this has not been fully explored in existing research. Therefore, we propose a novel model DMON-ARO that leverages latent neighborhood information to enhance both feature representation and index performance. Our approach is built on two complementary modules: Dynamic Multi-Order Neighbor Modeling (DMON) and Asymmetric Relationship Optimization (ARO). The DMON module dynamically aggregates multi-order neighbor relationships, allowing it to capture richer contextual information and enhance feature representation through adaptive neighborhood modeling. Meanwhile, ARO refines the distance matrix by optimizing query-to-gallery relationships, improving the index accuracy. Extensive experiments on three benchmark datasets demonstrate that our approach achieves performance improvements against baseline models, which illustrate the effectiveness of our model. Specifically, our model demonstrates improvements in Rank-1 accuracy and mAP. Moreover, this method can also be directly extended to other re-identification tasks.

cs.CV↗

arXiv2025

From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization

Person re-identification (ReID) aims to extract accurate identity representation features. However, during feature extraction, individual samples are inevitably affected by noise (background, occlusions, and model limitations). Considering that features from the same identity follow a normal distribution around identity centers after training, we propose a Training-Free Feature Centralization ReID framework (Pose2ID) by aggregating the same identity features to reduce individual noise and enhance the stability of identity representation, which preserves the feature's original distribution for following strategies such as re-ranking. Specifically, to obtain samples of the same identity, we introduce two components: Identity-Guided Pedestrian Generation: by leveraging identity features to guide the generation process, we obtain high-quality images with diverse poses, ensuring identity consistency even in complex scenarios such as infrared, and occlusion. Neighbor Feature Centralization: it explores each sample's potential positive samples from its neighborhood. Experiments demonstrate that our generative model exhibits strong generalization capabilities and maintains high identity consistency. With the Feature Centralization framework, we achieve impressive performance even with an ImageNet pre-trained model without ReID training, reaching mAP/Rank-1 of 52.81/78.92 on Market1501. Moreover, our method sets new state-of-the-art results across standard, cross-modality, and occluded ReID tasks, showcasing strong adaptability.

cs.CV↗

arXiv2025

Dur360BEV: A Real-world 360-degree Single Camera Dataset and Benchmark for Bird-Eye View Mapping in Autonomous Driving

We present Dur360BEV, a novel spherical camera autonomous driving dataset equipped with a high-resolution 128-channel 3D LiDAR and a RTK-refined GNSS/INS system, along with a benchmark architecture designed to generate Bird-Eye-View (BEV) maps using only a single spherical camera. This dataset and benchmark address the challenges of BEV generation in autonomous driving, particularly by reducing hardware complexity through the use of a single 360-degree camera instead of multiple perspective cameras. Within our benchmark architecture, we propose a novel spherical-image-to-BEV module that leverages spherical imagery and a refined sampling strategy to project features from 2D to 3D. Our approach also includes an innovative application of focal loss, specifically adapted to address the extreme class imbalance often encountered in BEV segmentation tasks, that demonstrates improved segmentation performance on the Dur360BEV dataset. The results show that our benchmark not only simplifies the sensor setup but also achieves competitive performance.

cs.CV↗

arXiv2024

FreeShell: A Context-Free 4D Printing Technique for Fabricating Complex 3D Triangle Mesh Shells

Freeform thin-shell surfaces are critical in various fields, but their fabrication is complex and costly. Traditional methods are wasteful and require custom molds, while 3D printing needs extensive support structures and post-processing. Thermoshrinkage actuated 4D printing is an effective method through flat structures fabricating 3D shell. However, existing research faces issues related to precise deformation and limited robustness. Addressing these issues is challenging due to three key factors: (1) Difficulty in finding a universal method to control deformation across different materials; (2) Variability in deformation influenced by factors such as printing speed, layer thickness, and heating temperature; (3) Environmental factors affecting the deformation process. To overcome these challenges, we introduce FreeShell, a robust 4D printing technique that uses thermoshrinkage to create precise 3D shells. This method prints triangular tiles connected by shrinkable connectors from a single material. Upon heating, the connectors shrink, moving the tiles to form the desired 3D shape, simplifying fabrication and reducing material and environment dependency. An optimized algorithm for flattening 3D meshes ensures precision in printing. FreeShell demonstrates its effectiveness through various examples and experiments, showcasing accuracy, robustness, and strength, representing advancement in fabricating complex freeform surfaces.

cs.GR↗

arXiv2023

A Survey of Developable Surfaces: From Shape Modeling to Manufacturing

Developable surfaces are commonly observed in various applications such as architecture, product design, manufacturing, mechanical materials, and data physicalization as well as in the development of tangible interaction and deformable robots, with the characteristics of easy-to-product, low-cost, transport-friendly, and deformable. Transforming shapes into developable surfaces is a complex and comprehensive task, which forms a variety of methods of segmentation, unfolding, and manufacturing for shapes with different geometry and topology, resulting in the complexity of developable surfaces. In this paper, we reviewed relevant methods and techniques for the study of developable surfaces, characterize them with our proposed pipeline, and categorize them based on digital modeling, physical modeling, interaction, and application. Through the analysis to the relevant literature, we also discussed some of the research challenges and future research opportunities.

cs.GR↗

arXiv2023

Yade Documentation

Yade is an extensible open-source framework for discrete numerical models, focused on the Discrete Element Method. The computation parts are written in c++ using a flexible object model and allowing independent implementation of new algorithms and interfaces. Python is used for rapid and concise scene construction, simulation control, postprocessing and debugging. Yade is located at yade-dem.org, which contains this documentation. Development is kindly hosted on launchpad and GitLab ; they are used for source code, bug tracking and source downloads and more. Building, regression tests and packages distribution are hosted on servers of the Grenoble Geomechanics group at Laboratoire 3SR, UMS Gricad and Gdańsk University of Technology. Yade supports high precision calculations and Python 3. The development branch is on GitLab.

physics.comp-ph↗

arXiv2021

Domain Adaptation Broad Learning System Based on Locally Linear Embedding

Broad learning system (BLS) has been proposed for a few years. It demonstrates an effective learning capability for many classification and regression problems. However, BLS and its improved versions are mainly used to deal with unsupervised, supervised and semi-supervised learning problems in a single domain. As far as we know, a little attention is paid to the cross-domain learning ability of BLS. Therefore, we introduce BLS into the field of transfer learning and propose a novel algorithm called domain adaptation broad learning system based on locally linear embedding (DABLS-LLE). The proposed algorithm can learn a robust classification model by using a small part of labeled data from the target domain and all labeled data from the source domain. The proposed algorithm inherits the computational efficiency and learning capability of BLS. Experiments on benchmark dataset (Office-Caltech-10) verify the effectiveness of our approach. The results show that our approach can get better classification accuracy with less running time than many existing transfer learning approaches. It shows that our approach can bring a new superiority for BLS.

cs.LG↗