arXiv subjects

Di Yang

Publications and source records attributed to Di Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Hairpin Vortices Extraction in Turbulent Boundary Layer Flows

Hairpin vortices are fundamental structures within turbulent boundary layers, playing a crucial role in energy dissipation, mixing, and momentum transport. However, accurately extracting these structures remains challenging due to their irregular shapes, varying scales, and entanglement with surrounding vortical structures. This paper presents a novel framework for the extraction of hairpin vortices from turbulent boundary layers. The method begins by identifying vortical regions and decomposing them into smaller segments using merge tree based segmentation. A novel bottom up rejoining approach is then introduced to group candidate segments according to the geometric and physical characteristics of hairpin vortices, resulting in regions that encompass complete hairpin vortex structures. These regions are subsequently refined and validated through skeleton analysis to detect the characteristic hairpin shape and are further confirmed using additional scalar based criteria. Finally, smooth enclosing surfaces are generated for effective visualization. To enable quantitative evaluation, reference hairpin vortices are extracted from several flow datasets and used as ground truth. Compared with existing approaches, the proposed method eliminates manual parameter tuning, reduces under and over segmentation, and significantly improves both accuracy and computational efficiency. Demonstrations on multiple turbulent flow cases show that the method is robust and effective for hairpin vortex extraction under varying boundary layer conditions.

cs.OH↗

arXiv2026

Modeling Vehicle-Type-Specific Pedestrian Crash Avoidance Behavior in Safety-Critical Interactions Using Smooth-Mamba Deep Reinforcement Learning

As automated vehicles (AVs) increasingly share roadways with human-driven vehicles (HDVs), understanding how pedestrians respond to different vehicle types in safety-critical interactions is essential for the safe deployment of automated driving technologies. This study extracts safety-critical pedestrian-vehicle interactions from the Argoverse 2 dataset to capture real-world crash avoidance behaviors in encounters involving AVs and HDVs. To model vehicle-type-specific pedestrian crash avoidance behavior, we develop a Smooth-Mamba Deep Deterministic Policy Gradient framework, termed SMamba-DDPG, which integrates smooth action constraints with efficient temporal representation learning. To quantify pedestrian behavioral differences, the framework trains separate crash avoidance policies for pedestrian interactions with AVs and HDVs. Results show that SMamba-DDPG outperforms baseline reinforcement learning and supervised learning models in reproducing pedestrian crash avoidance behaviors. Reconstructed trajectories demonstrate strong behavioral realism, accurately reproducing crash avoidance kinematics in both AV and HDV scenarios. Reaction time analysis shows that the model captures human-like response delays and reveals that pedestrians respond more quickly to AVs than to HDVs. Counterfactual analysis further indicates that pedestrians adopt lower crossing speeds when interacting with AVs. Large-scale safety analysis of model-generated data revealed that pedestrian-AV interactions consistently yielded lower conflict rates and higher pedestrian yielding rates compared to pedestrian-HDV interactions. The findings highlight the importance of incorporating vehicle-type-specific pedestrian behavioral models for safer automated driving system design and more realistic traffic simulations in mixed-traffic environments.

cs.AI↗

arXiv2026

On enumeration of $b$-angulations of surfaces from an integrability perspective

In this paper, we study generating series enumerating polygonal angulations of closed oriented surfaces of fixed genus, focusing on $b$-angulations with $b = 3$ or $b = 2ν$, $ν\geq 2$. Based on Toda integrability, we establish new structural results in the cases $b = 3$ and $b = 4$. Furthermore, via the Hodge--GUE correspondence, we derive a fine structure in the $b = 2ν$ case, which implies a conjectural statement of Gharakhloo--Latimer.

math-ph↗

arXiv2026

Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama

We present Genie Sim PanoRecon, a feed-forward Gaussian-splatting pipeline that delivers high-fidelity, low-cost 3D scenes for robotic manipulation simulation. The panorama input is decomposed into six non-overlapping cube-map faces, processed in parallel, and seamlessly reassembled. To guarantee geometric consistency across views, we devise a depth-aware fusion strategy coupled with a training-free depth-injection module that steers the monocular feed-forward network to generate coherent 3D Gaussians. The whole system reconstructs photo-realistic scenes in seconds and has been integrated into Genie Sim - a LLM-driven simulation platform for embodied synthetic data generation and evaluation - to provide scalable backgrounds for manipulation tasks. For code details, please refer to: https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world.

cs.RO↗

arXiv2026

FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling

Text-to-motion generation is driven by learning motion representations for semantic alignment with language. Existing methods rely on either continuous or discrete motion representations. However, continuous representations entangle semantics with dynamics, while discrete representations lose fine-grained motion details. In this context, we propose FlowCoMotion, a novel motion generation framework that unifies both treatments from a modeling perspective. Specifically, FlowCoMotion employs token-latent coupling to capture both semantic content and high-fidelity motion details. In the latent branch, we apply multi-view distillation to regularize the continuous latent space, while in the token branch we use discrete temporal resolution quantization to extract high-level semantic cues. The motion latent is then obtained by combining the representations from the two branches through a token-latent coupling network. Subsequently, a velocity field is predicted based on the textual conditions. An ODE solver integrates this velocity field from a simple prior, thereby guiding the sample to the potential state of the target motion. Extensive experiments show that FlowCoMotion achieves competitive performance on text-to-motion benchmarks, including HumanML3D and SnapMoGen.

cs.CV↗

arXiv2026

The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across distinct domains. As part of NTIRE 2026, we hosted the second CD-FSOD Challenge to systematically evaluate and promote progress in detecting objects in unseen target domains under limited annotation conditions. The challenge received strong community interest, with 128 registered participants and a total of 696 submissions. Among them, 31 teams actively participated, and 19 teams submitted valid final results. Participants explored a wide range of strategies, introducing innovative methods that push the performance frontier under both open-source and closed-source tracks. This report presents a detailed overview of the NTIRE 2026 CD-FSOD Challenge, including a summary of the submitted approaches and an analysis of the final results across all participating teams. Challenge Codes: https://github.com/ohMargin/NTIRE2026_CDFSOD.

cs.CV↗

arXiv2026

A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps

Few-shot object detection (FSOD) is challenging due to unstable optimization and limited generalization arising from the scarcity of training samples. To address these issues, we propose a hybrid ensemble decoder that enhances generalization during fine-tuning. Inspired by ensemble learning, the decoder comprises a shared hierarchical layer followed by multiple parallel decoder branches, where each branch employs denoising queries either inherited from the shared layer or newly initialized to encourage prediction diversity. This design fully exploits pretrained weights without introducing additional parameters, and the resulting diverse predictions can be effectively ensembled to improve generalization. We further leverage a unified progressive fine-tuning framework with a plateau-aware learning rate schedule, which stabilizes optimization and achieves strong few-shot adaptation without complex data augmentations or extensive hyperparameter tuning. Extensive experiments on CD-FSOD, ODinW-13, and RF100-VL validate the effectiveness of our approach. Notably, on RF100-VL, which includes 100 datasets across diverse domains, our method achieves an average performance of 41.9 in the 10-shot setting, significantly outperforming the recent approach SAM3, which obtains 35.7. We further construct a mixed-domain test set from CD-FSOD to evaluate robustness to out-of-distribution (OOD) samples, showing that our proposed modules lead to clear improvement gains. These results highlight the effectiveness, generalization, and robustness of the proposed method. Code is available at: https://github.com/Intellindust-AI-Lab/FT-FSOD.

cs.CV↗

arXiv2026

KdV integrability in GUE correlators

Okounkov [36] proved a remarkable formula relating $n$-point GUE (Gaussian unitary ensemble) correlators of a fixed genus to Witten's intersection numbers of the same genus. The partition function of GUE correlators is a tau-function for the Toda lattice hierarchy. In this note, based on the knowledge of these two statements we give a new proof of the Witten--Kontsevich theorem, that relates Witten's intersection numbers to the KdV (Korteweg--de Vries) integrable hierarchy.

math-ph↗

arXiv2026

On uniform large genus asymptotics of Witten's intersection numbers

Following ideas from [14], we give a uniform large genus asymptotics for primitive psi-class intersection numbers on the moduli space of stable algebraic curves, and extend this result including insertions of zeros in a certain uniform way. Application to a particular formal solution of the Painlevé I equation is given. We also use a method from [14] to give a new proof of the polynomiality conjecture on large genus asymptotic expansions of psi-class intersection numbers.

math-ph↗

arXiv2026

LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination

Despite the remarkable progress of modern machine translation (MT) systems on general-domain texts, translating structured LaTeX-formatted documents remains a significant challenge. These documents typically interleave natural language with domain-specific syntax, such as mathematical equations, tables, figures, and cross-references, all of which must be accurately preserved to maintain semantic integrity and compilability. In this paper, we introduce LaTeXTrans, a collaborative multi-agent system designed to address this challenge. LaTeXTrans ensures format preservation, structural fidelity, and terminology consistency through six specialized agents: 1) a Parser that decomposes LaTeX into translation-friendly units via placeholder substitution and syntax filtering; 2) a Translator, Validator, Summarizer, and Terminology Extractor that work collaboratively to ensure context-aware, self-correcting, and terminology-consistent translations; 3) a Generator that reconstructs the translated content into well-structured LaTeX documents. Experimental results show that LaTeXTrans outperforms mainstream MT systems in both translation accuracy and structural preservation. The source code, the online demonstration platform, and a demo video are publicly available.

cs.CL↗

arXiv2026

PD-Diag-Net: Clinical-Priors guided Network on Brain MRI for Auxiliary Diagnosis of Parkinson's Disease

Parkinson's disease (PD) is a common neurodegenerative disorder that severely diminishes patients' quality of life. Its global prevalence has increased markedly in recent decades. Current diagnostic workflows are complex and heavily reliant on neurologists' expertise, often resulting in delays in early detection and missed opportunities for timely intervention. To address these issues, we propose an end-to-end automated diagnostic method for PD, termed PD-Diag-Net, which performs risk assessment and auxiliary diagnosis directly from raw MRI scans. This framework first introduces an MRI Pre-processing Module (MRI-Processor) to mitigate inter-subject and inter-scanner variability by flexibly integrating established medical imaging preprocessing tools. It then incorporates two forms of clinical prior knowledge: (1) Brain-Region-Relevance-Prior (Relevance-Prior), which specifies brain regions strongly associated with PD; and (2) Brain-Region-Aging-Prior (Aging-Prior), which reflects the accelerated aging typically observed in PD-associated regions. Building on these priors, we design two dedicated modules: the Relevance-Prior Guided Feature Aggregation Module (Aggregator), which guides the model to focus on PD-associated regions at the inter-subject level, and the Age-Prior Guided Diagnosis Module (Diagnoser), which leverages brain age gaps as auxiliary constraints at the intra-subject level to enhance diagnostic accuracy and clinical interpretability. Furthermore, we collected external test data from our collaborating hospital. Experimental results show that PD-Diag-Net achieves 86\% accuracy on external tests and over 96% accuracy in early-stage diagnosis, outperforming existing advanced methods by more than 20%.

cs.CV↗

arXiv2026

ReBA-Pred-Net: Weakly-Supervised Regional Brain Age Prediction on MRI

Brain age has become a prominent biomarker of brain health. Yet most prior work targets whole brain age (WBA), a coarse paradigm that struggles to support tasks such as disease characterization and research on development and aging patterns, because relevant changes are typically region-selective rather than brain-wide. Therefore, robust regional brain age (ReBA) estimation is critical, yet a widely generalizable model has yet to be established. In this paper, we propose the Regional Brain Age Prediction Network (ReBA-Pred-Net), a Teacher-Student framework designed for fine-grained brain age estimation. The Teacher produces soft ReBA to guide the Student to yield reliable ReBA estimates with a clinical-prior consistency constraint (regions within the same function should change similarly). For rigorous evaluation, we introduce two indirect metrics: Healthy Control Similarity (HCS), which assesses statistical consistency by testing whether regional brain-age-gap (ReBA minus chronological age) distributions align between training and unseen HC; and Neuro Disease Correlation (NDC), which assesses factual consistency by checking whether clinically confirmed patients show elevated brain-age-gap in disease-associated regions. Experiments across multiple backbones demonstrate the statistical and factual validity of our method.

cs.CV↗

arXiv2026

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation

Embodied navigation has long been fragmented by task-specific architectures. We introduce ABot-N0, a unified Vision-Language-Action (VLA) foundation model that achieves a ``Grand Unification'' across 5 core tasks: Point-Goal, Object-Goal, Instruction-Following, POI-Goal, and Person-Following. ABot-N0 utilizes a hierarchical ``Brain-Action'' architecture, pairing an LLM-based Cognitive Brain for semantic reasoning with a Flow Matching-based Action Expert for precise, continuous trajectory generation. To support large-scale learning, we developed the ABot-N0 Data Engine, curating 16.9M expert trajectories and 5.0M reasoning samples across 7,802 high-fidelity 3D scenes (10.7 $\text{km}^2$). ABot-N0 achieves new SOTA performance across 7 benchmarks, significantly outperforming specialized models. Furthermore, our Agentic Navigation System integrates a planner with hierarchical topological memory, enabling robust, long-horizon missions in dynamic real-world environments.

cs.RO↗

arXiv2025

On a class of integrable deformations of the integrable hierarchy of topological type associated to a semisimple Frobenius manifold

Given a semisimple Frobenius manifold, we construct a class of integrable deformations of its hierarchy of topological type. We show that these integrable deformations have polynomial tau-structures, and conjecture that for the one-dimensional Frobenius manifold they give a universal object for integrable deformations of the Riemann--Hopf hierarchy having a tau-structure.

math-ph↗

arXiv2025

On enumeration of $l$-hypermaps

The $l$-hypermaps, $l\ge2$, which generalize (dual of) ribbon graphs ($l=2$ case), are interesting enumerative objects. In this paper, based on a theorem of Carlet--van de Leur--Posthuma--Shadrin and the matrix-resolvent method, we derive an explicit formula for $k$-point generating series of enumeration of $l$-hypermaps, which generalizes the one obtained in [30] for the $l=2$ case. We also generalize a theorem of Dubrovin [29].

math-ph↗

arXiv2025

Drinfeld-Sokolov Hierarchies, Tau Functions, and Generalized Schur Polynomials

For a simple Lie algebra $\mathfrak{g}$ and an irreducible faithful representation $π$ of $\mathfrak{g}$, we introduce the Schur polynomials of $(\mathfrak{g},π)$-type. We then derive the Sato-Zhou type formula for tau functions of the Drinfeld-Sokolov (DS) hierarchy of $\mathfrak{g}$-type. Namely, we show that the tau functions are linear combinations of the Schur polynomials of $(\mathfrak{g},π)$-type with the coefficients being the Plücker coordinates. As an application, we provide a way of computing polynomial tau functions for the DS hierarchy. For $\mathfrak{g}$ of low rank, we give several examples of polynomial tau functions, and use them to detect bilinear equations for the DS hierarchy.

math-ph↗

arXiv2025

LIA-X: Interpretable Latent Portrait Animator

We introduce LIA-X, a novel interpretable portrait animator designed to transfer facial dynamics from a driving video to a source portrait with fine-grained control. LIA-X is an autoencoder that models motion transfer as a linear navigation of motion codes in latent space. Crucially, it incorporates a novel Sparse Motion Dictionary that enables the model to disentangle facial dynamics into interpretable factors. Deviating from previous 'warp-render' approaches, the interpretability of the Sparse Motion Dictionary allows LIA-X to support a highly controllable 'edit-warp-render' strategy, enabling precise manipulation of fine-grained facial semantics in the source portrait. This helps to narrow initial differences with the driving video in terms of pose and expression. Moreover, we demonstrate the scalability of LIA-X by successfully training a large-scale model with approximately 1 billion parameters on extensive datasets. Experimental results show that our proposed method outperforms previous approaches in both self-reenactment and cross-reenactment tasks across several benchmarks. Additionally, the interpretable and controllable nature of LIA-X supports practical applications such as fine-grained, user-guided image and video editing, as well as 3D-aware portrait video manipulation.

cs.CV↗

arXiv2025

From Toda Hierarchy to KP Hierarchy

Using the matrix-resolvent method and a formula of the second-named author on the $n$-point function for a KP tau-function, we show that the tau-function of an arbitrary solution to the Toda lattice hierarchy is a KP tau-function. We then generalize this result to tau-functions for the extended Toda hierarchy (ETH) by developing the matrix-resolvent method for the ETH. As an example the partition function of Gromov-Witten invariants of the complex projective line is a KP tau-function, and an application on irreducible representations of the symmetric group is obtained.

nlin.SI↗