arXiv subjects

Jiaqi Yang

Publications and source records attributed to Jiaqi Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Boosting Multimodal Remote Sensing Image Classification with Transformer-based Heterogeneously Salient Graph Representation

Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-spatial properties, synthetic aperture radar (SAR) to provide structural information about the Earth's surface, and light detection and ranging (LiDAR) to cover altitude information about ground elevation. Therefore, a natural idea is to combine multimodal images for refined and accurate land-cover interpretation. Although many efforts have been attempted to achieve multi-source remote sensing image classification, there are still three issues as follows: 1) indiscriminate feature representation without sufficiently considering modal heterogeneity, 2) abundant features and complex computations associated with modeling long-range dependencies, and 3) overfitting phenomenon caused by sparsely labeled samples. To overcome the above barriers, a transformer-based heterogeneously salient graph representation (THSGR) approach is proposed in this paper. First, a multimodal heterogeneous graph encoder is presented to encode distinctively non-Euclidean structural features from heterogeneous data. Then, a self-attention-free multi-convolutional modulator is designed for effective and efficient long-term dependency modeling. Finally, a mean forward strategy is developed in order to avoid overfitting. Based on the above structures, the proposed model is able to break through modal gaps to obtain differentiated graph representation with competitive time cost, even for a small fraction of training samples. Experiments and analyses in three benchmark datasets with various state-of-the-art (SOTA) approaches show the performance of the proposed THSGR. The code will be available in https://github.com/jqyang22.

cs.CV↗

arXiv2026

Metric, inertially aligned monocular state estimation via kinetodynamic priors

Accurate state estimation for flexible robotic systems poses significant challenges, particularly for platforms with dynamically deforming structures that invalidate rigid-body assumptions. This paper addresses this problem and enables the extension of existing rigid-body pose estimation methods to non-rigid systems. Our approach integrates two core components: first, we capture elastic properties using a deformation-force model, efficiently learned via a Multi-Layer Perceptron; second, we resolve the platform's inherently smooth motion using continuous-time B-spline kinematic models. By continuously applying Newton's Second Law, our method formulates the relationship between visually-derived trajectory acceleration and predicted deformation-induced acceleration. We demonstrate that our approach not only enables robust and accurate pose estimation on non-rigid platforms, but also shows that the properly modeled platform physics allow for the recovery of inertial sensing properties. We validate this feasibility on a simple spring-camera system, showing how it robustly resolves the typically ill-posed problem of metric scale and gravity recovery in monocular visual odometry.

cs.RO↗

arXiv2026

Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs

Image-to-point-cloud (I2P) registration aims to align 2D images with 3D point clouds by establishing reliable 2D-3D correspondences. The drastic modality gap between images and point clouds makes it challenging to learn features that are both discriminative and generalizable, leading to severe performance drops in unseen scenarios. We address this challenge by introducing a heterogeneous graph that enables refining both cross-modal features and correspondences within a unified architecture. The proposed graph represents a mapping between segmented 2D and 3D regions, which enhances cross-modal feature interaction and thus improves feature discriminability. In addition, modeling the consistency among vertices and edges within the graph enables pruning of unreliable correspondences. Building on these insights, we propose a heterogeneous graph embedded I2P registration method, termed Hg-I2P. It learns a heterogeneous graph by mining multi-path feature relationships, adapts features under the guidance of heterogeneous edges, and prunes correspondences using graph-based projection consistency. Experiments on six indoor and outdoor benchmarks under cross-domain setups demonstrate that Hg-I2P significantly outperforms existing methods in both generalization and accuracy. Code is released on https://github.com/anpei96/hg-i2p-demo.

cs.CV↗

arXiv2026

Nonlinear modulational instability of two-dimensional deep hydroelastic Stokes waves

In this paper, we study the nonlinear modulational instability of two-dimensional hydroelastic Stokes waves in infinite depth. We first justify a focusing cubic nonlinear Schrödinger (NLS) approximation result for 2D deep hydroelastic wave system in the spirit of Ifrim-Tataru [22]. Then we exploit the instability mechanism of the cubic NLS to prove that the Stokes waves are nonlinearly unstable under long-wave perturbations.

math.AP↗

arXiv2026

TAFG-MAN: Timestep-Adaptive Frequency-Gated Latent Diffusion for Efficient and High-Quality Low-Dose CT Image Denoising

Low-dose computed tomography (LDCT) reduces radiation exposure but also introduces substantial noise and structural degradation, making it difficult to suppress noise without erasing subtle anatomical details. In this paper, we present TAFG-MAN, a latent diffusion framework for efficient and high-quality LDCT image denoising. The framework combines a perceptually optimized autoencoder, conditional latent diffusion restoration in a compact latent space, and a lightweight Timestep-Adaptive Frequency-Gated (TAFG) conditioning design. TAFG decomposes condition features into low- and high-frequency components, predicts timestep-adaptive gates from the current denoising feature and timestep embedding, and progressively releases high-frequency guidance in later denoising stages before cross-attention. In this way, the model relies more on stable structural guidance at early reverse steps and introduces fine details more cautiously as denoising proceeds, improving the balance between noise suppression and detail preservation. Experiments show that TAFG-MAN achieves a favorable quality-efficiency trade-off against representative baselines. Compared with its base variant without TAFG, it further improves detail preservation and perceptual quality while maintaining essentially the same inference cost, and ablation results confirm the effectiveness of the proposed conditioning mechanism.

cs.CV↗

arXiv2026

CutVQA: Co-Designing Circuit Cutting and Architecture Search for Scaling Variational Quantum Algorithms

Circuit cutting enables large quantum circuits to run on small NISQ devices, but it introduces an exponentially high sampling overhead. Here, we present CutVQA, a co-design framework that integrates circuit cutting with quantum architecture search to scale VQAs. CutVQA performs cutting-aware architecture search and applies subcircuit-level optimization enabled by parameter locality, reducing both reconstruction and training overhead. Evaluations on two representative VQAs (QAOA and VQE) show that CutVQA matches baseline accuracy while reducing sampling overhead by 2-3 orders of magnitude and shortening training time by at least 50%, demonstrating that co-design is essential for scaling VQA execution.

quant-ph↗

arXiv2026

GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstruction

Feature extraction, matching, structure from motion (SfM), and novel view synthesis (NVS) have traditionally been treated as separate problems with independent optimization objectives. We present GloSplat, a framework that performs \emph{joint pose-appearance optimization} during 3D Gaussian Splatting training. Unlike prior joint optimization methods (BARF, NeRF--, 3RGS) that rely purely on photometric gradients for pose refinement, GloSplat preserves \emph{explicit SfM feature tracks} as first-class entities throughout training: track 3D points are maintained as separate optimizable parameters from Gaussian primitives, providing persistent geometric anchors via a reprojection loss that operates alongside photometric supervision. This architectural choice prevents early-stage pose drift while enabling fine-grained refinement -- a capability absent in photometric-only approaches. We introduce two pipeline variants: (1) \textbf{GloSplat-F}, a COLMAP-free variant using retrieval-based pair selection for efficient reconstruction, and (2) \textbf{GloSplat-A}, an exhaustive matching variant for maximum quality. Both employ global SfM initialization followed by joint photometric-geometric optimization during 3DGS training. Experiments demonstrate that GloSplat-F achieves state-of-the-art among COLMAP-free methods while GloSplat-A surpasses all COLMAP-based baselines.

cs.CV↗

arXiv2026

InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions

End-to-end human animation with rich multi-modal conditions, e.g., text, image and audio has achieved remarkable advancements in recent years. However, most existing methods could only animate a single subject and inject conditions in a global manner, ignoring scenarios where multiple concepts could appear in the same video with rich human-human interactions and human-object interactions. Such a global assumption prevents precise and per-identity control of multiple concepts including humans and objects, therefore hinders applications. In this work, we discard the single-entity assumption and introduce a novel framework that enforces strong, region-specific binding of conditions from modalities to each identity's spatiotemporal footprint. Given reference images of multiple concepts, our method could automatically infer layout information by leveraging a mask predictor to match appearance cues between the denoised video and each reference appearance. Furthermore, we inject local audio condition into its corresponding region to ensure layout-aligned modality matching in an iterative manner. This design enables the high-quality generation of human dialogue videos between two to three people or video customization from multiple reference images. Empirical results and ablation studies validate the effectiveness of our explicit layout control for multi-modal conditions compared to implicit counterparts and other existing methods. Video demos are available at https://zhenzhiwang.github.io/interacthuman/

cs.CV↗

arXiv2026

Exact controllability of two-dimensional hydroelastic waves

We prove the exact controllability of two-dimensional hydroelastic waves in the periodic setting. We show that if the initial data and the final data are small, for exterior pressure whose support is any non-empty open set $ω$, the two-dimensional hydroelastic wave system is exactly controllable in arbitrary short time.

math.AP↗

arXiv2026

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation

Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An embodiment-agnostic interaction representation that captures this structure would make manipulation behaviors easier to validate and transfer across robots. We propose FlowHOI, a two-stage flow-matching framework that generates semantically grounded, temporally coherent HOI sequences, comprising hand poses, object poses, and hand-object contact states, conditioned on an egocentric observation, a language instruction, and a 3D Gaussian splatting (3DGS) scene reconstruction. We decouple geometry-centric grasping from semantics-centric manipulation, conditioning the latter on compact 3D scene tokens and employing a motion-text alignment loss to semantically ground the generated interactions in both the physical scene layout and the language instruction. To address the scarcity of high-fidelity HOI supervision, we introduce a reconstruction pipeline that recovers aligned hand-object trajectories and meshes from large-scale egocentric videos, yielding an HOI prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI representations to real-robot execution pipelines.

cs.RO↗

arXiv2026

Self-heterodyne spectroscopy via a non-uniformly spaced frequency comb

Frequency comb spectroscopy has significantly advanced molecular spectroscopy across scientific research and diverse applications. Among its key performance metrics especially for time-resolved studies, sensitivity and measurement speed are paramount. However, a long-standing compromise between these parameters arises from the need for noise reduction. Here, we introduce a comb spectroscopy system that overcomes this limitation using a single frequency comb of non-uniformly spaced modes. The comb is generated using an extremely simple setup, composed of a continuous-wave (CW) fiber laser and a single-sideband phase modulator (SSM). Our approach delivers optical-to-radio-frequency conversion comparable to dual-comb spectroscopy (DCS) but through a simplified self-heterodyning architecture. By leveraging the intrinsic mutual coherence of the comb, this design achieves a noise-equivalent absorption coefficient (NEA) of 5.0*10^(-6) Hz^(-1/2)--an order-of-magnitude improvement over state-of-the-art DCS, coupled with long-term stability. The system resolves weak molecular overtone spectra on nanosecond timescales, in a single-shot measurement, at a signal-to-noise ratio of 128. This integration of high sensitivity, resolution, and speed resolves the core trade-off that has long constrained time-resolved spectroscopic analysis.

physics.optics↗

arXiv2026

On the well-posedness of two-dimensional Muskat problem with an elastic interface

We investigate the two-dimensional Muskat problem with a nonlinear elastic interface, for both one-phase and two-phase scenarios. Following the framework developed by Nguyen [35,36], we demonstrate that the problem is locally well-posed in $H^s$ for $s\geq 2$ for arbitrary initial data. Furthermore, for the one-phase case and the stable two-phase case $(ρ^+ \leq ρ^-)$, we establish global well-posedness for small initial data in $H^s$ when $s> \frac{3}{2}$.

math.AP↗

arXiv2025

Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidance

Accurate segmentation of Optical Coherence Tomography (OCT) images is crucial for diagnosing and monitoring retinal diseases. However, the labor-intensive nature of pixel-level annotation limits the scalability of supervised learning for large datasets. Weakly Supervised Semantic Segmentation (WSSS) offers a promising alternative by using weaker forms of supervision, such as image-level labels, to reduce the annotation burden. Despite its advantages, weak supervision inherently carries limited information. We propose a novel WSSS framework with only image-level labels for OCT lesion segmentation that integrates structural and text-driven guidance to produce high-quality, pixel-level pseudo labels. The framework employs two visual processing modules: one that processes the original OCT images and another that operates on layer segmentations augmented with anomalous signals, enabling the model to associate lesions with their corresponding anatomical layers. Complementing these visual cues, we leverage large-scale pretrained models to provide two forms of textual guidance: label-derived descriptions that encode local semantics, and domain-agnostic synthetic descriptions that, although expressed in natural image terms, capture spatial and relational semantics useful for generating globally consistent representations. By fusing these visual and textual features in a multi-modal framework, our method aligns semantic meaning with structural relevance, thereby improving lesion localization and segmentation performance. Experiments on three OCT datasets demonstrate state-of-the-art results, highlighting its potential to advance diagnostic accuracy and efficiency in medical imaging.

cs.CV↗

arXiv2025

Low regularity well-posedness for two-dimensional hydroelastic waves

We investigate the low regularity local well-posedness of two-dimensional irrotational deep hydroelastic waves. Building on the approach of Ifrim-Tataru [29] and Ai-Ifrim-Tataru [5], in particular by constructing a cubic modified energy that incorporates a paradifferential weight chosen carefully, we prove that the hydroelastic waves are locally well-posed in $\mathcal{H}^s$ for $s>\frac{3}{4}$.

math.AP↗

arXiv2025

SurvAgent: Hierarchical CoT-Enhanced Case Banking and Dichotomy-Based Multi-Agent System for Multimodal Survival Prediction

Survival analysis is critical for cancer prognosis and treatment planning, yet existing methods lack the transparency essential for clinical adoption. While recent pathology agents have demonstrated explainability in diagnostic tasks, they face three limitations for survival prediction: inability to integrate multimodal data, ineffective region-of-interest exploration, and failure to leverage experiential learning from historical cases. We introduce SurvAgent, the first hierarchical chain-of-thought (CoT)-enhanced multi-agent system for multimodal survival prediction. SurvAgent consists of two stages: (1) WSI-Gene CoT-Enhanced Case Bank Construction employs hierarchical analysis through Low-Magnification Screening, Cross-Modal Similarity-Aware Patch Mining, and Confidence-Aware Patch Mining for pathology images, while Gene-Stratified analysis processes six functional gene categories. Both generate structured reports with CoT reasoning, storing complete analytical processes for experiential learning. (2) Dichotomy-Based Multi-Expert Agent Inference retrieves similar cases via RAG and integrates multimodal reports with expert predictions through progressive interval refinement. Extensive experiments on five TCGA cohorts demonstrate SurvAgent's superority over conventional methods, proprietary MLLMs, and medical agents, establishing a new paradigm for explainable AI-driven survival prediction in precision oncology.

cs.CV↗

arXiv2025

Assist-As-Needed: Adaptive Multimodal Robotic Assistance for Medication Management in Dementia Care

People living with dementia (PLWDs) face progressively declining abilities in medication management-from simple forgetfulness to complete task breakdown-yet most assistive technologies fail to adapt to these changing needs. This one-size-fits-all approach undermines autonomy, accelerates dependence, and increases caregiver burden. Occupational therapy principles emphasize matching assistance levels to individual capabilities: minimal reminders for those who merely forget, spatial guidance for those who misplace items, and comprehensive multimodal support for those requiring step-by-step instruction. However, existing robotic systems lack this adaptive, graduated response framework essential for maintaining PLWD independence. We present an adaptive multimodal robotic framework using the Pepper robot that dynamically adjusts assistance based on real-time assessment of user needs. Our system implements a hierarchical intervention model progressing from (1) simple verbal reminders, to (2) verbal + gestural cues, to (3) full multimodal guidance combining physical navigation to medication locations with step-by-step verbal and gestural instructions. Powered by LLM-driven interaction strategies and multimodal sensing, the system continuously evaluates task states to provide just-enough assistance-preserving autonomy while ensuring medication adherence. We conducted a preliminary study with healthy adults and dementia care stakeholders in a controlled lab setting, evaluating the system's usability, comprehensibility, and appropriateness of adaptive feedback mechanisms. This work contributes: (1) a theoretically grounded adaptive assistance framework translating occupational therapy principles into HRI design, (2) a multimodal robotic implementation that preserves PLWD dignity through graduated support, and (3) empirical insights into stakeholder perceptions of adaptive robotic care.

cs.RO↗

arXiv2025

BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation

This paper presents a generalizable RGB-based approach for object pose estimation, specifically designed to address challenges in sparse-view settings. While existing methods can estimate the poses of unseen objects, their generalization ability remains limited in scenarios involving occlusions and sparse reference views, restricting their real-world applicability. To overcome these limitations, we introduce corner points of the object bounding box as an intermediate representation of the object pose. The 3D object corners can be reliably recovered from sparse input views, while the 2D corner points in the target view are estimated through a novel reference-based point synthesizer, which works well even in scenarios involving occlusions. As object semantic points, object corners naturally establish 2D-3D correspondences for object pose estimation with a PnP algorithm. Extensive experiments on the YCB-Video and Occluded-LINEMOD datasets show that our approach outperforms state-of-the-art methods, highlighting the effectiveness of the proposed representation and significantly enhancing the generalization capabilities of object pose estimation, which is crucial for real-world applications.

cs.CV↗

arXiv2025

MAN: Latent Diffusion Enhanced Multistage Anti-Noise Network for Efficient and High-Quality Low-Dose CT Image Denoising

While diffusion models have set a new benchmark for quality in Low-Dose Computed Tomography (LDCT) denoising, their clinical adoption is critically hindered by extreme computational costs, with inference times often exceeding thousands of seconds per scan. To overcome this barrier, we introduce MAN, a Latent Diffusion Enhanced Multistage Anti-Noise Network for Efficient and High-Quality Low-Dose CT Image Denoising task. Our method operates in a compressed latent space via a perceptually-optimized autoencoder, enabling an attention-based conditional U-Net to perform the fast, deterministic conditional denoising diffusion process with drastically reduced overhead. On the LDCT and Projection dataset, our model achieves superior perceptual quality, surpassing CNN/GAN-based methods while rivaling the reconstruction fidelity of computationally heavy diffusion models like DDPM and Dn-Dp. Most critically, in the inference stage, our model is over 60x faster than representative pixel space diffusion denoisers, while remaining competitive on PSNR/SSIM scores. By bridging the gap between high fidelity and clinical viability, our work demonstrates a practical path forward for advanced generative models in medical imaging.

cs.CV↗