arXiv subjects

Yu Xin

Publications and source records attributed to Yu Xin.

At least 19 recordsLinked to original sources

arXiv2026

OlfactProfile: Profile-Conditioned Odor Prediction from Audiovisual Content

Automated video-odor matching predicts scents aligned with audiovisual content for scent-enhanced media. Existing methods usually treat odor labels as determined only by scene content, but odor judgment also depends on individual olfactory profiles, including scent sensitivity, tolerance to unpleasant odors, and affective preference. Ignoring this observer context limits current systems' ability to predict scents that match perceived experience. We present OlfactProfile, a framework for profile-conditioned odor prediction from audiovisual content. Our results show that olfactory profiles are not beneficial by default: with matched feature backbones, naive profile concatenation and uniform profile modulation can degrade performance, while structured field-wise profile conditioning consistently improves prediction. Thus, the key challenge is not merely whether observer context is available, but how it is integrated into multimodal reasoning. To study this setting, we construct an audiovisual benchmark pairing temporally aligned odor annotations with annotator olfactory preference profiles. It contains 1,350 video clips, a 99-class scent vocabulary, and three semantic odor tracks: Foreground Odor, Background Odor, and Emotion Odor. We also propose OAR (Olfactory-Aware Routing), a multimodal fusion module that performs track-aware audiovisual routing with field-wise profile modulation, allowing profile dimensions to influence odor reasoning according to perceptual role. Experiments show that OlfactProfile outperforms supervised baselines and general-purpose multimodal large models, is competitive with odor experts in a small human comparison, and improves perceived scent fit in scent-enhanced applications without task-specific fine-tuning. Per-track analysis shows that gains are strongest for Background Odor and Emotion Odor, where observer-dependent judgment is most important.

cs.MM↗

arXiv2026

LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending

Garment refitting, the task of adapting a garment from a source to a target avatar, must preserve the original design features and fine-scale wrinkles, a challenge exacerbated by significant shape variations and varying poses without registration to a shared canonical pose. Existing methods struggle to balance robustness, efficiency, and fidelity of detail: physics-based simulation is costly, data-driven approaches lack generalizability, and geometry optimization in the full vertex space is often ill-conditioned and prone to local minima with unsatisfactory quality. We identify that a fundamental limitation lies in the representation: deforming garments directly in global coordinates couples vertices non-locally, creating a complex and poorly-structured optimization landscape. Therefore, we introduce LoBoFit, a robust refitting method built upon a novel Local Bone Mapping Blending (LoBoMap Blending) representation. Instead of manipulating global vertex positions, LoBoMap Blending expresses garment geometry as a linear blend of its mappings into local bone coordinate frames. This representation is highly expressive and flexible: local bone mappings yield a pose-robust initialization and a well-conditioned parameterization, while blending weights smooth the optimization landscape and broaden the space of plausible solutions for stable convergence with fine-scale detail preservation. The subsequent refinement efficiently resolves collisions and preserves details by optimizing localized residuals, effectively decomposing the complex global deformation into manageable subproblems. Our experiments demonstrate that LoBoFit reliably refits high-resolution, single- and multi-layer garments across avatars with large shape and topological differences, while faithfully preserving intricate wrinkles and the intended fit style, outperforming state-of-the-art methods in robustness and output quality.

cs.GR↗

arXiv2026

ESICA: A Scalable Framework for Text-Guided 3D Medical Image Segmentation

Text guided 3D medical image segmentation offers a flexible alternative to class based and spatial prompt based models by allowing users to specify regions of interest directly in natural language. This paradigm avoids reliance on predefined label sets, reduces ambiguous outputs, and aligns more naturally with clinical workflows. However, existing text guided frameworks are often computationally expensive, exhibit weak text volume feature alignment, and fail to capture fine anatomical details. We propose ESICA, a lightweight and scalable framework that addresses these challenges through three innovations: (1) a similarity matrix based mask prediction formulation that enhances semantic alignment, (2) an efficient decomposed decoder with adapter modules for accurate volumetric decoding, and (3) a two pass refinement strategy that sharpens boundaries and resolves uncertain regions. To improve training stability and generalization, ESICA adopts a two stage scheme consisting of positive only pretraining followed by balanced fine tuning. On the CVPR BiomedSegFM benchmark spanning five imaging modalities (CT, MRI, PET, ultrasound, and microscopy), ESICA achieves state of the art segmentation accuracy, while the compact ESICA4 Lite variant attains similar segmentation performance with substantially fewer parameters, yielding a superior efficiency accuracy trade off. Our framework advances text guided segmentation toward efficient, scalable, and clinically deployable systems. Code will be made publicly available at https://github.com/mirthAI/ESICA.

cs.CV↗

arXiv2025

Single-Photon Scattering in a Waveguide Coupled to a Lossy or Gain Giant Atom

This work investigates single-photon scattering in a one-dimensional coupled-resonator waveguide coupled to a giant atom with a complex on-site energy. Within the generalized projection operator formalism, we derive analytical expressions for the scattering coefficients. We find that a lossy giant atom absorbs the incident wave, whereas a gain giant atom not only amplifies the incident wave but also leads to scattering divergence at certain energies, corresponding to spectral singularities. We explore the critical scattering dynamics associated with these singularities, and attribute the persistent wave emission to the existence of a stationary bound state in the continuum. Due to the presence of this bound state, the conventional time-independent scattering theory proves inadequate for such a non-Hermitian system. Furthermore, we show that the system with gain always features at least one time-growing bound state, which dominates the long-time dynamics, and we verify our time-dependent theoretical predictions via numerical simulations of Gaussian wave packet scattering.

quant-ph↗

arXiv2025

Bound states and decay dynamics in $N$-level Friedrichs model with factorizable interactions

Considering an $N$-level system interacting factorizably with a continuous spectrum, we derive expressions for the bound states and the dynamical evolution within this single-excitation Friedrichs model by using the projection operator formalism. First, we establish explicit criteria to determine the number of bound states, whose existence suppresses the complete spontaneous decay of the system. Second, we derive the open system's decay dynamics, which is naturally described by an energy-independent non-Hermitian Hamiltonian in the Markovian limit. As an example, we apply our framework to a two-level atomic chain side-coupled to a photonic lattice, uncovering a rich variety of decay dynamics and realizing an anti-$\mathcal{PT}$-symmetric Hamiltonian in the system's evolution.

quant-ph↗

arXiv2025

PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition

This paper presents a Pronunciation-Aware Contextualized (PAC) framework to address two key challenges in Large Language Model (LLM)-based Automatic Speech Recognition (ASR) systems: effective pronunciation modeling and robust homophone discrimination. Both are essential for raw or long-tail word recognition. The proposed approach adopts a two-stage learning paradigm. First, we introduce a pronunciation-guided context learning method. It employs an interleaved grapheme-phoneme context modeling strategy that incorporates grapheme-only distractors, encouraging the model to leverage phonemic cues for accurate recognition. Then, we propose a pronunciation-discriminative reinforcement learning method with perturbed label sampling to further enhance the model\'s ability to distinguish contextualized homophones. Experimental results on the public English Librispeech and Mandarin AISHELL-1 datasets indicate that PAC: (1) reduces relative Word Error Rate (WER) by 30.2% and 53.8% compared to pre-trained LLM-based ASR models, and (2) achieves 31.8% and 60.5% relative reductions in biased WER for long-tail words compared to strong baselines, respectively.

cs.CL↗

arXiv2025

Explicit formulas for the Bessel models: odd general spin groups

Let $F$ be a non-archimedean local field of characteristic zero. In this work, we study the Bessel model for $\GSpin_{2n+1}$, extending a result of Bump, Friedberg and Furusawa. In particular, we obtain explicit formulas for the unramified Bessel functions. These formulas have a global application to a Rankin--Selberg integral of the $L$-function for $\GSpin_{2n+1} \times \GL_n$, generalizing a construction of Furusawa. We compute the local factor of the global integral at a good place. Moreover, a corollary of this computation finds an application in a recent work of Asgari, Cogdell and Shahidi, specifically in their unramified computation.

math.NT↗

arXiv2025

Arbitrarily polarized $\gamma$-photon source from nonlinear Compton scattering

We investigate the nonlinear Compton photon source for upcoming laser-particle experiments in the collision scenario of high-energy electron beams and relativistic laser pulses. The stronger laser field could not only improve the scattering probability but also induce broader photon beam divergence. To maximize the photon flux in a realistic narrow angular acceptance, we show that a balance must be met for the laser intensity to boost the scattering probability and simultaneously confine its beam divergence. For the currently experiment-concerned $10~\textrm{GeV}$ energy regime, the balanced laser intensity locates in the intermediate intensity regime of $\xi \sim O(1)$. In these regimes of laser intensity and electron energy, the accepted photons within a relatively narrow acceptance are highly polarized in the state closely relating to the polarization of the laser pulse, which actually implies a potential route to finely control the photon polarization via the laser polarization.

hep-ph↗

arXiv2025

Bridging Theory and Experiment in Materials Discovery: Machine-Learning-Assisted Prediction of Synthesizable Structures

Even though thermodynamic energy-based crystal structure prediction (CSP) has revolutionized materials discovery, the energy-driven CSP approaches often struggle to identify experimentally realizable metastable materials synthesized through kinetically controlled pathways, creating a critical gap between theoretical predictions and experimental synthesis. Here, we propose a synthesizability-driven CSP framework that integrates symmetry-guided structure derivation with a Wyckoff encode-based machine-learning model, allowing for the efficient localization of subspaces likely to yield highly synthesizable structures. Within the identified promising subspaces, a structure-based synthesizability evaluation model, fine-tuned using recently synthesized structures to enhance predictive accuracy, is employed in conjunction with ab initio calculations to systematically identify synthesizable candidates. The framework successfully reproduces 13 experimentally known XSe (X = Sc, Ti, Mn, Fe, Ni, Cu, Zn) structures, demonstrating its effectiveness in predicting synthesizable structures. Notably, 92,310 structures are filtered from the 554,054 candidates predicted by GNoME, exhibiting great potential for promising synthesizability. Additionally, eight thermodynamically favorable Hf-X-O (X = Ti, V, and Mn) structures have been identified, among which three HfV$_2$O$_7$ candidates exhibit high synthesizability, presenting viable candidates for experimental realization and potentially associated with experimentally observed temperature-induced phase transitions. This work establishes a data-driven paradigm for machine-learning-assisted inorganic materials synthesis, highlighting its potential to bridge the gap between computational predictions and experimental realization while unlocking new opportunities for the targeted discovery of novel functional materials.

cond-mat.mtrl-sci↗

arXiv2025

FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection

Embedded flight devices with visual capabilities have become essential for a wide range of applications. In aerial image detection, while many existing methods have partially addressed the issue of small target detection, challenges remain in optimizing small target detection and balancing detection accuracy with efficiency. These issues are key obstacles to the advancement of real-time aerial image detection. In this paper, we propose a new family of real-time detectors for aerial image detection, named FBRT-YOLO, to address the imbalance between detection accuracy and efficiency. Our method comprises two lightweight modules: Feature Complementary Mapping Module (FCM) and Multi-Kernel Perception Unit(MKP), designed to enhance object perception for small targets in aerial images. FCM focuses on alleviating the problem of information imbalance caused by the loss of small target information in deep networks. It aims to integrate spatial positional information of targets more deeply into the network,better aligning with semantic information in the deeper layers to improve the localization of small targets. We introduce MKP, which leverages convolutions with kernels of different sizes to enhance the relationships between targets of various scales and improve the perception of targets at different scales. Extensive experimental results on three major aerial image datasets, including Visdrone, UAVDT, and AI-TOD,demonstrate that FBRT-YOLO outperforms various real-time detectors in terms of performance and speed.

cs.CV↗

arXiv2025

MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation

We introduce Masked Anchored SpHerical Distances (MASH), a novel multi-view and parametrized representation of 3D shapes. Inspired by multi-view geometry and motivated by the importance of perceptual shape understanding for learning 3D shapes, MASH represents a 3D shape as a collection of observable local surface patches, each defined by a spherical distance function emanating from an anchor point. We further leverage the compactness of spherical harmonics to encode the MASH functions, combined with a generalized view cone with a parameterized base that masks the spatial extent of the spherical function to attain locality. We develop a differentiable optimization algorithm capable of converting any point cloud into a MASH representation accurately approximating ground-truth surfaces with arbitrary geometry and topology. Extensive experiments demonstrate that MASH is versatile for multiple applications including surface reconstruction, shape generation, completion, and blending, achieving superior performance thanks to its unique representation encompassing both implicit and explicit features.

cs.CV↗

arXiv2025

Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis

Vision-language models (VLMs) have shown promise in 2D medical image analysis, but extending them to 3D remains challenging due to the high computational demands of volumetric data and the difficulty of aligning 3D spatial features with clinical text. We present Med3DVLM, a 3D VLM designed to address these challenges through three key innovations: (1) DCFormer, an efficient encoder that uses decomposed 3D convolutions to capture fine-grained spatial features at scale; (2) SigLIP, a contrastive learning strategy with pairwise sigmoid loss that improves image-text alignment without relying on large negative batches; and (3) a dual-stream MLP-Mixer projector that fuses low- and high-level image features with text embeddings for richer multi-modal representations. We evaluate our model on the M3D dataset, which includes radiology reports and VQA data for 120,084 3D medical images. Results show that Med3DVLM achieves superior performance across multiple benchmarks. For image-text retrieval, it reaches 61.00% R@1 on 2,000 samples, significantly outperforming the current state-of-the-art M3D model (19.10%). For report generation, it achieves a METEOR score of 36.42% (vs. 14.38%). In open-ended visual question answering (VQA), it scores 36.76% METEOR (vs. 33.58%), and in closed-ended VQA, it achieves 79.95% accuracy (vs. 75.78%). These results highlight Med3DVLM's ability to bridge the gap between 3D imaging and language, enabling scalable, multi-task reasoning across clinical applications. Our code is publicly available at https://github.com/mirthAI/Med3DVLM.

cs.CV↗

arXiv2025

ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting

We tackle the challenge of concurrent reconstruction at the part level with the RGB appearance and estimation of motion parameters for building digital twins of articulated objects using the 3D Gaussian Splatting (3D-GS) method. With two distinct sets of multi-view imagery, each depicting an object in separate static articulation configurations, we reconstruct the articulated object in 3D Gaussian representations with both appearance and geometry information at the same time. Our approach decoupled multiple highly interdependent parameters through a multi-step optimization process, thereby achieving a stable optimization procedure and high-quality outcomes. We introduce ArticulatedGS, a self-supervised, comprehensive framework that autonomously learns to model shapes and appearances at the part level and synchronizes the optimization of motion parameters, all without reliance on 3D supervision, motion cues, or semantic labels. Our experimental results demonstrate that, among comparable methodologies, our approach has achieved optimal outcomes in terms of part segmentation accuracy, motion estimation accuracy, and visual quality.

cs.CV↗

arXiv2025

Zero-Shot Hashing Based on Reconstruction With Part Alignment

Hashing algorithms have been widely used in large-scale image retrieval tasks, especially for seen class data. Zero-shot hashing algorithms have been proposed to handle unseen class data. The key technique in these algorithms involves learning features from seen classes and transferring them to unseen classes, that is, aligning the feature embeddings between the seen and unseen classes. Most existing zero-shot hashing algorithms use the shared attributes between the two classes of interest to complete alignment tasks. However, the attributes are always described for a whole image, even though they represent specific parts of the image. Hence, these methods ignore the importance of aligning attributes with the corresponding image parts, which explicitly introduces noise and reduces the accuracy achieved when aligning the features of seen and unseen classes. To address this problem, we propose a new zero-shot hashing method called RAZH. We first use a clustering algorithm to group similar patches to image parts for attribute matching and then replace the image parts with the corresponding attribute vectors, gradually aligning each part with its nearest attribute. Extensive evaluation results demonstrate the superiority of the RAZH method over several state-of-the-art methods.

cs.CV↗

arXiv2025

DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions

Vision-language models (VLMs) have been widely applied to 2D medical image analysis due to their ability to align visual and textual representations. However, extending VLMs to 3D imaging remains computationally challenging. Existing 3D VLMs often rely on Vision Transformers (ViTs), which are computationally expensive due to the quadratic complexity of self-attention, or on 3D convolutions, which require large numbers of parameters and FLOPs as kernel size increases. We introduce DCFormer, an efficient 3D image encoder that factorizes 3D convolutions into three parallel 1D convolutions along the depth, height, and width dimensions. This design preserves spatial information while significantly reducing computational cost. Integrated into a CLIP-based vision-language framework, DCFormer is trained and evaluated on CT-RATE, a dataset of 50,188 paired 3D chest CT volumes and radiology reports. In zero-shot and fine-tuned detection of 18 pathologies, as well as in image-text retrieval tasks, DCFormer consistently outperforms state-of-the-art 3D vision encoders, including CT-ViT, ViT, ConvNeXt, PoolFormer, and TransUNet. These results highlight DCFormer's potential for scalable, clinically deployable 3D medical VLMs. Our code is available at: https://github.com/mirthAI/DCFormer.

cs.CV↗

arXiv2024

BATseg: Boundary-aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans

Spinal cord tumors significantly contribute to neurological morbidity and mortality. Precise morphometric quantification, encompassing the size, location, and type of such tumors, holds promise for optimizing treatment planning strategies. Although recent methods have demonstrated excellent performance in medical image segmentation, they primarily focus on discerning shapes with relatively large morphology such as brain tumors, ignoring the challenging problem of identifying spinal cord tumors which tend to have tiny sizes, diverse locations, and shapes. To tackle this hard problem of multiclass spinal cord tumor segmentation, we propose a new method, called BATseg, to learn a tumor surface distance field by applying our new multiclass boundary-aware loss function. To verify the effectiveness of our approach, we also introduce the first and large-scale spinal cord tumor dataset. It comprises gadolinium-enhanced T1-weighted 3D MRI scans from 653 patients and contains the four most common spinal cord tumor types: astrocytomas, ependymomas, hemangioblastomas, and spinal meningiomas. Extensive experiments on our dataset and another public kidney tumor segmentation dataset show that our proposed method achieves superior performance for multiclass tumor segmentation.

eess.IV↗

arXiv2024

On the $\mathrm{Sp}_{2n}$-distinguished automorphic spectrum of $\mathrm{U}_{2n}$

Given a reductive group $G$ and a reductive subgroup $H$, both defined over a number field $F$, we introduce the notion of the $H$-distinguished automorphic spectrum of $G$ and analyze it for the pair $(\mathrm{U}_{2n},\mathrm{Sp}_{2n})$. We derived a formula for period integrals of pseudo-Eisenstein series of $\mathrm{U}_{2n}$ in analogy with the main result of Lapid and Offen in their work analyzing the pair $(\mathrm{Sp}_{4n},\mathrm{Sp}_{2n} \times \mathrm{Sp}_{2n})$. We give an upper bound of the distinguished spectrum with the formula. A non-trivial lower bound of the discrete distinguished spectrum is expected from the formula, given the previous work.

math.NT↗

arXiv2024

On the Rankin-Selberg gamma factor of simple supercuspidal representations of the unitary group for $p$-adic local fields

Let $\pi$ be a simple supercuspidal representation of the quasi-split unramified even unitary group with respect to an unramified quadratic extension $E/F$ of $p$-adic fields. We compute the Rankin-Selberg gamma factor for rank-$1$ twists of $\pi$ by a tamely ramified character of $E^\times$. For non-dyadic cases, the gamma factor can also be recovered by considering the endoscopic lift of the representation. For the dyadic case, the result is original and we expect to extend the results on the Langlands parameter of the simple supercuspidal representations to the dyadic case with our computation.

math.NT↗