papers

Publications (146)

cs.LG2026

UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma

Chongyu Fan, Pengfei Liu, Jingjia Huang +2

Reinforcement learning (RL) has become the standard paradigm for enhancing the complex reasoning capabilities of large language models (LLMs). To achieve sample efficiency, modern…

cs.CV2026

BrainFIBRE: A Foundation Model via Information Decomposition for Brain Microstructure

Zijian Dong, Yi Lin, Ji Fang +4

Diffusion MRI probes brain microstructure with particular sensitivity to early cerebrovascular and neurodegenerative changes. Neurite Orientation Dispersion and Density Imaging (NO…

math.SG2022

Riemannian foliations and geometric quantization

Yi Lin, Yiannis Loizides, Reyer Sjamaar +1

We introduce geometric quantization for constant rank presymplectic structures with Riemannian null foliation and compact leaf closure space. We prove a quantization-commutes-with-…

math.SG2006

Examples of Non-Kähler Hamiltonian circle manifolds with the strong Lefschetz property

Yi Lin

In this paper we construct six-dimensional compact non-Kähler Hamiltonian circle manifolds which satisfy the strong Lefschetz property themselves but nevertheless have a non-Lefsc…

cs.CV2025

A Disease-Aware Dual-Stage Framework for Chest X-ray Report Generation

Puzhen Wu, Hexin Dong, Yi Lin +2

Radiology report generation from chest X-rays is an important task in artificial intelligence with the potential to greatly reduce radiologists' workload and shorten patient wait t…

cs.CV2024

BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels

Yi Lin, Zeyu Wang, Dong Zhang +2

Nuclei segmentation is a fundamental prerequisite in the digital pathology workflow. The development of automated methods for nuclei segmentation enables quantitative analysis of t…

cs.CV2026

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Zhaowei Wang, Lishu Luo, Haodong Duan +9

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video…

cs.CV2025

Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions

Cheng Jin, Zhengrui Guo, Yi Lin +2

Deep learning has significantly advanced medical imaging analysis (MIA), achieving state-of-the-art performance across diverse clinical tasks. However, its success largely depends…

cs.CL2026

RSNA Large Language Model Benchmark Dataset for Chest Radiographs of Cardiothoracic Disease: Radiologist Evaluation and Validation Enhanced by AI Labels (REVEAL-CXR)

Yishu Wei, Adam E. Flanders, Errol Colak +35

Multimodal large language models have demonstrated comparable performance to that of radiology trainees on multiple-choice board-style exams. However, to develop clinically useful…

cs.RO2021

Fast-Racing: An Open-source Strong Baseline for SE(3) Planning in Autonomous Drone Racing

Zhichao Han, Zhepei Wang, Neng Pan +3

With the autonomy of aerial robots advances in recent years, autonomous drone racing has drawn increasing attention. In a professional pilot competition, a skilled operator always…

cond-mat.mes-hall2024

Ultrafast creation of a light induced semimetallic state in strongly excited 1T-TiSe

Maximilian Huber, Yi Lin, Giovanni Marini +5

Screening, a ubiquitous phenomenon associated with the shielding of electric fields by surrounding charges, has been widely adopted as a means to modify a material's properties. Wh…

eess.IV2024

LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction

Yi Lin, Yanfei Liu, Hao Chen +4

Radiation therapy treatment planning requires balancing the delivery of the target dose while sparing normal tissues, making it a complex process. To streamline the planning proces…

cs.CL2025

MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity

Kaiyuan Zhang, Chenghao Yang, Zhoufutu Wen +19

As reasoning models scale rapidly, the essential role of multimodality in human cognition has come into sharp relief, driving a growing need to probe vision-centric cognitive behav…

cs.CV2024

Revisiting Deep Ensemble Uncertainty for Enhanced Medical Anomaly Detection

Yi Gu, Yi Lin, Kwang-Ting Cheng +1

Medical anomaly detection (AD) is crucial in pathological identification and localization. Current methods typically rely on uncertainty estimation in deep ensembles to detect anom…

cs.LG2025

Virtual Width Networks

Seed, Baisheng Li, Banggu Wu +115

We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…

hep-ph2023

Resonance contributions from in the charmless three-body hadronic meson decays

Ya-Lan Zhang, Chao Wang, Yi Lin +1

Within the framework of perturbative QCD factorization, we investigate the nonfactorizable contributions to these factorization-forbidden Quasi-two-body decays $B_{(s)}\rightarrow…

math.SG2019

Kirwan Surjectivity for the Equivariant Dolbeault cohomology

Yi Lin

Consider the holomorphic Hamiltonian action of a compact Lie group on a compact Kähler manifold with a moment map . Assume that is a r…

stat.ME2016

Exact prior-free probabilistic inference in a class of non-regular models

Ryan Martin, Yi Lin

The use of standard statistical methods, such as maximum likelihood, is often justified based on their asymptotic properties. For suitably regular models, this theory is standard b…

math.DG2008

Topology of generalized complex quotients

Thomas Baird, Yi Lin

Consider the Hamiltonian action of a torus on a compact twisted generalized complex manifold . We first observe that Kirwan injectivity and surjectivity hold for ordinary equiva…

cs.AI2026

Towards end-to-end LLM-based censoring-aware survival analysis

Yishu Wei, Hexin Dong, Yi Lin +3

Objective: Survival analysis is central to medical prediction, yet large language models (LLMs) are rarely used as end-to-end survival models because censoring prevents straightfor…

math.DG2020

Cohomological localization for transverse Lie algebra actions on Riemannian foliations

Yi Lin, Reyer Sjamaar

We prove localization and integration formulas for the equivariant basic cohomology of Riemannian foliations. As a corollary we obtain a Duistermaat-Heckman theorem for transversel…

cs.CE2022

Improving the estimation of directional area scattering factor (DASF) from canopy reflectance: theoretical basis and validation

Yi Lin, Siyuan Liu, Lei Yan +3

Directional area scattering factor (DASF) is a critical canopy structural parameter for vegetation monitoring. It provides an efficient tool for decoupling of canopy structure and…

math.DG2007

Generalized geometry, equivariant -lemma, and torus actions

Yi Lin

In this paper we first consider the Hamiltonian action of a compact connected Lie group on an -twisted generalized complex manifold . Given such an action, we define generali…

cs.AI2026

MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation

Yi Lin, Yihao Ding, Yonghui Wu +1

Automated 3D radiology report generation often suffers from clinical hallucinations and a lack of the iterative verification found in human practice. While recent Vision-Language M…

math.DG2005

Symmetries in generalized Kähler geometry

Yi Lin, Susan Tolman

We define the notion of a moment map and reduction in both generalized complex geometry and generalized Kähler geometry. As an application, we give very simple explicit constructi…

cs.CV2021

Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network

Yi Lin, Jianchao Su, Xiang Wang +4

Automated methods for detecting pulmonary embolisms (PEs) on CT pulmonary angiography (CTPA) images are of high demand. Existing methods typically employ separate steps for PE cand…

cs.CV2019

STELA: A Real-Time Scene Text Detector with Learned Anchor

Linjie Deng, Yanxiang Gong, Xinchen Lu +3

To achieve high coverage of target boxes, a normal strategy of conventional one-stage anchor-based detectors is to utilize multiple priors at each spatial position, especially in s…

cs.CV2021

A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories

Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang +4

Recent work in computer vision and cognitive reasoning has given rise to an increasing adoption of the Violation-of-Expectation (VoE) paradigm in synthetic datasets. Inspired by in…

cs.RO2022

Dynamic Free-Space Roadmap for Safe Quadrotor Motion Planning

Junlong Guo, Zhiren Xun, Shuang Geng +3

Free-space-oriented roadmaps typically generate a series of convex geometric primitives, which constitute the safe region for motion planning. However, a static environment is assu…

physics.optics2021

Dual-microcomb generation in a synchronously-driven waveguide ring resonator

Yiqing Xu, Miro Erkintalo, Yi Lin +3

Microcombs -- optical frequency combs generated in coherently-driven nonlinear microresonators -- have attracted significant attention over the last decade. The ability to generate…

cs.CV2023

Exploring Visual Prompts for Whole Slide Image Classification with Multiple Instance Learning

Yi Lin, Zhongchen Zhao, Zhengjie ZHU +3

Multiple instance learning (MIL) has emerged as a popular method for classifying histopathology whole slide images (WSIs). However, existing approaches typically rely on pre-traine…

cs.CV2025

LLM-driven Medical Report Generation via Communication-efficient Heterogeneous Federated Learning

Haoxuan Che, Haibo Jin, Zhengrui Guo +3

LLMs have demonstrated significant potential in Medical Report Generation (MRG), yet their development requires large amounts of medical image-report pairs, which are commonly scat…

eess.IV2024

Continuous 3D Myocardial Motion Tracking via Echocardiography

Chengkang Shen, Hao Zhu, You Zhou +8

Myocardial motion tracking stands as an essential clinical tool in the prevention and detection of cardiovascular diseases (CVDs), the foremost cause of death globally. However, cu…

cond-mat.mtrl-sci2022

Exciton-Driven Renormalization of Quasiparticle Band Structure in Monolayer MoS2

Yi Lin, Yang-hao Chan, Woojoo Lee +7

Optical excitation serves as a powerful approach to control the electronic structure of layered Van der Waals materials via many-body screening effects, induced by photoexcited fre…

cs.FL2024

Dynamic Programming for Symbolic Boolean Realizability and Synthesis

Yi Lin, Lucas M. Tabajara, Moshe Y. Vardi

Inspired by recent progress in dynamic programming approaches for weighted model counting, we investigate a dynamic-programming approach in the context of boolean realizability and…

cs.CV2026

MonteRET: AI Agent Enhancing Multimodal LLMs with Multi-granularity Knowledge Retrieval for Chest CT Report Generation

Yi Lin, Yihao Ding, Elana Benishay +8

MonteRET is an AI system that combines whole‑volume CT features with region‑level anatomical information and knowledge retrieval to automatically generate more complete and clinica…

#chest ct#report generation#multimodal retrieval#region-aware modeling
cs.CV2025

DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentation

Chuang Chen, Yi Lin, Bo Wang +3

Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing accurate 3D point cloud data. Effic…

cond-mat.mes-hall2020

Momentum resolved ground/excited states and the ultra-fast excited state dynamics of monolayer MoS2

Woojoo Lee, Yi Lin, Li-Shuan Lu +6

The emergence of transition metal dichalcogenides (TMD) as crystalline atomically thin semiconductors has created a tremendous amount of scientific and technological interest. Many…

math.DG2024

Equivariant Morse theory for Lie algebra actions on Riemannian foliations

Yi Lin, Zuoqin Wang

Consider the transverse isometric action of a finite dimensional Lie algebra g on a Riemannian foliation. This paper studies the equivariant Morse-Bott theory on the leaf space of…

cs.SD2021

Improving speech recognition models with small samples for air traffic control systems

Yi Lin, Qin Li, Bo Yang +3

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since t…

cs.CV2022

Seg4Reg+: Consistency Learning between Spine Segmentation and Cobb Angle Regression

Yi Lin, Luyan Liu, Kai Ma +1

Automated methods for Cobb angle estimation are of high demand for scoliosis assessment. Existing methods typically calculate the Cobb angle from landmark estimation, or simply com…

math.SG2022

Basic Kirwan injectivity and its applications

Yi Lin, Xiangdong Yang

Consider the Hamiltonian action of a torus on a transversely symplectic foliation that is also Riemannian. When the transverse hard Lefschetz property is satisfied, we establish a…

math.ST2007

Component selection and smoothing in multivariate nonparametric regression

Yi Lin, Hao Helen Zhang

We propose a new method for model selection and model fitting in multivariate nonparametric regression models, in the framework of smoothing spline ANOVA. The ``COSSO'' is a method…

cs.CV2024

Prompt-Guided Foundation Model Tuning for Pathology Image Classification

Yi Lin, Zhengjie Zhu, Kwang-Ting Cheng +1

Foundation models have become pivotal in advancing computational pathology, particularly for whole slide image (WSI) classification. However, prevailing methodologies often rely on…

math.DG2024

Riemannian foliations and quasifolds

Yi Lin, David Miyamoto

It is well known that, by the Reeb stability theorem, the leaf space of a Riemannian foliation with compact leaves is an orbifold. We prove that, under mild completeness conditions…

math.SG2012

Log-concavity and symplectic flows

Yi Lin, Álvaro Pelayo

Let M be a compact, connected symplectic 2n-dimensional manifold on which an(n-2)-dimensional torus T acts effectively and Hamiltonianly. Under the assumption that there is an effe…

eess.IV2023

Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks

Xin Yang, Yi Lin, Zhiwei Wang +2

In this paper, we propose a bi-modality medical image synthesis approach based on sequential generative adversarial network (GAN) and semi-supervised learning. Our approach consist…

cs.SD2022

A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches

Dongyue Guo, Jianwei Zhang, Bo Yang +1

Automatic spoken instruction understanding (SIU) of the controller-pilot conversations in the air traffic control (ATC) requires not only recognizing the words and semantics of the…

cs.LG2022

Explainable and Safe Reinforcement Learning for Autonomous Air Mobility

Lei Wang, Hongyu Yang, Yi Lin +2

Increasing traffic demands, higher levels of automation, and communication enhancements provide novel design opportunities for future air traffic controllers (ATCs). This article p…

cs.CV2025

DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World

Xiangtai Li, Tao Zhang, Yanwei Li +13

Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack t…

cs.AI2026

Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports

Yishu Wei, Yi Lin, Adam Flanders +2

Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade…

cs.CV2023

Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation

Xiaoyang Lyu, Peng Dai, Zizhang Li +4

Implicit neural rendering, which uses signed distance function (SDF) representation with geometric priors (such as depth or surface normal), has led to impressive progress in the s…

math.SG2008

The log-concavity conjecture for the Duistermaat-Heckman measure revisited

Yi Lin

Karshon constructed the first counterexample to the log-concavity conjecture for the Duistermaat-Heckman measure: a Hamiltonian six manifold whose fixed points set is the disjoint…

math.SG2018

Equivariant formality of transversely symplectic foliations and Frobenius manifolds

Yi Lin, Xiangdong Yang

Consider the Hamiltonian action of a compact connected Lie group on a transversely symplectic foliation which satisfies the transverse hard Lefschetz property. We establish an equi…

eess.SP2019

Generation of Spectrally-Efficient Superchannel Using Optical Frequency Comb Referencing and Active Demultiplexing

Yi Lin, Seán Ó Duill, Frank Smyth +3

We generate multiple optical carriers with ultra-low phase noise, over a useable bandwidth of 160 GHz, from an externally injected gain-switched comb source with exceptional low li…

cond-mat.str-el2022

Mapping the dispersion of the occupied and unoccupied band structure in photoexcited 1T-TiSe

Maximilian Huber, Yi Lin, Nicholas Dale +4

Charge density waves (CDW) are states of broken symmetry with a periodic modulation of charge and lattice typically leading to the opening of a gap in the band structure. In the mo…

cs.LG2026

ProSpec RL: Plan Ahead, then Execute

Liangliang Liu, Yi Guan, BoRan Wang +5

Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstre…

math.ST2019

On optimal designs for non-regular models

Yi Lin, Ryan Martin, Min Yang

Classically, Fisher information is the relevant object in defining optimal experimental designs. However, for models that lack certain regularity, the Fisher information does not e…

physics.optics2020

Harmonic and rational harmonic driving of microresonator soliton frequency combs

Yiqing Xu, Yi Lin, Alexander Nielsen +5

With demonstrated applications ranging from metrology to telecommunications, soliton microresonator frequency combs have emerged over the past decade as a remarkable new technology…

math.CO2026

Kirillov's conjecture on Hecke-Grothendieck polynomials

Ben Brubaker, A. Suki Dasher, Michael Hu +6

We use algebraic methods in statistical mechanics to represent a multi-parameter class of polynomials in several variables as partition functions of a new family of solvable lattic…

cs.AI2026

BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments

Yuxuan Li, Yi Lin, Peng Wang +2

The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their deployment as autonomous decision-makers introduce…

math.DG2009

Generalized complex hamiltonian torus actions: Examples and constraints

Thomas Baird, Yi Lin

Consider an effective Hamiltonian torus action on a topologically twisted,generalized complex manifold of dimension . We prove that the

physics.app-ph2019

Real-Time Machine Learning Based Fiber-Induced Nonlinearity Compensation in Energy-Efficient Coherent Optical Networks

Elias Giacoumidis, Yi Lin, Michaela Blott +1

We experimentally demonstrate the first field-programmable gate-array-based real-time fiber nonlinearity compensator (NLC) using sparse K-means++ machine learning clustering in an…

cs.CV2019

Detecting Multi-Oriented Text with Corner-based Region Proposals

Linjie Deng, Yanxiang Gong, Yi Lin +5

Previous approaches for scene text detection usually rely on manually defined sliding windows. This work presents an intuitive two-stage region-based method to detect multi-oriente…

math.SG2013

Symplectic Harmonic theory and the Federer-Fleming deformation theorem

Yi Lin

In this article, we initiate a geometric measure theoretic approach to symplectic Hodge theory. In particular, we apply one of the central results in geometric measure theory, the…

cs.AI2026

Value-Decomposed Reinforcement Learning Framework for Taxiway Routing with Hierarchical Conflict-Aware Observations

Shizhong Zhou, Haifeng Liu, Zheng Zhang +3

Taxiway routing and on-surface conflict avoidance are coupled safety-critical decision problems in airport surface operations. Existing planning and optimization methods are often…

cs.LG2018

Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization

Zhiwei Wang, Yi Lin, Kwang-Ting Cheng +1

In this paper, we address the problem of synthesizing multi-parameter magnetic resonance imaging (mp-MRI) data, i.e. Apparent Diffusion Coefficients (ADC) and T2-weighted (T2w), co…

cs.SD2024

ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning

Xincheng Yu, Dongyue Guo, Jianwei Zhang +1

Radio speech echo is a specific phenomenon in the air traffic control (ATC) domain, which degrades speech quality and further impacts automatic speech recognition (ASR) accuracy. I…

cs.SD2024

Integrating spoken instructions into flight trajectory prediction to optimize automation in air traffic control

Dongyue Guo, Zheng Zhang, Bo Yang +3

The booming air transportation industry inevitably burdens air traffic controllers' workload, causing unexpected human factor-related incidents. Current air traffic control systems…

cs.CV2021

A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks

Qingsong Yao, Zecheng He, Yi Lin +3

Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making. Luckily, medical A…

cs.LG2024

A Non-autoregressive Multi-Horizon Flight Trajectory Prediction Framework with Gray Code Representation

Dongyue Guo, Zheng Zhang, Zhen Yan +2

Flight Trajectory Prediction (FTP) is an essential task in Air Traffic Control (ATC), which can assist air traffic controllers in managing airspace more safely and efficiently. Exi…

math.SG2017

Convexity properties of presymplectic moment maps

Yi Lin, Reyer Sjamaar

The convexity and Morse-theoretic properties of moment maps in symplectic geometry typically fail for presymplectic manifolds. We find a condition on presymplectic moment maps that…

physics.atom-ph2024

Enhancing sensitivity of atomic microwave receiver combining laser arrays

Bo Wu, Ruiqi Mao, Yi Liu +5

Rydberg atom,which exhibits a strong response to weak electric(E) fields,is regarded as a promising atomic receiver to surpass sensitivity of conventional receivers. However, its s…

math.SG2022

Log symplectic manifolds and

Yi Lin, Yiannis Loizides, Reyer Sjamaar +1

We show, under an orientation hypothesis, that a log symplectic manifold with simple normal crossing singularities has a stable almost complex structure, and hence is Spin. In…

math.OC2023

Penalties and Rewards for Fair Learning in Paired Kidney Exchange Programs

Margarida Carvalho, Alison Caulfield, Yi Lin +1

A kidney exchange program, also called a kidney paired donation program, can be viewed as a repeated, dynamic trading and allocation mechanism. This suggests that a dynamic algorit…

eess.IV2022

InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation

Yi Lin, Zeyu Wang, Kwang-Ting Cheng +1

Nuclei Segmentation from histology images is a fundamental task in digital pathology analysis. However, deep-learning-based nuclei segmentation methods often suffer from limited an…

eess.SY2023

Parallel Computing Based Solution for Reliability-Constrained Distribution Network Planning

Yaqi Sun, Wenchuan Wu, Yi Lin +2

The main goal of distribution network (DN) expansion planning is essentially to achieve minimal investment constrained with specified reliability requirements. The reliability-cons…

math.SG2003

Equivariant symplectic Hodge theory and the -lemma

Yi Lin, Reyer Sjamaar

Consider a Hamiltonian action of a compact Lie group on a symplectic manifold which has the strong Lefschetz property. We establish an equivariant version of the Merkulov-Guillemin…

cs.LG2026

Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting

Wenjie Ou, Zhishuo Zhao, Cheng Chen +2

Time series forecasting is critical across multiple domains, where time series data exhibit both local patterns and global dependencies. While Transformer-based methods effectively…

eess.IV2025

Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation

Jiabo Ma, Zhengrui Guo, Fengtao Zhou +20

Foundation models pretrained on large-scale datasets are revolutionizing the field of computational pathology (CPath). The generalization ability of foundation models is crucial fo…

eess.IV2022

Deep Learning for Computational Cytology: A Survey

Hao Jiang, Yanning Zhou, Yi Lin +3

Computational cytology is a critical, rapid-developing, yet challenging topic in the field of medical image computing which analyzes the digitized cytology image by computer-aided…

cs.CV2023

Disorder-invariant Implicit Neural Representation

Hao Zhu, Shaowen Xie, Zhen Liu +6

Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problem…

cs.CV2026

Overview of the CXR-LT 2026 Challenge: Multi-Center Long-Tailed and Zero Shot Chest X-ray Classification

Hexin Dong, Yi Lin, Pengyu Zhou +7

Chest X-ray (CXR) interpretation is hindered by the long-tailed distribution of pathologies and the open-world nature of clinical environments. Existing benchmarks often rely on cl…

math.DG2020

A Thom isomorphism in foliated de Rham theory

Yi Lin, Reyer Sjamaar

We prove a Thom isomorphism theorem for differential forms in the setting of transverse Lie algebra actions on foliated manifolds and foliated vector bundles.

q-bio.NC2025

Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens

Zijian Dong, Ruilin Li, Joanna Su Xian Chong +9

We present Brain Harmony (BrainHarmonix), the first multimodal brain foundation model that unifies structural morphology and functional dynamics into compact 1D token representatio…

cs.AI2025

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Haoming Wang, Haoyang Zou, Huatong Song +109

The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have sh…

math.DG2026

A Transverse Averaging Operator and Cohomology of Quotients by Homogeneous Non-closed Subgroups

Yi Lin

In this article, we introduce a transverse averaging operator for basic forms on a complete Riemannian foliation with compact leaf closure space, equipped with an isometric transve…

cs.CV2026

Masked Face Recognition under Different Backbones

Bo Zhang, Ming Zhang, Kun Wu +2

Erratum to the paper (Zhang et al., 2025): corrections to Table IV and the data in Page 3, Section A. In the post-pandemic era, a high proportion of civil aviation passengers wear…

cs.CL2025

Expert-Token Resonance MoE: Bidirectional Routing with Efficiency Affinity-Driven Active Selection

Jing Li, Zhijie Sun, Dachao Lin +5

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer fr…

eess.IV2020

Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes

Xin Yang, Xu Wang, Yi Wang +6

Background and Objective: Biometric measurements of fetal head are important indicators for maternal and fetal health monitoring during pregnancy. 3D ultrasound (US) has unique adv…

cs.CV2025

An Effective UNet Using Feature Interaction and Fusion for Organ Segmentation in Medical Image

Xiaolin Gou, Chuanlin Liao, Jizhe Zhou +2

Nowadays, pre-trained encoders are widely used in medical image segmentation due to their strong capability in extracting rich and generalized feature representations. However, exi…

math.DG2026

De Rham Cohomology of Certain Diffeological Quotients

Yi Lin

Hector, Mac\'ıas-Virgós, and Sanmart\'ın-Carbón identified the complex of diffeological differential forms on the leaf space of a foliation with the complex of basic differenti…

cs.RO2026

ARGOS: Automated Functional Safety Requirement Synthesis for Embodied AI via Attribute-Guided Combinatorial Reasoning

Dongsheng Chen, Yuxuan Li, Yi Lin +6

Ensuring functional safety is essential for the deployment of Embodied AI in complex open-world environments. However, traditional Hazard Analysis and Risk Assessment (HARA) method…

cs.CV2024

Iterative Online Image Synthesis via Diffusion Model for Imbalanced Classification

Shuhan Li, Yi Lin, Hao Chen +1

Accurate and robust classification of diseases is important for proper diagnosis and treatment. However, medical datasets often face challenges related to limited sample sizes and…

cs.CL2019

ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment

Bo Yang, Xianlong Tan, Zhengmao Chen +5

Automatic Speech Recognition (ASR) is greatly developed in recent years, which expedites many applications on other fields. For the ASR research, speech corpus is always an essenti…

eess.SY2024

Tunable Superconducting Magnetic Levitation with Self-Stability

Qi Xu, Yi Lin, Yunfei Tan +1

Magnetic levitation based on the flux pinning nature of type II superconductors has the merit of self-stability, making it appealing for applications such as high speed bearings, m…

cs.LG2022

Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction

Yuankai Wu, Hongyu Yang, Yi Lin +1

Demystifying the delay propagation mechanisms among multiple airports is fundamental to precise and interpretable delay prediction, which is crucial during decision-making for all…

math.SG2016

Lefschetz contact manifolds and odd dimensional symplectic geometry

Yi Lin

In the literature, there are two different versions of Hard Lefschetz theorems for a compact Sasakian manifold. The first version, due to Kacimi-Alaoui, asserts that the basic coho…

cs.CV2025

Visual Spatial Tuning

Rui Yang, Ziyu Zhu, Yanwei Li +9

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Visi…

math.DG2005

Reduction of twisted generalized Kähler structure

Yi Lin, Susan Tolman

We show that our earlier work in \cite{LT05} extends to the twisted case, that is, we defined a notion of moment map and reduction in both twisted generalized complex geometry and…