arXiv subjects

Yan Yang

Publications and source records attributed to Yan Yang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Variational analysis of determinantal varieties

Determinantal varieties -- the sets of bounded-rank matrices or tensors -- have attracted growing interest in low-rank optimization. The tangent cone to low-rank sets is widely studied and underpins a range of geometric methods. The second-order geometry, which encodes curvature information, is more intricate. In this work, we develop a unified framework to derive explicit formulas for both first- and second-order tangent sets to various low-rank sets, including low-rank matrices, tensors, symmetric matrices, and positive semidefinite matrices. The framework also accommodates the intersection of a low-rank set and another set satisfying mild assumptions, thereby yielding a tangent intersection rule. Through the lens of tangent sets, we establish a necessary and sufficient condition under which a nonsmooth problem and its smooth parameterization share equivalent second-order stationary points. Moreover, we exploit tangent sets to characterize optimality conditions for low-rank optimization and prove that verifying second-order optimality is NP-hard. In a separate line of analysis, we investigate variational geometry of the graph of the normal cone to matrix varieties, deriving the explicit Bouligand tangent cone, Fréchet and Mordukhovich normal cones to the graph. These results are further applied to develop optimality conditions for low-rank bilevel programs.

math.OC↗

arXiv2025

From Spots to Pixels: Dense Spatial Gene Expression Prediction from Histology Images

Spatial transcriptomics (ST) measures gene expression at fine-grained spatial resolution, offering insights into tissue molecular landscapes. Previous methods for spatial gene expression prediction typically crop spots of interest from histopathology slide images, and train models to map each spot to a corresponding gene expression profile. However, these methods inherently lose the spatial resolution in gene expression: 1) each spot often contains multiple cells with distinct gene expression profiles; 2) spots are typically defined at fixed spatial resolutions, limiting the ability to predict gene expression at varying scales. To address these limitations, this paper presents PixNet, a dense prediction network capable of predicting spatially resolved gene expression across spots of varying sizes and scales directly from histopathology slide images. Different from previous methods that map individual spots to gene expression values, we generate a spatially dense continuous gene expression map from the histopathology slide image, and aggregate values within spots of interest to predict the gene expression. Our PixNet outperforms state-of-the-art methods on four common ST datasets in multiple spatial scales. The source code will be publicly available.

cs.CV↗

arXiv2025

Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?

Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world software problems. Such software agents are typically equipped with a suite of coding tools and can autonomously decide the next actions to form complete trajectories to solve end-to-end software tasks. While promising, they typically require dedicated design and may still be suboptimal, since it can be extremely challenging and costly to exhaust the entire agent scaffold design space. Recognizing that software agents are inherently software themselves that can be further refined/modified, researchers have proposed a number of self-improving software agents recently, including the Darwin-Gödel Machine (DGM). Meanwhile, such self-improving agents require costly offline training on specific benchmarks and may not generalize well across different LLMs or benchmarks. In this paper, we propose Live-SWE-agent, the first live software agent that can autonomously and continuously evolve itself on-the-fly during runtime when solving real-world software problems. More specifically, Live-SWE-agent starts with the most basic agent scaffold with only access to bash tools (e.g., mini-SWE-agent), and autonomously evolves its own scaffold implementation while solving real-world software problems. Our evaluation on the widely studied SWE-bench Verified benchmark shows that LIVE-SWE-AGENT can achieve an impressive solve rate of 77.4% without test-time scaling, outperforming all existing software agents, including the best proprietary solution. Moreover, Live-SWE-agent outperforms state-of-the-art manually crafted software agents on the recent SWE-Bench Pro benchmark, achieving the best-known solve rate of 45.8%.

cs.SE↗

arXiv2025

Turbulence in the terrestrial magnetosheath: space-time correlation using the Magnetospheric Multiscale mission

Spatiotemporal correlation of magnetic field fluctuations is investigated using the Magnetospheric Multiscale mission in the terrestrial magnetosheath. The first observation of the turbulence propagator in space emerges through analysis of more than a thousand intervals. Results show clear features of spatial and spectral anisotropy, leading to a distinct behavior of relaxation times in the directions parallel and perpendicular to the mean magnetic field. Full space-time investigation of the Taylor hypothesis reveals a scale-dependent anisotropy of magnetosheath fluctuations that can be compared to the effect of flow propagation on spacecraft frame time decorrelation rates as well as with Eulerian estimates. The turbulence propagator reveals that the amplitudes of the perpendicular modes decorrelate according to sweeping or Alfvénic propagation mechanisms. The decorrelation time of parallel modes instead does not depend on the parallel wavenumber, which could be due to resonant interactions. Through direct observation, this study provides unprecedented insight into the space-time structure of turbulent space plasmas, while giving critical constraints for theoretical and numerical models.

physics.space-ph↗

arXiv2025

Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport

Medical image reconstruction from measurement data is a vital but challenging inverse problem. Deep learning approaches have achieved promising results, but often requires paired measurement and high-quality images, which is typically simulated through a forward model, i.e., retrospective reconstruction. However, training on simulated pairs commonly leads to performance degradation on real prospective data due to the retrospective-to-prospective gap caused by incomplete imaging knowledge in simulation. To address this challenge, this paper introduces imaging Knowledge-Informed Dynamic Optimal Transport (KIDOT), a novel dynamic optimal transport framework with optimality in the sense of preserving consistency with imaging physics in transport, that conceptualizes reconstruction as finding a dynamic transport path. KIDOT learns from unpaired data by modeling reconstruction as a continuous evolution path from measurements to images, guided by an imaging knowledge-informed cost function and transport equation. This dynamic and knowledge-aware approach enhances robustness and better leverages unpaired data while respecting acquisition physics. Theoretically, we demonstrate that KIDOT naturally generalizes dynamic optimal transport, ensuring its mathematical rationale and solution existence. Extensive experiments on MRI and CT reconstruction demonstrate KIDOT's superior performance.

eess.IV↗

arXiv2025

Human-Level and Beyond: Benchmarking Large Language Models Against Clinical Pharmacists in Prescription Review

The rapid advancement of large language models (LLMs) has accelerated their integration into clinical decision support, particularly in prescription review. To enable systematic and fine-grained evaluation, we developed RxBench, a comprehensive benchmark that covers common prescription review categories and consolidates 14 frequent types of prescription errors drawn from authoritative pharmacy references. RxBench consists of 1,150 single-choice, 230 multiple-choice, and 879 short-answer items, all reviewed by experienced clinical pharmacists. We benchmarked 18 state-of-the-art LLMs and identified clear stratification of performance across tasks. Notably, Gemini-2.5-pro-preview-05-06, Grok-4-0709, and DeepSeek-R1-0528 consistently formed the first tier, outperforming other models in both accuracy and robustness. Comparisons with licensed pharmacists indicated that leading LLMs can match or exceed human performance in certain tasks. Furthermore, building on insights from our benchmark evaluation, we performed targeted fine-tuning on a mid-tier model, resulting in a specialized model that rivals leading general-purpose LLMs in performance on short-answer question tasks. The main contribution of RxBench lies in establishing a standardized, error-type-oriented framework that not only reveals the capabilities and limitations of frontier LLMs in prescription review but also provides a foundational resource for building more reliable and specialized clinical tools.

cs.CL↗

arXiv2025

Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene Reconstruction

Dynamic Gaussian Splatting approaches have achieved remarkable performance for 4D scene reconstruction. However, these approaches rely on dense-frame video sequences for photorealistic reconstruction. In real-world scenarios, due to equipment constraints, sometimes only sparse frames are accessible. In this paper, we propose Sparse4DGS, the first method for sparse-frame dynamic scene reconstruction. We observe that dynamic reconstruction methods fail in both canonical and deformed spaces under sparse-frame settings, especially in areas with high texture richness. Sparse4DGS tackles this challenge by focusing on texture-rich areas. For the deformation network, we propose Texture-Aware Deformation Regularization, which introduces a texture-based depth alignment loss to regulate Gaussian deformation. For the canonical Gaussian field, we introduce Texture-Aware Canonical Optimization, which incorporates texture-based noise into the gradient descent process of canonical Gaussians. Extensive experiments show that when taking sparse frames as inputs, our method outperforms existing dynamic or few-shot techniques on NeRF-Synthetic, HyperNeRF, NeRF-DS, and our iPhone-4D datasets.

cs.CV↗

arXiv2025

Fast Time-Varying mmWave MIMO Channel Estimation and Reconstruction: An Efficient Rank-Aware Matrix Completion Method

We address the problem of fast time-varying channel estimation in millimeter-wave (mmWave) MIMO systems with imperfect channel state information (CSI) and facilitate efficient channel reconstruction. Specifically, leveraging the low-rank and sparse characteristics of the mmWave channel matrix, a two-phase rank-aware compressed sensing framework is proposed for efficient channel estimation and reconstruction. In the first phase, a robust rank-one matrix completion (R1MC) algorithm is used to reconstruct part of the observed channel matrix through low-rank matrix completion (LRMC). To address abrupt rank changes caused by user mobility, a discrete-time autoregressive (AR) model is established that leverages temporal rank correlations across consecutive time instances to enable adaptive observation matrix completion, thereby improving estimation accuracy under dynamic conditions. In the second phase, a rank-aware block orthogonal matching pursuit (RA-BOMP) algorithm is developed for sparse channel recovery with low computational complexity. Furthermore, a rank-aware measurement matrix design is introduced to improve angle estimation accuracy. Simulation results demonstrate that, compared with existing benchmark algorithms, the proposed approach achieves superior channel estimation performance while significantly reducing computational complexity and training overhead.

eess.SP↗

arXiv2025

Fast Time-Varying mmWave Channel Estimation: A Rank-Aware Matrix Completion Approach

We consider the problem of high-dimensional channel estimation in fast time-varying millimeter-wave MIMO systems with a hybrid architecture. By exploiting the low-rank and sparsity properties of the channel matrix, we propose a two-phase compressed sensing framework consisting of observation matrix completion and channel matrix sparse recovery, respectively. First, we formulate the observation matrix completion problem as a low-rank matrix completion (LRMC) problem and develop a robust rank-one matrix completion (R1MC) algorithm that enables the matrix and its rank to iteratively update. This approach achieves high-precision completion of the observation matrix and explicit rank estimation without prior knowledge. Second, we devise a rank-aware batch orthogonal matching pursuit (OMP) method for achieving low-latency sparse channel recovery. To handle abrupt rank changes caused by user mobility, we establish a discrete-time autoregressive (AR) model that leverages the temporal rank correlation between continuous-time instances to obtain a complete observation matrix capable of perceiving rank changes for more accurate channel estimates. Simulation results confirm the effectiveness of the proposed channel estimation frame and demonstrate that our algorithms achieve state-of-the-art performance in low-rank matrix recovery with theoretical guarantees.

eess.SP↗

arXiv2025

Symmetry-Driven Asynchronous Forwarding for Reliable Distributed Coordination in Toroidal Networks

The proliferation of large-scale distributed systems, such as satellite constellations and high-performance computing clusters, demands robust communication primitives that maintain coordination under unreliable links. The torus topology, with its inherent rotational and reflection symmetries, is a prevalent architecture in these domains. However, conventional routing schemes suffer from substantial packet loss during control-plane synchronization after link failures. This paper introduces a symmetry-driven asynchronous forwarding mechanism that leverages the torus's geometric properties to achieve reliable packet delivery without control-plane coordination. We model packet flow using a topological potential gradient and demonstrate that symmetry-breaking failures naturally induce a reverse flow, which we harness for fault circumvention. We propose two local forwarding strategies, Reverse Flow with Counter-facing Priority (RF-CF) and Lateral-facing Priority (RF-LF), that guarantee reachability to the destination via forward-flow phase transition points, without protocol modifications or additional in-packet overhead. Through percolation analysis and packet-level simulations on a 16 x 16 torus, we show that our mechanism reduces packet loss by up to 17.5% under a 1% link failure rate, with the RF-LF strategy contributing to 28% of successfully delivered packets. This work establishes a foundational link between topological symmetry and communication resilience, providing a lightweight, protocol-agnostic substrate for enhancing distributed systems.

cs.NI↗

arXiv2025

Cooperative Multi-Static ISAC Networks: A Unified Design Framework for Active and Passive Sensing

Multi-static cooperative sensing emerges as a promising technology for advancing integrated sensing and communication (ISAC), enhancing sensing accuracy and range. In this paper, we develop a unified design framework for joint active and passive sensing (JAPS). In particular, we consider a JAPSbased cooperative multi-static ISAC system for coexisting downlink (DL) and uplink (UL) communications. An optimization problem is formulated for maximizing the sum rate of both the DL and UL transmissions via jointly optimizing beamforming, receive filters and power allocation, while guaranteeing the sensing requirements and transmission power constraints. However, the formulated problem is a non-convex optimization problem that is challenging to solve directly due to the tight coupling among optimization variables. To tackle this complicated issue, we employ an efficient algorithm architecture leveraging alternating optimization (AO). Specifically, with the given receive filters and transmission power for UL communication, the transmit beamforming subproblem is addressed by successive convex approximation (SCA)-based and penalty-based algorithms. A fractional programming (FP)-based algorithm is developed to tackle the receive filters and transmission power for UL communication optimization subproblem. Extensive numerical results validate the performance improvement of our proposed JAPS scheme and demonstrate the effectiveness of our proposed algorithms.

eess.SP↗

arXiv2025

GTA1: GUI Test-time Scaling Agent

Graphical user interface (GUI) agents autonomously complete tasks across platforms (\eg, Linux) by sequentially decomposing user instructions into action proposals that iteratively interact with visual elements in the evolving environment. However, two main challenges arise: i) planning (\ie, the action proposal sequence) under expansive action space, where selecting an appropriate plan is non-trivial, as many valid ones may exist; ii) accurately grounding actions in complex and high-resolution interfaces, \ie, precisely interacting with visual targets. This paper investigates the aforementioned challenges with our \textbf{G}UI \textbf{T}est-time Scaling \textbf{A}gent, namely GTA1. First, we conduct test-time scaling to select the most appropriate action proposal: at each step, multiple candidate proposals are sampled and evaluated and selected by a judge model. It trades off computation for better decision quality by concurrent sampling. Second, we propose a model that improves grounding of the selected action proposals to its corresponding visual elements. Our key insight is that reinforcement learning (RL) facilitates grounding through inherent objective alignments, rewarding successful clicks on interface elements. Experimentally, GTA1 achieves state-of-the-art performance on both grounding and agent task execution benchmarks. The code and models are released here.

cs.AI↗

arXiv2025

A space-decoupling framework for optimization on bounded-rank matrices with orthogonally invariant constraints

Imposing additional constraints on low-rank optimization has garnered growing interest. However, the geometry of coupled constraints hampers the well-developed low-rank structure and makes the problem intricate. To this end, we propose a space-decoupling framework for optimization on bounded-rank matrices with orthogonally invariant constraints. The "space-decoupling" is reflected in several ways. We show that the tangent cone of coupled constraints is the intersection of tangent cones of each constraint. Moreover, we decouple the intertwined bounded-rank and orthogonally invariant constraints into two spaces, leading to optimization on a smooth manifold. Implementing Riemannian algorithms on this manifold is painless as long as the geometry of additional constraints is known. In addition, we unveil the equivalence between the reformulated problem and the original problem. Numerical experiments on real-world applications -- spherical data fitting, graph similarity measuring, low-rank SDP, model reduction of Markov processes, reinforcement learning, and deep learning -- validate the superiority of the proposed framework.

math.OC↗

arXiv2025

Estimation of Effective Viscosity to Quantify Collisional Behavior in Collisionless Plasma

While dissipation in collisional plasma is defined in terms of viscosity and resistivity, the exact functional form of dissipation i.e., the so-called dissipation function in nearly collisionless plasma is unknown. Nevertheless, previous studies have suggested that there exists viscous-like energy conversion in collisionless plasma with scaling characteristics analogous to collisional plasma, and in particular that the average dissipation is proportional to the square of the rate of strain as in hydrodynamics. In this study, using 2.5D kinetic particle-in-cell (PIC) simulation of collisionless plasma turbulence, we provide an estimate of effective viscosity at each scale, obtained via a scale-filtering approach. We then compare the turbulent dynamics of the PIC simulation with that from MHD and two-fluid simulations in which with the viscosity is equal to the effective viscosity estimate obtained from the PIC simulation. We find that the global behavior in these MHD and two-fluid simulations has a striking similarity with that in its kinetic/PIC counterpart. In addition, we explore the scale dependence of the effective viscosity, and discuss implications of this approach for space plasmas.

physics.plasm-ph↗

arXiv2025

Multilingual Speech Recognition Using Discrete Tokens with a Two-step Training Strategy

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as features for training downstream tasks, the utilization of discrete units has gained increasing attention in recent years owing to its lower storage requirements and broader range of applications. In multilingual ASR tasks, representations at different layers of the model contribute differently to various languages, complicating the unification of discrete unit modeling. In this paper, we propose a two-stage training strategy to improve the discrete token performance of pre-trained models and narrow the gap with continuous representation performance. We validate our method on the XLS-R model following the settings of Interspeech2024 Speech Processing Using Discrete Speech Unit Challenge. Our method demonstrates a significant improvement on the ML-SUPERB dataset, achieving a 44% relative reduction on CER for the XLS-R model. This surpasses the previous baseline set by the WavLM model, which achieves a 26% relative reduction on CER. Furthermore, our method achieves the first place among all the single-system results on the leaderboard.

eess.AS↗

arXiv2025

T$^\text{3}$SVFND: Towards an Evolving Fake News Detector for Emergencies with Test-time Training on Short Video Platforms

The existing methods for fake news videos detection may not be generalized, because there is a distribution shift between short video news of different events, and the performance of such techniques greatly drops if news records are coming from emergencies. We propose a new fake news videos detection framework (T$^3$SVFND) using Test-Time Training (TTT) to alleviate this limitation, enhancing the robustness of fake news videos detection. Specifically, we design a self-supervised auxiliary task based on Mask Language Modeling (MLM) that masks a certain percentage of words in text and predicts these masked words by combining contextual information from different modalities (audio and video). In the test-time training phase, the model adapts to the distribution of test data through auxiliary tasks. Extensive experiments on the public benchmark demonstrate the effectiveness of the proposed model, especially for the detection of emergency news.

cs.CV↗

arXiv2025

Sparrow: Data-Efficient Video-LLM with Text-to-Image Augmentation

Recent years have seen the success of Multimodal Large Language Models (MLLMs) in the domain of vision understanding. The success of these models can largely be attributed to the dominant scaling law, which states that larger parameter sizes and data volumes contribute to better performance. Notably, data scaling has been primarily driven by automatic data pipelines, which focus on the self-instruction of LLMs. The paradigm has been taken for granted for quite some time, but the study of the effectiveness of scaling with these data has been neglected for a long time. In this context, this work revisits scaling with synthetic data and focuses on developing video-LLMs from a data-centric perspective. Our primary study approach involves fine-tuning pre-trained image-LLMs with video data and examining learning efficiency through data scaling. Results from our preliminary experiments reveal a low learning efficiency phenomenon when simply scaling up video data samples, which, through our probing, can be ascribed to a lack of instruction diversity. Aiming at this issue, we propose a data augmentation method called Sparrow, which synthesizes video-like samples from pure text instruction data. Mixing these synthetic samples with the video data enables a more efficient training scheme. Through comprehensive experiments, we demonstrate that our proposed method achieves performance comparable to or even superior to that of baselines trained with significantly more samples. Meanwhile, we find that incorporating these synthetic samples can enhance the performance of long video understanding without requiring training on long video data. The code and data examples are available at https://github.com/VITA-MLLM/Sparrow.

cs.CV↗

arXiv2025

NTIRE 2025 Image Shadow Removal Challenge Report

This work examines the findings of the NTIRE 2025 Shadow Removal Challenge. A total of 306 participants have registered, with 17 teams successfully submitting their solutions during the final evaluation phase. Following the last two editions, this challenge had two evaluation tracks: one focusing on reconstruction fidelity and the other on visual perception through a user study. Both tracks were evaluated with images from the WSRD+ dataset, simulating interactions between self- and cast-shadows with a large number of diverse objects, textures, and materials.

cs.CV↗