arXiv subjects

Yan Yang

Publications and source records attributed to Yan Yang.

At least 37 records · Page 2Linked to original sources

arXiv2026

CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation

Chest X-ray (CXR) plays a pivotal role in clinical diagnosis, and a variety of task-specific and foundation models have been developed for automatic CXR interpretation. However, these models often struggle to adapt to new diagnostic tasks and complex reasoning scenarios. Recently, LLM-based agent models have emerged as a promising paradigm for CXR analysis, enhancing model's capability through tool coordination, multi-step reasoning, and team collaboration, etc. However, existing agents often rely on a single diagnostic pipeline and lack mechanisms for assessing tools' reliability, limiting their adaptability and credibility. To this end, we propose CXRAgent, a director-orchestrated, multi-stage agent for CXR interpretation, where a central director coordinates the following stages: (1) Tool Invocation: The agent strategically orchestrates a set of CXR-analysis tools, with outputs normalized and verified by the Evidence-driven Validator (EDV), which grounds diagnostic outputs with visual evidence to support reliable downstream diagnosis; (2) Diagnostic Planning: Guided by task requirements and intermediate findings, the agent formulates a targeted diagnostic plan. It then assembles an expert team accordingly, defining member roles and coordinating their interactions to enable adaptive and collaborative reasoning; (3) Collaborative Decision-making: The agent integrates insights from the expert team with accumulated contextual memories, synthesizing them into an evidence-backed diagnostic conclusion. Experiments on various CXR interpretation tasks show that CXRAgent delivers strong performance, providing visual evidence and generalizes well to clinical tasks of different complexity. Code and data are valuable at this \href{https://github.com/laojiahuo2003/CXRAgent/}{link}.

cs.AI↗

arXiv2026

Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification

Unsupervised visible-infrared person re-identification (USVI-ReID) is challenging due to the large modality gap and the lack of cross-modal identity annotations. Progressive association paradigms have been proposed to gradually bridge the gap, but they suffer from two critical bottlenecks: reliance on ambiguous global representations and unchecked propagation of pseudo-label noise in an open-loop manner. To address these issues, we propose Structural-Semantic Reciprocal Learning (SSRL), a framework that transforms open-loop association into a self-correcting closed-loop system. Structurally, we introduce Fine-grained Structural Decoupling (FSD) to extract discriminative body-part primitives as reliable spatial anchors, complementing ambiguous holistic silhouettes with spatially consistent structural details. Semantically, we design a Closed-loop Semantic Calibration (CSC) mechanism that reconstructs shared semantic prototypes at each epoch and feeds them back into the training loop, effectively filtering pseudo-label noise before the next clustering cycle. Through the reciprocal interaction between structural and semantic learning, SSRL achieves robust cross-modal representation. Extensive experiments demonstrate the competitive performance of SSRL against state-of-the-art USVI-ReID methods on both SYSU-MM01 and RegDB, notably surpassing several supervised counterparts on RegDB.

cs.CV↗

arXiv2026

Loss Landscape Diagnosis for Gradient-Based Gray-Scott System Inversion: Disentangling the Roles of PINN Components

Gradient-based inversion of reaction-diffusion systems is typically approached via surrogate models or physics-informed neural networks (PINNs), while the most direct route, backpropagation through the PDE's structure itself, has largely been avoided. We pursue this direct route as a diagnostic probe, backpropagating a steady-state loss through unrolled Gray-Scott simulation to recover its parameters, with no surrogate or neural-network augmentation. Optimization fails to converge, and plotting the landscape directly locates the failure in its geometry -- flat plateaus with no gradient signal, bounded by sharp cliffs that align with bifurcation boundaries -- a structure that recurs across loss functions and is inherited however the gradients are routed to parameters. Reading this minimal setup as an ablation of PINN, we disentangle each component's role: with the neural network fixed, the residual loss is quadratic in the PDE parameters and yields a smooth landscape, so it alone already avoids the pathology, by implicitly encoding the full PDE dynamics across all initial conditions. The neural network, for its part, cannot repair an ill-posed parameter subspace, and so serves only to complete the observed data -- a division of labor not previously made explicit. These findings carry concrete design implications for PINN-type methods and a broader heuristic on when added dimensions actually help.

cs.LG↗

arXiv2026

Inertial-Range Energy Transfer Free from Isotropic Assumption in Turbulent Space Plasma

The idea of an energy cascade in the inertial range is often invoked in turbulent space plasmas to estimate the energy dissipation rate. Laws governing the behavior of third-order structure functions in the inertial range, so-called third-order laws, are among the few rigorous theoretical results quantifying cross-scale energy transfer. The widely used third-order-law derived rate assumes isotropy, which fundamentally conflicts with the anisotropic nature of space plasmas. Elementary questions persist regarding how such anisotropic energy cascades can be quantified using multi-spacecraft constellations. As the heliospheric community increasingly progresses towards multi-spacecraft, multi-scale constellations, such as Plasma Observatory and HelioSwarm, we revisit these crucial issues pertinent to accurately measuring the inertial-range energy transfer. Here we make a systematic comparison between two methods: direction-averaging (DA) and lag polyhedral derivative ensemble (LPDE) to determine the full three-dimensional (3D) dependence of cross-scale energy transfer. We find that DA exhibits both polar and azimuthal dependence, but is insensitive to spacecraft configuration. By contrast, LPDE is strongly affected by spacecraft separation and tetrahedral shape, while being comparatively insensitive to the sampling trajectory. Our findings have direct implications for current and future multi-spacecraft missions. Both DA and LPDE will provide crucial information on the nature of turbulence in space and astrophysics.

physics.plasm-ph↗

arXiv2026

WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild

Using multimodal foundation models to analyze table images is a high-value yet challenging application in consumer and enterprise scenarios. Despite its importance, current evaluations rely largely on structured-text tables or clean rendered images, leaving the visual complexity of in-the-wild table images underexplored. Such images feature varied layouts and diverse domains that demand sophisticated structural perception and numerical reasoning. To bridge this gap, we introduce WildTableBench, the first question-answering benchmark for naturally occurring table images from real-world settings. WildTableBench comprises 402 high-information-density table images collected from online forums and websites across diverse domains, together with 928 manually annotated and verified questions spanning 17 subtypes across five categories. We evaluate 21 frontier proprietary and open-source multimodal foundation models on this benchmark. Only one model exceeds 50% accuracy, while all remaining models range from 4.1% to 49.9%. We further conduct diagnostic analyses to characterize model failures and reveal persistent weaknesses in structural perception and reasoning. These results and analyses provide useful insights into current model capabilities and establish WildTableBench as a valuable diagnostic benchmark for table image understanding. Dataset: https://huggingface.co/datasets/jzhuang/WildTableBench Code: https://github.com/hjzhe/WildTableBench Leaderboard: https://hjzhe.github.io/WildTableBench

cs.CV↗

arXiv2026

Optimization over the intersection of manifolds

Optimization over the intersection of two manifolds arises in a broad range of applications, but is hindered by the coupled geometry of the feasible region. In this paper, we prove that the regularities -- clean intersection and intrinsic transversality -- are equivalent, which yields a tractable projection onto the tangent space of the intersection. Therefore, we propose a geometric method that employs a retraction on only one manifold and updates the iterate along two orthogonal directions. Specifically, the iterates stay on one manifold, and the two directions are responsible for asymptotically approaching the other manifold and decreasing the objective function, respectively. Under intrinsic transversality, we derive the convergence rate for both the feasibility and optimality measures, and show that every accumulation point is first-order stationary. Numerical experiments on problems stemming from sparse and low-rank optimization, including fitting spherical data, approximating hyperbolic embeddings on real data, and computing compressed modes, demonstrate the effectiveness of the proposed method.

math.OC↗

arXiv2026

Benchmarking and Improving GUI Agents in High-Dynamic Environments

Recent advancements in Graphical User Interface (GUI) agents have predominantly focused on training paradigms like supervised fine-tuning (SFT) and reinforcement learning (RL). However, the challenge of high-dynamic GUI environments remains largely underexplored. Existing agents typically rely on a single screenshot after each action for decision-making, leading to a partially observable (or even unobservable) Markov decision process, where the key GUI state including important information for actions is often inadequately captured. To systematically explore this challenge, we introduce DynamicGUIBench, a comprehensive online GUI benchmark spanning ten applications and diverse interaction scenarios characterized by important interface changes between actions. Furthermore, we present DynamicUI, an agent designed for dynamic interfaces, which takes screen-recording videos of the interaction process as input and consists of three components: a dynamic perceiver, a refinement strategy, and a reflection. Specifically, the dynamic perceiver clusters frames of the GUI video, generates captions for the centroids, and iteratively selects the most informative frames as the salient dynamic context. Considering that there may be inconsistencies and noise between the selected frames and the textual context of the agent, the refinement strategy employs an action-conditioned filtering to refine thoughts to mitigate thought-action inconsistency and redundancy. Based on the refined agent trajectories, the reflection module provides effective and accurate guidance for further actions. Experiments on DynamicGUIBench demonstrate that DynamicUI significantly improves the performance in dynamic GUI environments, while maintaining competitive performance on other public benchmarks.

cs.CV↗

arXiv2026

CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding

Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object constancy. In addition, existing approaches typically rely on expensive human annotations or large-scale chain-of-thought (CoT) data generation. We propose Compositional Grounded Contrast (abbr. CGC), a low-cost full framework for boosting fine-grained multi-image understanding of MLLMs. Built on existing single-image grounding annotations, CGC constructs compositional multi-image training instances through Inter-Image Contrast and Intra-Image Contrast, which introduce semantically decoupled distractor contexts for cross-image discrimination and correlated cross-view samples for object constancy, respectively. CGC further introduces a Rule-Based Spatial Reward within the GRPO framework to improve source-image attribution, spatial alignment, and structured output validity under a Think-before-Grounding paradigm. Experiments show that CGC achieves state-of-the-art results on fine-grained multi-image benchmarks, including MIG-Bench and VLM2-Bench. The learned multi-image understanding capability also transfers to broader multimodal understanding and reasoning tasks, yielding consistent gains over the Qwen3-VL-8B base model on MathVista (+2.90), MuirBench (+2.88), MMStar (+1.93), MMMU (+1.77), and BLINK (+1.69).

cs.CV↗

arXiv2026

On derivatives and higher-order derivatives of chromatic polynomials

Let $ G $ be a graph of order $ n $ with maximum degree $Δ$, and let $P(G,x)$ denote its chromatic polynomial. We investigate several properties of $P(G,x)$ related to its derivatives and higher-order derivatives. First, we study the monotonicity of $P(G,x)/x^n$. Dong proved that $(x-1)^nP(G,x)\geq x^nP(G,x-1)$ for all real $x\geq n$. In particular, taking $x=n$ establishes the Bartels-Welsh ``shameful conjecture" that $P(G,n)/P(G,n-1)>e$. Fadnavis later showed that the same inequality holds for all real $x\geq 36Δ^{3/2}$. We improve this bound by proving that it also holds for all real $x\geq 10Δ^{3/2}$. We then consider a conjecture of Dong, Ge, Gong, Ning, Ouyang, and Tay asserting that $ \frac{d^k}{dx^k} \bigl( \ln[(-1)^n P(G, x)] \bigr) < 0 $ for all $ k \geq 2 $ and $ x \in (-\infty, 0) $. We establish this conjecture for all $ k \geq 2 $ and $ x\leq -3.01Δk $.

math.CO↗

arXiv2026

Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models

Large vision-language models (VLMs) have demonstrated remarkable capabilities in open-world multimodal understanding, yet their high computational overheads pose great challenges for practical deployment. Some recent works have proposed methods to accelerate VLMs by pruning redundant visual tokens guided by the attention maps of VLM's early layers. Despite the success of these token pruning methods, they still suffer from two major shortcomings: (i) considerable accuracy drop due to insensitive attention signals in early layers, and (ii) limited speedup when generating long responses (e.g., 30 tokens). To address the limitations above, we present TwigVLM -- a simple and general architecture by growing a lightweight module, named twig, upon an early layer of the base VLM. Compared with most existing VLM acceleration methods purely based on visual token pruning, our TwigVLM not only achieves better accuracy retention by employing a twig-guided token pruning (TTP) strategy, but also yields higher generation speed by utilizing a self-speculative decoding (SSD) strategy. Taking LLaVA-1.5-7B as the base VLM, experimental results show that TwigVLM preserves 96% of the original performance after pruning 88.9% of the visual tokens and achieves 154% speedup in generating long responses, delivering significantly better performance in terms of both accuracy and speed over the state-of-the-art VLM acceleration methods. Moreover, we extend TwigVLM to an improved TwigVLM++ variant by introducing a novel multi-head twig architecture with a specialized pruning head. TwigVLM++ improves pruning quality via a two-stage training paradigm combining a distillation learning stage and a pruning-oriented reinforcement learning stage, and further accelerates inference via a tree-based SSD strategy.

cs.CV↗

arXiv2026

GPA: Learning GUI Process Automation from Demonstrations

GUI Process Automation (GPA) is a lightweight but general vision-based Robotic Process Automation (RPA), which enables fast and stable process replay with only a single demo. Addressing the fragility of traditional RPA and the non-deterministic risks of current vision language model-based GUI agents, GPA introduces three core benefits: (1) Robustness via Sequential Monte Carlo-based localization to handle rescaling and detection uncertainty; (2) Deterministic and Reliability safeguarded by readiness calibration; and (3) Privacy through fast, fully local execution. This approach delivers the adaptability, robustness, and security required for enterprise workflows. It can also be used as an MCP/CLI tool by other agents with coding capabilities so that the agent only reasons and orchestrates while GPA handles the GUI execution. We conducted a pilot experiment to compare GPA with Gemini 3 Pro (with CUA tools) and found that GPA achieves higher success rate with 10 times faster execution speed in finishing long-horizon GUI tasks.

cs.CV↗

arXiv2026

Progressive Video Condensation with MLLM Agent for Long-form Video Understanding

Understanding long videos requires extracting query-relevant information from long sequences under tight compute budgets. Existing text-then-LLM pipelines lose fine-grained visual cues, while video-based multimodal large language models (MLLMs) can keep visual details but are too frame-hungry and computationally expensive. In this work, we aim to harness MLLMs for efficient video understanding. We propose ProVCA, a progressive video condensation agent that iteratively locates key video frames at multiple granularities. ProVCA first adopts a segment localization module to identify the video segment relevant to the query, then a snippet selection module to select important snippets based on similarity, and finally a keyframe refinement module to pinpoint specific keyframes in those snippets. By progressively narrowing the scope from coarse segments to fine frames, ProVCA identifies a small set of keyframes for MLLM-based reasoning. ProVCA achieves state-of-the-art zero-shot accuracies of 69.3\% on EgoSchema, 80.5\% on NExT-QA, and 77.7\% on IntentQA, while using fewer frames than previous training-free methods.

cs.CV↗

arXiv2026

SRGS: Super-Resolution 3D Gaussian Splatting

Low-resolution (LR) multi-view capture limits the fidelity of 3D Gaussian Splatting (3DGS). 3DGS super-resolution (SR) is therefore important, yet challenging because it must recover missing high-frequency details while enforcing cross-view geometric consistency. We revisit SRGS, a simple baseline that couples plug-in 2D SR priors with geometry-aware cross-view regularization, and observe that most subsequent advances follow the same paradigm, either strengthening prior injection, refining cross-view constraints, or modulating the objective. However, this shared structure is rarely formalized as a unified objective with explicit modules, limiting principled attribution of improvements and reusable design guidance. In this paper, we formalize SRGS as a unified modular framework that factorizes 3DGS SR into two components, prior injection and cross-view regularization, within a joint objective. This abstraction subsumes a broad family of recent methods as instantiations of the same recipe, enabling analysis beyond single-method innovation. Across five public benchmarks, we consolidate nine representative follow-up methods and trace reported improvements to specific modules and settings. Ablations disentangle the roles of priors and consistency, and stress tests under sparse-view input and challenging capture conditions characterize robustness. Overall, our study consolidates 3DGS SR into a coherent foundation and offers practical guidance for robust, comparable 3DGS SR methods.

cs.CV↗

arXiv2026

On a conjecture concerning the property of chromatic polynomials with negative variables

Let $G$ be a graph of order $n$ and $P(G,x)$ be the chromatic polynomial of $G$. Dong, Ge, Gong, Ning, Ouyang, and Tay (J. Graph Theory 96(2021) 343) conjectured that $\frac{d^k}{dx^k} \bigl( \ln[(-1)^n P(G, x)] \bigr) < 0$ holds for all $k \geq 2$ and $x \in (-\infty, 0)$. We prove this conjecture for all $k \geq 2 $ and $ x\leq -6.66Δk $, in which $Δ$ is the maximum degree of $G$.

math.CO↗

arXiv2026

Polarimeter to Unify the Corona and Heliosphere (PUNCH)

The Polarimeter to Unify the Corona and Heliosphere (PUNCH) mission is a NASA Small Explorer to determine the cross-scale processes that unify the solar corona and heliosphere. PUNCH has two science objectives: (1) understand how coronal structures become the ambient solar wind, and (2) understand the dynamic evolution of transient structures, such as coronal mass ejections, in the young solar wind. To address these objectives, PUNCH uses a constellation of four small spacecraft in Sun-synchronous low Earth orbit, to collect linearly polarized images of the K corona and young solar wind. The four spacecraft each carry one visible-light imager in a 1+3 configuration: a single Narrow Field Imager solar coronagraph captures images of the outer corona at all position angles, and at solar elongations from 1.5 degrees (6 R$_\odot$) to 8 degrees (32 R$_\odot$); and three separate Wide Field Imager heliospheric imagers together capture views of the entire inner solar system, at solar elongations from 3 degrees (12 R$_\odot$) to 45 degrees (180 R$_\odot$) from the Sun. PUNCH images include linear-polarization data, to enable inferring the three-dimensional structure of visible features without stereoscopy. The instruments are matched in wavelength passband, support overlapping instantaneous fields of view, and are operated synchronously, to act as a single ``virtual instrument'' with a 90 degree wide field of view, centered on the Sun. PUNCH launched in March of 2025 and began science operations in June of 2025. PUNCH has an open data policy with no proprietary period, and PUNCH Science Team Meetings are open to all.

astro-ph.SR↗

arXiv2025

A Preliminary Study on GPT-Image Generation Model for Image Restoration

Recent advances in OpenAI's GPT-series multimodal generation models have shown remarkable capabilities in producing visually compelling images. In this work, we investigate its potential impact on the image restoration community. We provide, to the best of our knowledge, the first systematic benchmark across diverse restoration scenarios. Our evaluation shows that, while the restoration results generated by GPT-Image models are often perceptually pleasant, they tend to lack pixel-level structural fidelity compared with ground-truth references. Typical deviations include changes in image geometry, object positions or counts, and even modifications in perspective. Beyond empirical observations, we further demonstrate that outputs from GPT-Image models can act as strong visual priors, offering notable performance improvements for existing restoration networks. Using dehazing, deraining, and low-light enhancement as representative case studies, we show that integrating GPT-generated priors significantly boosts restoration quality. This study not only provides practical insights and a baseline framework for incorporating GPT-based generative priors into restoration pipelines, but also highlights new opportunities for bridging image generation models and restoration tasks. To support future research, we will release GPT-restored results.

cs.CV↗

arXiv2025

Cross-organ all-in-one parallel compressed sensing magnetic resonance imaging

Recent advances in deep learning-based parallel compressed sensing magnetic resonance imaging (p-CSMRI) have significantly improved reconstruction quality. However, current p-CSMRI methods often require training separate deep neural network (DNN) for each organ due to anatomical variations, creating a barrier to developing generalized medical image reconstruction systems. To address this, we propose CAPNet (cross-organ all-in-one deep unfolding p-CSMRI network), a unified framework that implements a p-CSMRI iterative algorithm via three specialized modules: auxiliary variable module, prior module, and data consistency module. Recognizing that p-CSMRI systems often employ varying sampling ratios for different organs, resulting in organ-specific artifact patterns, we introduce an artifact generator, which extracts and integrates artifact features into the data consistency module to enhance the discriminative ability of the overall network. For the prior module, we design an organ structure-prompt generation submodule that leverages structural features extracted from the segment anything model (SAM) to create cross-organ prompts. These prompts are strategically incorporated into the prior module through an organ structure-aware Mamba submodule. Comprehensive evaluations on a cross-organ dataset confirm that CAPNet achieves state-of-the-art reconstruction performance across multiple anatomical structures using a single unified model. Our code will be published at https://github.com/shibaoshun/CAPNet.

eess.IV↗

arXiv2025

Angular dependence of third-order law in anisotropic MHD turbulence

In solar wind turbulence, the energy transfer/dissipation rate is typically estimated using MHD third-order structure functions calculated using spacecraft observations. However, the inherent anisotropy of solar wind turbulence leads to significant variations in structure functions along different observational directions, thereby affecting the accuracy of energy-dissipation rate estimation. An unresolved issue is how to optimise the selection of observation angles under limited directional sampling to improve estimation precision. We conduct a series of MHD turbulence simulations with different mean magnetic field strengths, $ B_0 $. Our analysis of the third-order structure functions reveals that the global energy dissipation rate estimated around a polar angle of $ θ= 60^\circ$ agrees reasonably with the exact one for $ 0 \le B_0/b_{rms} \le 5 $, where $b_{rms}$ denotes the root-mean-square magnetic field fluctuation. The speciality of $60^\circ$ polar angle can be understood by the Mean Value Theorem of Integrals, since the spherical integral of the polar-angle component ($\widetilde{T_θ}$) of the divergence of Yaglom flux is zero, and $\widetilde{T_θ}$ changes sign around 60$^\circ$. Existing theory on the energy flux vector as a function of the polar angle is assessed, and supports the speciality of $60^\circ$ polar angle. The angular dependence of the third-order structure functions is further assessed with virtual spacecraft data analysis. The present results can be applied to measure the turbulent dissipation rates of energy in the solar wind, which are of potential importance to other areas in which turbulence takes place, such as laboratory plasmas and astrophysics.

physics.space-ph↗