arXiv subjects

Guang Yang

Publications and source records attributed to Guang Yang.

At least 109 records · Page 6Linked to original sources

arXiv2026

Multimodal OCR: Parse Anything from Documents

We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped pixels, our method, termed dots.mocr, treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets, enabling systems to parse documents while preserving semantic relationships across elements. It offers several advantages: (1) it reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction; (2) it supports end-to-end training over heterogeneous document elements, allowing models to exploit semantic relations between textual and visual components; and (3) it converts previously discarded graphics into reusable code-level supervision, unlocking multimodal supervision embedded in existing documents. To make this paradigm practical at scale, we build a comprehensive data engine from PDFs, rendered webpages, and native SVG assets, and train a compact 3B-parameter model through staged pretraining and supervised fine-tuning. We evaluate dots.mocr from two perspectives: document parsing and structured graphics parsing. On document parsing benchmarks, it ranks second only to Gemini 3 Pro on our OCR Arena Elo leaderboard, surpasses existing open-source document parsing systems, and sets a new state of the art of 83.9 on olmOCR Bench. On structured graphics parsing, our model achieves higher reconstruction quality than Gemini 3 Pro across image-to-SVG benchmarks, demonstrating strong performance on charts, UI layouts, scientific figures, and chemical diagrams. These results show a scalable path toward building large-scale image-to-code corpora for multimodal pretraining. Code and models are publicly available at https://github.com/rednote-hilab/dots.mocr.

cs.CV↗

arXiv2026

Tuning Cu/Diamond Interfacial Thermal Conductance via Nitrogen-Termination Engineering

Cu-diamond composites are recognized as promising high-thermal-conductivity candidates for electronic cooling, offering tunable properties and competitive cost. However, their performance is significantly limited by the poor Cu/diamond interfacial thermal conductance (ITC). Here, we propose a nitrogen-termination strategy to tune the ITC of Cu/diamond interfaces and unravel atomistic mechanisms by which nitride interlayers tailor phonon transport. Based on the MACE machine-learning interatomic potential (MLIP) framework, we fine-tune the pre-trained MACE-MPA-0 foundation model by incorporating customized C-N-Cu training datasets. Through MLIP-driven lattice dynamics simulations, we demonstrate that an atomically flat N-termination on diamond enhances the ITC by 21% compared to the bare Cu/diamond interface. Mode-resolved phonon spectroscopy reveals that the LA phonons with frequency above 4 THz and wavevectors near Γ-X and Γ-U directions are selectively modulated by N-termination engineering. Analyses of local vibrational states and interfacial bonding further indicate that the N-termination on diamond tunes the interfacial heat conduction via surficial mass modification and bonding regulation, as evidenced by variations in LDOS overlap and COHP spectra. These findings open venues for tuning heat transfer across Cu/diamond interfaces via non-metallic modification, which avoids the graphitization issues associated with metallic coatings, and provide novel guidelines for upgrading the phonon-mediated heat transfer in Cu-diamond composites.

physics.comp-ph↗

arXiv2026

CT-Conditioned Diffusion Prior with Physics-Constrained Sampling for PET Super-Resolution

PET super-resolution is highly under-constrained because paired multi-resolution scans from the same subject are rarely available, and effective resolution is determined by scanner-specific physics (e.g., PSF, detector geometry, and acquisition settings). This limits supervised end-to-end training and makes purely image-domain generative restoration prone to hallucinated structures when anatomical and physical constraints are weak. We formulate PET super-resolution as posterior inference under heterogeneous system configurations and propose a CT-conditioned diffusion framework with physics-constrained sampling. During training, a conditional diffusion prior is learned from high-quality PET/CT pairs using cross-attention for anatomical guidance, without requiring paired LR--HR PET data. During inference, measurement consistency is enforced through a scanner-aware forward model with explicit PSF effects and gradient-based data-consistency refinement. Under both standard and OOD settings, the proposed method consistently improves experimental metrics and lesion-level clinical relevance indicators over strong baselines, while reducing hallucination artifacts and improving structural fidelity.

cs.CV↗

arXiv2026

Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs

Partial differential equations (PDEs) are widely used to model complex physical systems, but solving them efficiently remains a significant challenge. Recently, Transformers have emerged as the preferred architecture for PDEs due to their ability to capture intricate dependencies. However, they struggle with representing continuous dynamics and long-range interactions. To overcome these limitations, we introduce the Mamba Neural Operator (MNO), a novel framework that enhances neural operator-based techniques for solving PDEs. MNO establishes a formal theoretical connection between structured state-space models (SSMs) and neural operators, offering a unified structure that can adapt to diverse architectures, including Transformer-based models. By leveraging the structured design of SSMs, MNO captures long-range dependencies and continuous dynamics more effectively than traditional Transformers. Through extensive analysis, we show that MNO significantly boosts the expressive power and accuracy of neural operators, making it not just a complement but a superior framework for PDE-related tasks, bridging the gap between efficient representation and accurate solution approximation. Our code is available on https://github.com/Math-ML-X/Mamba-Neural-Operator

cs.LG↗

arXiv2026

Multi-Agent Reinforcement Learning with Communication-Constrained Priors

Communication is one of the effective means to improve the learning of cooperative policy in multi-agent systems. However, in most real-world scenarios, lossy communication is a prevalent issue. Existing multi-agent reinforcement learning with communication, due to their limited scalability and robustness, struggles to apply to complex and dynamic real-world environments. To address these challenges, we propose a generalized communication-constrained model to uniformly characterize communication conditions across different scenarios. Based on this, we utilize it as a learning prior to distinguish between lossy and lossless messages for specific scenarios. Additionally, we decouple the impact of lossy and lossless messages on distributed decision-making, drawing on a dual mutual information estimatior, and introduce a communication-constrained multi-agent reinforcement learning framework, quantifying the impact of communication messages into the global reward. Finally, we validate the effectiveness of our approach across several communication-constrained benchmarks.

cs.AI↗

arXiv2026

Neutrino Oscillation Prospects with a Dual-Baseline Beam from BNL to SNOLAB and SURF

The Electron-Ion Collider (EIC) is a next-generation accelerator primarily designed to study the internal structure of nucleons through high-precision electron-hadron collisions. In this work, we explore the feasibility of employing a 1 MW fraction of the EIC proton beam to generate a high-intensity GeV-scale neutrino beam for long-baseline oscillation studies. We have simulated proton-target interactions and optimize the resulting neutrino fluxes for water-based liquid scintillator (WbLS) detectors located at distinct baselines of 900 km and 2900 km. Oscillation analyses performed with GLoBES show that extended baselines allow access to multiple oscillation maxima, significantly enhancing sensitivity to leptonic CP violation. The study also examines the interplay between matter effects and the intrinsic CP violating phase in shaping observable asymmetries. We note that simplified systematics and no backgrounds are used in this analysis to establish the baseline physics potential. These results suggest that the EIC proton beam could provide a novel and complementary source for precision neutrino physics, extending the scientific reach of the EIC program.

hep-ph↗

arXiv2026

ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection

Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution encoder features into the decoder. However, these skip pathways also propagate low-level textures, background clutter, and acquisition noise, allowing irrelevant information to bypass deeper semantic filtering -- an issue that is particularly detrimental in low-contrast clinical imaging. Although attention gates have been introduced to address this limitation, they typically produce dense sigmoid masks that softly reweight features rather than explicitly removing irrelevant activations. We propose ProSMA-UNet (Proximal-Sparse Multi-Scale Attention U-Net), which reformulates skip gating as a decoder-conditioned sparse feature selection problem. ProSMA constructs a multi-scale compatibility field using lightweight depthwise dilated convolutions to capture relevance across local and contextual scales, then enforces explicit sparsity via an $\ell_1$ proximal operator with learnable per-channel thresholds, yielding a closed-form soft-thresholding gate that can remove noisy responses. To further suppress semantically irrelevant channels, ProSMA incorporates decoder-conditioned channel gating driven by global decoder context. Extensive experiments on challenging 2D and 3D benchmarks demonstrate state-of-the-art performance, with particularly large gains ($\approx20$\%) on difficult 3D segmentation tasks. Project page: https://math-ml-x.github.io/ProSMA-UNet/

cs.CV↗

arXiv2026

3D Wavelet-Based Structural Priors for Controlled Diffusion in Whole-Body Low-Dose PET Denoising

Low-dose Positron Emission Tomography (PET) imaging reduces patient radiation exposure but suffers from increased noise that degrades image quality and diagnostic reliability. Although diffusion models have demonstrated strong denoising capability, their stochastic nature makes it challenging to enforce anatomically consistent structures, particularly in low signal-to-noise regimes and volumetric whole-body imaging. We propose Wavelet-Conditioned ControlNet (WCC-Net), a fully 3D diffusion-based framework that introduces explicit frequency-domain structural priors via wavelet representations to guide volumetric PET denoising. By injecting wavelet-based structural guidance into a frozen pretrained diffusion backbone through a lightweight control branch, WCC-Net decouples anatomical structure from noise while preserving generative expressiveness and 3D structural continuity. Extensive experiments demonstrate that WCC-Net consistently outperforms CNN-, GAN-, and diffusion-based baselines. On the internal 1/20-dose test set, WCC-Net improves PSNR by +1.21 dB and SSIM by +0.008 over a strong diffusion baseline, while reducing structural distortion (GMSD) and intensity error (NMAE). Moreover, WCC-Net generalizes robustly to unseen dose levels (1/50 and 1/4), achieving superior quantitative performance and improved volumetric anatomical consistency.

cs.CV↗

arXiv2026

Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation

Radiology report generation is critical for efficiency but current models lack the structured reasoning of experts, hindering clinical trust and explainability by failing to link visual findings to precise anatomical locations. This paper introduces BoxMed-RL, a groundbreaking unified training framework for generating spatially verifiable and explainable radiology reports. Built on a large vision-language model, BoxMed-RL revolutionizes report generation through two integrated phases: (1) In the Pretraining Phase, we refine the model via medical concept learning, using Chain-of-Thought supervision to internalize the radiologist-like workflow, followed by spatially verifiable reinforcement, which applies reinforcement learning to align medical findings with bounding boxes. (2) In the Downstream Adapter Phase, we freeze the pretrained weights and train a downstream adapter to ensure fluent and clinically credible reports. This framework precisely mimics radiologists' workflow, compelling the model to connect high-level medical concepts with definitive anatomical evidence. Extensive experiments on public datasets demonstrate that BoxMed-RL achieves an average 7% improvement in both METEOR and ROUGE-L metrics compared to state-of-the-art methods. An average 5% improvement in large language model-based metrics further underscores BoxMed-RL's robustness in generating high-quality radiology reports.

cs.AI↗

arXiv2026

AGNBoost: A Machine Learning Approach to AGN Identification with JWST/NIRCam+MIRI Colors and Photometry

We present AGNBoost, a machine learning framework utilizing XGBoostLSS to identify AGN and estimate redshifts from JWST NIRCam and MIRI photometry. AGNBoost constructs 66 input features from 7 NIRCam and 4 MIRI bands to predict the fraction of mid-IR $3$--$30\,μ$m emission attributable to an AGN power law ($\text{frac}_{\text{AGN}}$) and photometric redshift. Each model is trained on $10^6$ simulated galaxies from CIGALE. Models are tested on mock CIGALE galaxies, an independent set of empirically-derived templates, and 748 observations from the JWST MIRI EGS Galaxy and AGN (MEGA) survey. On idealized noise-free mock CIGALE galaxies, AGNBoost achieves $15\%$ outlier fractions of $1.63\%$ ($\text{frac}_{\text{AGN}}$) and $0.15\%$ (redshift), with $σ_{\text{RMSE}} = 0.045$ for $\text{frac}_{\text{AGN}}$ and $σ_{\text{NMAD}} = 0.004$ for redshift. When realistic photometric uncertainties are introduced, performance remains robust with median predictions on the 1:1 relation, though outlier fractions increase to $4.38\%$ and $3.35\%$, respectively. On the independent template set, AGNBoost identifies $92.6\%$ of AGN candidates with $\text{frac}_{\text{AGN}} > 0.3$ and $100\%$ with $\text{frac}_{\text{AGN}} > 0.5$, demonstrating generalization beyond the training distribution. On MEGA galaxies with spectroscopic redshifts, AGNBoost achieves $σ_{\text{NMAD}} = 0.056$ and $19.79\%$ outliers. AGNBoost $\text{frac}_{\text{AGN}}$ estimates broadly agree with CIGALE fitting ($σ_{\text{RMSE}} = 0.178$, $11.96\%$ outliers). The flexible framework allows straightforward incorporation of additional photometric bands and re-training for other variables. AGNBoost's computational efficiency makes it well-suited for wide-sky surveys requiring rapid AGN identification and redshift estimation.

astro-ph.GA↗

arXiv2026

MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising

Low-dose Positron Emission Tomography (PET) reduces radiation exposure but suffers from severe noise and quantitative degradation. Diffusion-based denoising models achieve strong final reconstructions, yet their reverse trajectories are typically unconstrained and not aligned with the progressive nature of PET dose formation. We propose MAP-Diff, a multi-anchor guided diffusion framework for progressive 3D whole-body PET denoising. MAP-Diff introduces clinically observed intermediate-dose scans as trajectory anchors and enforces timestep-dependent supervision to regularize the reverse process toward dose-aligned intermediate states. Anchor timesteps are calibrated via degradation matching between simulated diffusion corruption and real multi-dose PET pairs, and a timestep-weighted anchor loss stabilizes stage-wise learning. At inference, the model requires only ultra-low-dose input while enabling progressive, dose-consistent intermediate restoration. Experiments on internal (Siemens Biograph Vision Quadra) and cross-scanner (United Imaging uEXPLORER) datasets show consistent improvements over strong CNN-, Transformer-, GAN-, and diffusion-based baselines. On the internal dataset, MAP-Diff improves PSNR from 42.48 dB to 43.71 dB (+1.23 dB), increases SSIM to 0.986, and reduces NMAE from 0.115 to 0.103 (-0.012) compared to 3D DDPM. Performance gains generalize across scanners, achieving 34.42 dB PSNR and 0.141 NMAE on the external cohort, outperforming all competing methods.

cs.CV↗

arXiv2026

Constraining Neutrino--Nucleon Form Factors with Charged-Current Scattering at the Electron-Ion Collider

Next-generation neutrino oscillation experiments such as DUNE require percent-level knowledge of neutrino--nucleon interaction cross sections. The nucleon axial form factor $F_A(Q^2)$, parameterized by the axial mass $\MA$, is the dominant source of uncertainty in the quasi-elastic channel, and the parity-violating structure function $xF_3$ is poorly constrained on free nucleons. We propose using charged-current (CC) electron--proton scattering at the Electron-Ion Collider (EIC) to address both problems simultaneously. The measurement exploits three key features of the EIC: (1)~helicity-selective electron bunches provide \emph{in situ} electromagnetic background rejection; (2)~a longitudinally polarized proton target enables extraction of $F_A(Q^2)$ through the target-spin asymmetry $A_{UL}$; and (3)~the $y$-distribution leverage in CC deep inelastic scattering separates $F_2$ and $xF_3$ on a \emph{free proton}, without nuclear corrections. Using a Fisher-information analysis at $\sqrt{s} = 141\GeV$ with $500\fb^{-1}$ of integrated luminosity, we project the Cramér--Rao statistical floor of $δ\MA \approx 0.03\GeV$ (3\%). Incorporating first-order realistic detector effects: ZDC acceptance, $Q^2$ smearing (5\%), and background noise from helicity subtraction, the projected sensitivity is severely background-limited due to the small signal-to-background ratio ($S/B \approx 3 \times 10^{-4}$) in the elastic channel. Achieving competitive sensitivity ($δ\MA \approx 0.14\GeV$) would require $\sim\!10^{-7}$ background suppression, three orders of magnitude beyond current projections. The CC DIS $y$-distribution provides sub-percent extraction of $xF_3^{\Wminus}$ over $0.05 < x < 0.5$, representing the most robust electroweak measurement in the near term.

hep-ph↗

arXiv2026

A Morphology Catalog of Galaxies in CEERS: Evolution in the Size and Color Gradients of Galaxies Since Cosmic Dawn

We present measurements of morphological parameters from fitting 53,885 galaxies detected to a magnitude limit of F356W$< 28.5$ in the CEERS NIRCam imaging with galfit in six broadband filters: F115W, F150W, F200W, F277W, F356W, and F444W. We provide a public catalog of Sérsic index, effective semi-major axis, axis ratio, integrated magnitude, and position angle for these galaxies in each of the filters. Uncertainties in the measured parameters are estimated from simulated galaxies that have similar noise and background properties as the observed galaxies. We compare our measurements with those in the CANDELS/EGS field measured with HST/WFC3 and find that the sizes agree to within 0.09 dex and the Sérsic indices agree to within 0.13 dex. We further present the evolution in the size-mass relation, and find that the evolution to $z\sim9$ is consistent with previous results derived at lower redshift. Finally, we look at the color gradients of galaxies at $1 2.5$), the color gradients are nearly flat with no dependence on mass, indicating that the stellar populations are more uniform throughout. The structural measurements presented are accurate to $20\%$ or better for most galaxies with F356W $<27.0$ mag and will enable further studies of galaxy morphology to $z\sim10$.

astro-ph.GA↗

arXiv2026

DAMSA Experiment Conceptual Design White Paper

DAMSA (DArk Messenger Searches at an Accelerator) is a novel short-baseline accelerator experiment aimed at probing short-lived physics processes, including searches for evidence of a dark sector of particle physics and well-motivated Standard Model signals. Motivated by open questions in neutrino physics and the absence of conclusive evidence for conventional weakly interacting massive particles, DAMSA targets MeV-to-sub-GeV dark-sector messengers with feeble couplings that can be produced in abundance at the PIP-II LINAC. By employing an ultra-short baseline of order one meter, DAMSA is uniquely positioned to overcome the beam-dump "ceiling" that limits sensitivity to promptly decaying particles in longer-baseline experiments. The conceptual design emphasizes a beam-dump production scheme combined with a compact detector optimized for rare decays while mitigating intense neutron-induced backgrounds inherent to high-power proton beams. To validate the experimental strategy and detector technologies, the Little DAMSA Path-Finder (LDPF) proof-of-concept experiment is proposed, focusing on axion-like particles decaying to two photons and operating with 300 MeV electron beams at FAST. Successful realization of LDPF will establish the feasibility of the DAMSA approach, enabling a broad and powerful program to explore short-lived new physics and precision Standard Model processes in a previously inaccessible regime. This conceptual design document outlines the technical details of DAMSA's physics goals, the beam facility proposals, key experimental challenges and how to overcome them, and the proposed experimental staging campaigns.

hep-ex↗

arXiv2026

Extensible universal photonic quantum computing with nonlinearity

Universal quantum computing requires an architecture that supports both linear circuits and, crucially, strong nonlinear resources. For quantum photonic systems, integrating such nonlinearities with scalable linear circuitry has been a major bottleneck, leaving most optical experiments without nonlinear operations and, consequently, incapable of achieving universality. Here, we report an extensible photonic computer that supports a universal gate set by seamlessly combining fully programmable, scalable linear optical networks with integrated nonlinear modules. This platform enables a broad range of quantum computing and simulation tasks. We demonstrate the quasi-deterministic generation of optical Gottesman-Kitaev-Preskill states, which are essential resources for bosonic error correction, yet had previously been realized only probabilistically. Furthermore, we simulate complex many-body quantum dynamics, exemplified by the Bose-Hubbard model. Such quantum simulation tasks have long been considered beyond the reach of photonic hardware limited to linear operations. These capabilities, enabled by our extensible architecture, establish a viable route towards photonic quantum simulation and fault-tolerant quantum computing.

quant-ph↗

arXiv2026

Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation

Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design, yet remain vulnerable to backdoor attacks where adversaries inject malicious triggers during training to induce vulnerable hardware designs. Unlike patchable software vulnerabilities, hardware trojans become irreversible once fabricated, making remediation extremely costly or impossible. Existing active defenses require access to training data, impractical for third-party LLM users, while passive defenses struggle against semantically stealthy triggers that naturally blend into design specifications. In this paper, we hypothesize that under the requirements of both effectiveness and stealthiness, attackers are strongly biased toward embedding triggers in non-functional requirements (e.g., style modifiers, quality descriptors) rather than functional specifications that determine hardware behavior. Exploiting this insight, we propose Semantic Consensus Decoding (SCD), an inference-time passive defense with two key components: (1) functional requirement extraction that identifies essential requirements from user specifications, and (2) consensus decoding that adaptively fuses output distributions based on full user specifications and extracted functional requirements. When these distributions diverge significantly, SCD automatically suppresses suspicious components. Extensive experiments with three representative backdoor attacks demonstrate that SCD reduces average attack success rate from 89% to under 3% with negligible impact on generation quality.

cs.SE↗

arXiv2026

Extended Self-similarity in Multimode Optical Fiber Speckles

Extended Self-Similarity (ESS) is a widely used tool for uncovering universal power-law scaling in systems dominated by nonlinear interactions. This work demonstrates that ESS scaling can also emerge in a system governed by purely linear physics: the propagation of coherent light in a multimode fiber. The system produces complex speckle patterns arising solely from deterministic linear mode interference. We analyze the intensity structure functions of these speckles and observe a robust extended scaling range. The measured scaling exponents align with the classical Kolmogorov scaling exponents. This finding establishes that the statistical signatures captured by ESS are not exclusive to nonlinear systems, revealing a broader applicability of this scaling framework to complex linear systems.

physics.optics↗

arXiv2026

StealthMark: Harmless and Stealthy Ownership Verification for Medical Segmentation via Uncertainty-Guided Backdoors

Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded by privacy and ethical concerns associated with sensitive patient information. As a result, well-trained medical segmentation models on private datasets constitute valuable intellectual property requiring robust protection mechanisms. Existing model protection techniques primarily focus on classification and generative tasks, while segmentation models-crucial to medical image analysis-remain largely underexplored. In this paper, we propose a novel, stealthy, and harmless method, StealthMark, for verifying the ownership of medical segmentation models under black-box conditions. Our approach subtly modulates model uncertainty without altering the final segmentation outputs, thereby preserving the model's performance. To enable ownership verification, we incorporate model-agnostic explanation methods, e.g. LIME, to extract feature attributions from the model outputs. Under specific triggering conditions, these explanations reveal a distinct and verifiable watermark. We further design the watermark as a QR code to facilitate robust and recognizable ownership claims. We conducted extensive experiments across four medical imaging datasets and five mainstream segmentation models. The results demonstrate the effectiveness, stealthiness, and harmlessness of our method on the original model's segmentation performance. For example, when applied to the SAM model, StealthMark consistently achieved ASR above 95% across various datasets while maintaining less than a 1% drop in Dice and AUC scores, significantly outperforming backdoor-based watermarking methods and highlighting its strong potential for practical deployment. Our implementation code is made available at: https://github.com/Qinkaiyu/StealthMark.

cs.CV↗