arXiv subjects

Shuang Zhao

Publications and source records attributed to Shuang Zhao.

At least 19 recordsLinked to original sources

arXiv2026

Diffusion-Based Material Regularization for Physics-Based Inverse Rendering

Reconstructing physics-based 3D assets -- geometry, materials, and illumination -- from multi-view images is a core problem in computer graphics and vision, and a prerequisite for realistic relighting and editing. Physics-based inverse rendering offers an accurate image-formation model, but is severely underconstrained: without strong priors, illumination is baked into materials, and reconstructions generalize poorly to novel views and lighting. Data-driven diffusion models, in contrast, predict visually plausible materials, yet their predictions rarely satisfy the rendering equation and are not directly usable for physics-based rendering. We bridge these two paradigms rather than replacing either. Our key idea is to treat the predictions of a state-of-the-art diffusion model not as target material values but as a similarity kernel for optimization: we introduce a regularization loss that penalizes deviations in the optimized material over surface regions where the diffusion predictions are near-constant, while leaving the optimization free to match the input images. Built on this regularizer, our end-to-end pipeline jointly reconstructs geometry, materials, and illumination, yielding high-quality assets that drop into standard rendering pipelines and relight faithfully. On the Synthetic4Relight, Stanford-ORB, and DTC-Synthetic datasets, our method significantly outperforms state-of-the-art baselines in both reconstruction accuracy and relighting quality.

cs.CV↗

arXiv2026

Robust Neural Policy Distillation of Long-Horizon FCS-MPC for Flying-Capacitor Three-Level Boost Converters

Long-horizon finite-control-set model predictive control (FCS-MPC) can improve transient regulation and flying-capacitor balancing in flying-capacitor three-level boost converters (FC-TLBCs). However, searching over switching sequences becomes computationally expensive at high switching frequencies. We train a feedforward neural network to imitate an $N$-step FCS-MPC expert computed with beam search. To improve robustness, expert trajectories are generated under randomized input voltage, load resistance, and component parameters, and a disagreement-based DAgger variant is used to relabel on-policy states where the student and expert disagree. In simulation, the learned policy maintains stable voltage regulation and capacitor balancing under nominal conditions, operating-point changes, and perturbations of several physical parameters. We demonstrate the effectiveness of our approach by reducing the computational burden. We also demonstrate transfer to an NPC-type three-level buck converter, where initializing from the FC-TLBC network improves sample efficiency compared with training from scratch.

math.OC↗

arXiv2026

Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting

Ray-tracing-based 3D Gaussian splatting (3DGS) methods overcome the limitations of rasterization -- rigid pinhole camera assumptions, inaccurate shadows, and lack of native reflection or refraction -- but remain slower due to the cost of sorting all intersecting Gaussians along every ray. Moreover, existing ray-tracing methods still rely on rasterization-style approximations such as shadow mapping for relightable scenes, undermining the generality that ray tracing promises. We present a differentiable, sorting-free stochastic formulation for ray-traced 3DGS -- the first framework that uses stochastic ray tracing to both reconstruct and render standard and relightable 3DGS scenes. At its core is an unbiased Monte Carlo estimator for pixel-color gradients that evaluates only a small sampled subset of Gaussians per ray, bypassing the need for sorting. For standard 3DGS, our method matches the reconstruction quality and speed of rasterization-based 3DGS while substantially outperforming sorting-based ray tracing. For relightable 3DGS, the same stochastic estimator drives per-Gaussian shading with fully ray-traced shadow rays, delivering notably higher reconstruction fidelity than prior work.

cs.CV↗

arXiv2026

Giant Magnetocrystalline Anisotropy in Honeycomb Iridate NiIrO3 with Large Coercive Field Exceeding 17 T

The realization of unconventional quantum phases in frustrated and spin-orbit coupled materials remains at the forefront of quantum materials research. Here we report the synthesis and discovery of NiIrO3, the first honeycomb iridate with coupled 3d-5d magnetic sublattices, through a soft topotactic reaction. Structural analysis reveals an ilmenite-type stacking of edge-sharing NiO6 and IrO6 octahedral honeycomb sublattices in a Kitaev geometry. Comprehensive magnetic and electrical transport measurements unveil its long-range ferrimagnetic order below 213 K, which is in sharp contrast to the predominantly antiferromagnetic order in the known honeycomb iridates. Notably, the titled compound displays an exceptionally large magnetocrystalline anisotropy energy of 32.2 meV/f.u. and a giant coercivity with coercive field exceeding 17.3 T below 4.2 K, both ranking among the highest observed in iridates to date. Combined experimental and theoretical investigations indicate that the exceptional anisotropy and coercivity originate from the synergistic effect between strong lattice frustration in the coupled 3d-5d honeycomb lattice network and the robust spin-orbit coupling of the Ir4+ (Jeff = 1/2) state. This work positions NiIrO3 as a promising platform to investigate low-dimensional and frustrated quantum spin systems, and highlights its potential for spintronic applications through the targeted engineering of 3d-5d interactions.

cond-mat.str-el↗

arXiv2026

A Vision-Language Foundation Model for Zero-shot Clinical Collaboration and Automated Concept Discovery in Dermatology

Medical foundation models have shown promise in controlled benchmarks, yet widespread deployment remains hindered by reliance on task-specific fine-tuning. Here, we introduce DermFM-Zero, a dermatology vision-language foundation model trained via masked latent modelling and contrastive learning on over 4 million multimodal data points. We evaluated DermFM-Zero across 20 benchmarks spanning zero-shot diagnosis and multimodal retrieval, achieving state-of-the-art performance without task-specific adaptation. We further evaluated its zero-shot capabilities in three multinational reader studies involving over 1,100 clinicians. In primary care settings, AI assistance enabled general practitioners to nearly double their differential diagnostic accuracy across 98 skin conditions. In specialist settings, the model significantly outperformed board-certified dermatologists in multimodal skin cancer assessment. In collaborative workflows, AI assistance enabled non-experts to surpass unassisted experts while improving management appropriateness. Finally, we show that DermFM-Zero's latent representations are interpretable: sparse autoencoders unsupervisedly disentangle clinically meaningful concepts that outperform predefined-vocabulary approaches and enable targeted suppression of artifact-induced biases, enhancing robustness without retraining. These findings demonstrate that a foundation model can provide effective, safe, and transparent zero-shot clinical decision support.

cs.CV↗

arXiv2025

Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference

Reasoning-focused large language models (LLMs) are rapidly evolving across various domains, yet their capabilities in handling complex legal problems remains underexplored. In this paper, we introduce Unilaw-R1, a large language model tailored for legal reasoning. With a lightweight 7-billion parameter scale, Unilaw-R1 significantly reduces deployment cost while effectively tackling three core challenges in the legal domain: insufficient legal knowledge, unreliable reasoning logic, and weak business generalization. To address these issues, we first construct Unilaw-R1-Data, a high-quality dataset containing 17K distilled and screened chain-of-thought (CoT) samples. Based on this, we adopt a two-stage training strategy combining Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), which significantly boosts the performance on complex legal reasoning tasks and supports interpretable decision-making in legal AI applications. To assess legal reasoning ability, we also introduce Unilaw-R1-Eval, a dedicated benchmark designed to evaluate models across single- and multi-choice legal tasks. Unilaw-R1 demonstrates strong results on authoritative benchmarks, outperforming all models of similar scale and achieving performance on par with the much larger DeepSeek-R1-Distill-Qwen-32B (54.9%). Following domain-specific training, it also showed significant gains on LawBench and LexEval, exceeding Qwen-2.5-7B-Instruct (46.6%) by an average margin of 6.6%.

cs.CL↗

arXiv2025

A degree sum condition for the existence of a quasi 5-contractible edge in a quasi 5-connected graph

An edge of a quasi $k$-connected graph is said to be quasi $k$-contractible if the contraction of the edge results in a quasi $k$-connected graph. We show that every 5-connected graph contains a quasi 5-contractible edge. Furthermore, we prove that a quasi 5-connected graph possesses a quasi 5-contractible edge, if the degree sum of any two vertices with distance at most two is at least 9. This result strengthens a theorem proved by Kriesell when $k=4$ (M. Kriesell, A degree sum condition for the existence of a contractible edge in a $k$-connected graph, J. Combin. Theory Ser. B 82(2001)81-101).

math.CO↗

arXiv2025

A forbidden pair for quasi 5-contractible edges

An edge of a quasi $k$-connected graph is said to be quasi $k$-contractible if the contraction of the edge results in a quasi $k$-connected graph. If every quasi $k$-connected graph without a quasi $k$-contractible edge has either $H_{1}$ or $H_{2}$ as a subgraph, then an unordered pair of graphs $\{H_{1}, H_{2}\}$ is said to be a forbidden pair for quasi $k$-contractible edges. We prove that $\{K_{4}^{-}, \overline{P_{5}}\}$ is a forbidden pair for quasi 5-contractible edges, where $K_{4}^{-}$ is the graph obtained from $K_{4}$ by removing just one edge and $\overline{P_{5}}$ is the complement of a path on five vertices.

math.CO↗

arXiv2025

Physics-Guided Motion Loss for Video Generation Model

Current video diffusion models generate visually compelling content but often violate basic laws of physics, producing subtle artifacts like rubber-sheet deformations and inconsistent object motion. We introduce a frequency-domain physics prior that improves motion plausibility without modifying model architectures. Our method decomposes common rigid motions (translation, rotation, scaling) into lightweight spectral losses, requiring only 2.7% of frequency coefficients while preserving 97%+ of spectral energy. Applied to Open-Sora, MVDIT, and Hunyuan, our approach improves both motion accuracy and action recognition by ~11% on average on OpenVID-1M (relative), while maintaining visual quality. User studies show 74--83% preference for our physics-enhanced videos. It also reduces warping error by 22--37% (depending on the backbone) and improves temporal consistency scores. These results indicate that simple, global spectral cues are an effective drop-in regularizer for physically plausible motion in video diffusion.

cs.CV↗

arXiv2025

A Survey on Physics-based Differentiable Rendering

Physics-based differentiable rendering has emerged as a powerful technique in computer graphics and vision, with a broad range of applications in solving inverse rendering tasks. At its core, differentiable rendering enables the computation of gradients with respect to scene parameters, allowing optimization-based approaches to solve various problems. Over the past few years, significant advancements have been made in both the underlying theory and the practical implementations of differentiable rendering algorithms. In this report, we provide a comprehensive overview of the current state of the art in physics-based differentiable rendering, focusing on recent advances in general differentiable rendering theory, Monte Carlo sampling strategy, and computational efficiency.

cs.GR↗

arXiv2025

PBR-Inspired Controllable Diffusion for Image Generation

Despite recent advances in text-to-image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G-buffer (albedo, normals, depth, roughness, shading, and metallic) from a text prompt and then renders a final image through a PBR-inspired branch network. This intermediate representation enables fine-grained control: users can copy and paste within specific G-buffer channels to insert or reposition objects, or apply masks to the irradiance channel to adjust lighting locally. As a result, real objects can be seamlessly integrated into virtual scenes. By separating user-friendly scene description from image rendering, our method offers a practical balance between detailed post-generation control and efficient text-driven synthesis. We demonstrate its effectiveness through quantitative evaluations and a user study with 156 participants, showing consistent human preference over strong baselines and confirming that G-buffer control extends the flexibility of text-guided image generation.

cs.GR↗

arXiv2024

Guiding-Based Importance Sampling for Walk on Stars

Walk on stars (WoSt) has shown its power in being applied to Monte Carlo methods for solving partial differential equations, but the sampling techniques in WoSt are not satisfactory, leading to high variance. We propose a guiding-based importance sampling method to reduce the variance of WoSt. Drawing inspiration from path guiding in rendering, we approximate the directional distribution of the recursive term of WoSt using online-learned parametric mixture distributions, decoded by a lightweight neural field. This adaptive approach enables importance sampling the recursive term, which lacks shape information before computation. We introduce a reflection technique to represent guiding distributions at Neumann boundaries and incorporate multiple importance sampling with learnable selection probabilities to further reduce variance. We also present a practical GPU implementation of our method. Experiments show that our method effectively reduces variance compared to the original WoSt, given the same time or the same sample budget. Code and data for this paper are at https://github.com/tyanyuy3125/elaina.

cs.GR↗

arXiv2024

PBIR-NIE: Glossy Object Capture under Non-Distant Lighting

Glossy objects present a significant challenge for 3D reconstruction from multi-view input images under natural lighting. In this paper, we introduce PBIR-NIE, an inverse rendering framework designed to holistically capture the geometry, material attributes, and surrounding illumination of such objects. We propose a novel parallax-aware non-distant environment map as a lightweight and efficient lighting representation, accurately modeling the near-field background of the scene, which is commonly encountered in real-world capture setups. This feature allows our framework to accommodate complex parallax effects beyond the capabilities of standard infinite-distance environment maps. Our method optimizes an underlying signed distance field (SDF) through physics-based differentiable rendering, seamlessly connecting surface gradients between a triangle mesh and the SDF via neural implicit evolution (NIE). To address the intricacies of highly glossy BRDFs in differentiable rendering, we integrate the antithetic sampling algorithm to mitigate variance in the Monte Carlo gradient estimator. Consequently, our framework exhibits robust capabilities in handling glossy object reconstruction, showcasing superior quality in geometry, relighting, and material estimation.

cs.CV↗

arXiv2024

RE-SORT: Removing Spurious Correlation in Multilevel Interaction for CTR Prediction

Click-through rate (CTR) prediction is a critical task in recommendation systems, serving as the ultimate filtering step to sort items for a user. Most recent cutting-edge methods primarily focus on investigating complex implicit and explicit feature interactions; however, these methods neglect the spurious correlation issue caused by confounding factors, thereby diminishing the model's generalization ability. We propose a CTR prediction framework that REmoves Spurious cORrelations in mulTilevel feature interactions, termed RE-SORT, which has two key components. I. A multilevel stacked recurrent (MSR) structure enables the model to efficiently capture diverse nonlinear interactions from feature spaces at different levels. II. A spurious correlation elimination (SCE) module further leverages Laplacian kernel mapping and sample reweighting methods to eliminate the spurious correlations concealed within the multilevel features, allowing the model to focus on the true causal features. Extensive experiments conducted on four challenging CTR datasets and our production dataset demonstrate that the proposed method achieves state-of-the-art performance in both accuracy and speed. The utilized codes, models and dataset will be released at https://github.com/RE-SORT.

cs.IR↗

arXiv2024

NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Rendering

Physics-based inverse rendering enables joint optimization of shape, material, and lighting based on captured 2D images. To ensure accurate reconstruction, using a light model that closely resembles the captured environment is essential. Although the widely adopted distant environmental lighting model is adequate in many cases, we demonstrate that its inability to capture spatially varying illumination can lead to inaccurate reconstructions in many real-world inverse rendering scenarios. To address this limitation, we incorporate NeRF as a non-distant environment emitter into the inverse rendering pipeline. Additionally, we introduce an emitter importance sampling technique for NeRF to reduce the rendering variance. Through comparisons on both real and synthetic datasets, our results demonstrate that our NeRF-based emitter offers a more precise representation of scene lighting, thereby improving the accuracy of inverse rendering.

cs.CV↗

arXiv2024

ReflectanceFusion: Diffusion-based text to SVBRDF Generation

We introduce Reflectance Diffusion, a new neural text-to-texture model capable of generating high-fidelity SVBRDF maps from textual descriptions. Our method leverages a tandem neural approach, consisting of two modules, to accurately model the distribution of spatially varying reflectance as described by text prompts. Initially, we employ a pre-trained stable diffusion 2 model to generate a latent representation that informs the overall shape of the material and serves as our backbone model. Then, our ReflectanceUNet enables fine-tuning control over the material's physical appearance and generates SVBRDF maps. ReflectanceUNet module is trained on an extensive dataset comprising approximately 200,000 synthetic spatially varying materials. Our generative SVBRDF diffusion model allows for the synthesis of multiple SVBRDF estimates from a single textual input, offering users the possibility to choose the output that best aligns with their requirements. We illustrate our method's versatility by generating SVBRDF maps from a range of textual descriptions, both specific and broad. Our ReflectanceUNet model can integrate optional physical parameters, such as roughness and specularity, enhancing customization. When the backbone module is fixed, the ReflectanceUNet module refines the material, allowing direct edits to its physical attributes. Comparative evaluations demonstrate that ReflectanceFusion achieves better accuracy than existing text-to-material models, such as Text2Mat, while also providing the benefits of editable and relightable SVBRDF maps.

cs.GR↗

arXiv2024

A Hierarchical Architecture for Neural Materials

Neural reflectance models are capable of reproducing the spatially-varying appearance of many real-world materials at different scales. Unfortunately, existing techniques such as NeuMIP have difficulties handling materials with strong shadowing effects or detailed specular highlights. In this paper, we introduce a neural appearance model that offers a new level of accuracy. Central to our model is an inception-based core network structure that captures material appearances at multiple scales using parallel-operating kernels and ensures multi-stage features through specialized convolution layers. Furthermore, we encode the inputs into frequency space, introduce a gradient-based loss, and employ it adaptive to the progress of the learning phase. We demonstrate the effectiveness of our method using a variety of synthetic and real examples.

cs.GR↗

arXiv2024

Neural-PBIR Reconstruction of Shape, Material, and Illumination

Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the object has been a long-standing problem in computer vision and graphics. In this paper, we introduce an accurate and highly efficient object reconstruction pipeline combining neural based object reconstruction and physics-based inverse rendering (PBIR). Our pipeline firstly leverages a neural SDF based shape reconstruction to produce high-quality but potentially imperfect object shape. Then, we introduce a neural material and lighting distillation stage to achieve high-quality predictions for material and illumination. In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination. Experimental results demonstrate our pipeline significantly outperforms existing methods quality-wise and performance-wise.

cs.CV↗