arXiv subjects

Nan Wang

Publications and source records attributed to Nan Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting

The creation of 3D scenes has traditionally been both labor-intensive and costly, requiring designers to meticulously configure 3D assets and environments. Recent advancements in generative AI, including text-to-3D and image-to-3D methods, have dramatically reduced the complexity and cost of this process. However, current techniques for editing complex 3D scenes continue to rely on generally interactive multi-step, 2D-to-3D projection methods and diffusion-based techniques, which often lack precision in control and hamper interactive-rate performance. In this work, we propose ***3DSceneEditor***, a fully 3D-based paradigm for interactive-rate, precise editing of intricate 3D scenes using Gaussian Splatting. Unlike conventional methods, 3DSceneEditor operates through a streamlined 3D pipeline, enabling direct Gaussian-based manipulation for efficient, high-quality edits based on input prompts. The proposed framework (i) integrates a pre-trained instance segmentation model for semantic labeling; (ii) employs a zero-shot grounding approach with CLIP to align target objects with user prompts; and (iii) applies scene modifications, such as object addition, repositioning, recoloring, replacing, and removal--directly on Gaussians. Extensive experimental results show that 3DSceneEditor surpasses existing state-of-the-art techniques in terms of both editing precision and efficiency, establishing a new benchmark for efficient and interactive 3D scene customization.

cs.CV↗

arXiv2026

Quantitative U/Th deposition and cleanliness control strategies in the JUNO site air

The Jiangmen Underground Neutrino Observatory (JUNO) employs a 20 kt liquid scintillator (LS) detector located 700 m underground. To meet its physics objectives, the LS must achieve an ultra-low $^{238}$U/$^{232}$Th content of 10$^{-17}$ g/g. Given that airborne dust exhibits radioactivity about 12 orders of magnitude higher, exceptional cleanliness is essential during on-site installation. The total permissible dust mass in the 20 kt LS is only about 8 mg. To attain this, the acrylic vessel interior must comply with class 1,000 cleanliness. Pre-filling water spray cleaning improves cleanliness by roughly two orders of magnitude, requiring the overall environment to be maintained between class 10,000 and 100,000. At JUNO, a cleanroom management system has been implemented across the 120,000 m$^3$ underground experimental hall. Since May 2022, continuous laser particle monitoring has consistently achieved an average cleanliness class of 74,000. Furthermore, we developed a method to directly measure $^{238}$U/$^{232}$Th deposition rates on detector surfaces. Using ICP-MS, sensitivity reaches sub-ppt levels ($<$10$^{-12}$ g/g), enabling effective cleanliness control and assessment of external contamination during detector construction.

physics.ins-det↗

arXiv2026

RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators

Operator fusion, as a key performance optimization technique in the deployment of AI models, significantly improves execution efficiency and has been widely adopted in modern AI compilers. However, for cascaded reduction operations involving multiple loops with inter-loop data dependencies, such as the safe softmax followed by GEMM within attention mechanisms, existing compilers lack effective automated fusion and kernel generation capabilities. Although some works have addressed specific instances through hand-crafted fusion strategies, their solutions are limited in generality and difficult to extend to other similar structures. Given the prevalence of such computational patterns in deep learning models, there remains significant untapped potential in achieving general and automated fusion optimization. In this paper, we present a formal theoretical methodology for analyzing cascaded reductions which can fuse them into a single loop and introduce an incremental computation form. Based on this methodology, we design Reduction Fuser (RedFuser), a framework that automatically identifies supported cascaded reduction patterns and generates optimized fused kernels. Experiments show that RedFuser successfully fuses diverse workloads, achieving up to 2$\times$ to 5$\times$ speedup over state-of-the-art AI compilers and matching the performance of highly optimized hand-written kernels. The code is available at https://github.com/alibaba/redfuser

cs.AR↗

arXiv2026

OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understanding

Multimodal Large Language Models demonstrate strong performance on natural image understanding, yet exhibit limited capability in interpreting scientific images, including but not limited to schematic diagrams, experimental characterizations, and analytical charts. This limitation is particularly pronounced in open-source MLLMs. The gap largely stems from existing datasets with limited domain coverage, coarse structural annotations, and weak semantic grounding. We introduce OmniScience, a large-scale, high-fidelity multi-modal dataset comprising 1.5 million figure-caption-context triplets, spanning more than 10 major scientific disciplines. To obtain image caption data with higher information density and accuracy for multi-modal large-model training, we develop a dynamic model-routing re-captioning pipeline that leverages state-of-the-art multi-modal large language models to generate dense, self-contained descriptions by jointly synthesizing visual features, original figure captions, and corresponding in-text references authored by human scientists. The pipeline is further reinforced with rigorous quality filtering and alignment with human expert judgments, ensuring both factual accuracy and semantic completeness, and boosts the image-text multi-modal similarity score from 0.769 to 0.956. We further propose a caption QA protocol as a proxy task for evaluating visual understanding. Under this setting, Qwen2.5-VL-3B model finetuned on OmniScience show substantial gains over baselines, achieving a gain of 0.378 on MM-MT-Bench and a gain of 0.140 on MMMU.

cs.CV↗

arXiv2026

Emergence of a spin Hall topological Hall effect in the non-collinear phase of the ferrimagnetic insulator terbium-iron garnet

Magnetic compensation in rare-earth iron garnets (REIGs) offers a unique setting for which competing sublattice moments can give rise to non-collinear (canted) magnetic configurations, in which the sublattice magnetizations are not aligned with each other or with the external magnetic field. We show that this compensation regime can also host non-trivial magnetic textures. To explore this behavior, we investigated (111)-oriented epitaxial Tb$_3$Fe$_5$O$_{12}$/Pt heterostructures across the compensation temperature region using combined transverse magneto-transport and polar Kerr microscopy. Notably, we observe a topological Hall-like signal in the vicinity of the compensation temperature, a feature often interpreted as evidence for skyrmions in the absence of direct imaging. Here, in contrast, complementary Kerr microscopy reveals instead a non-collinear multidomain state which collapses outside the compensation regime, correlating directly with the appearance and disappearance of the spin Hall topological Hall effect (SH-THE) signal. These observations cannot be accounted for by a simple multi-anomalous-Hall-effect model, ruling out common artifacts as the origin, but indicate the presence of a topologically non-trivial contribution to the Hall response. These results establish strained REIG films as a tunable platform for exploring topological responses arising from compensation-driven non-collinear ferrimagnetic phases.

cond-mat.mtrl-sci↗

arXiv2026

Can Vision-Language Models Handle Long-Context Code? An Empirical Study on Visual Compression

Large Language Models (LLMs) struggle with long-context code due to window limitations. Existing textual code compression methods mitigate this via selective filtering but often disrupt dependency closure, causing semantic fragmentation. To address this, we introduce LongCodeOCR, a visual compression framework that renders code into compressed two-dimensional image sequences for Vision-Language Models (VLMs). By preserving a global view, this approach avoids the dependency breakage inherent in filtering. We systematically evaluate LongCodeOCR against the state-of-the-art LongCodeZip across four benchmarks spanning code summarization, code question answering, and code completion. Our results demonstrate that visual code compression serves as a viable alternative for tasks requiring global understanding. At comparable compression ratios ($\sim$1.7$\times$), LongCodeOCR improves CompScore on Long Module Summarization by 36.85 points over LongCodeZip. At a 1M-token context length with Glyph (a specialized 9B VLM), LongCodeOCR maintains higher accuracy than LongCodeZip while operating at about 4$\times$ higher compression. Moreover, compared with LongCodeZip, LongCodeOCR drastically reduces compression-stage overhead (reducing latency from $\sim$4.3 hours to $\sim$1 minute at 1M tokens). Finally, our results characterize a fundamental coverage--fidelity trade-off: visual code compression retains broader context coverage to support global dependencies, yet faces fidelity bottlenecks on exactness-critical tasks; by contrast, textual code compression preserves symbol-level precision while sacrificing structural coverage.

cs.SE↗

arXiv2026

Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent performance on general vision tasks. Contrary to the trend of relying on massive domain-specific pretraining and opaque pipelines, our work demonstrates that principled training design and transparent methodology can yield strong scientific intelligence with substantially reduced data requirements. (i) First, we provide a fully transparent, end-to-end reproducible training pipeline, covering data collection, cleaning, preprocessing, supervised fine-tuning, reinforcement learning, and evaluation, along with detailed optimization recipes. This facilitates systematic extension by the community. (ii) Second, Innovator-VL exhibits remarkable data efficiency, achieving competitive performance on various scientific tasks using fewer than five million curated samples without large-scale pretraining. These results highlight that effective reasoning can be achieved through principled data selection rather than indiscriminate scaling. (iii) Third, Innovator-VL demonstrates strong generalization, achieving competitive performance on general vision, multimodal reasoning, and scientific benchmarks. This indicates that scientific alignment can be integrated into a unified model without compromising general-purpose capabilities. Our practices suggest that efficient, reproducible, and high-performing scientific multimodal models can be built even without large-scale data, providing a practical foundation for future research.

cs.CV↗

arXiv2026

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

Neural rendering techniques, including NeRF and Gaussian Splatting (GS), rely on photometric consistency to produce high-quality reconstructions. However, in real-world scenarios, it is challenging to guarantee perfect photometric consistency in acquired images. Appearance codes have been widely used to address this issue, but their modeling capability is limited, as a single code is applied to the entire image. Recently, the bilateral grid was introduced to perform pixel-wise color mapping, but it is difficult to optimize and constrain effectively. In this paper, we propose a novel multi-scale bilateral grid that unifies appearance codes and bilateral grids. We demonstrate that this approach significantly improves geometric accuracy in dynamic, decoupled autonomous driving scene reconstruction, outperforming both appearance codes and bilateral grids. This is crucial for autonomous driving, where accurate geometry is important for obstacle avoidance and control. Our method shows strong results across four datasets: Waymo, NuScenes, Argoverse, and PandaSet. We further demonstrate that the improvement in geometry is driven by the multi-scale bilateral grid, which effectively reduces floaters caused by photometric inconsistency.

cs.CV↗

arXiv2026

Advanced Global Wildfire Activity Modeling with Hierarchical Graph ODE

Wildfires, as an integral component of the Earth system, are governed by a complex interplay of atmospheric, oceanic, and terrestrial processes spanning a vast range of spatiotemporal scales. Modeling their global activity on large timescales is therefore a critical yet challenging task. While deep learning has recently achieved significant breakthroughs in global weather forecasting, its potential for global wildfire behavior prediction remains underexplored. In this work, we reframe this problem and introduce the Hierarchical Graph ODE (HiGO), a novel framework designed to learn the multi-scale, continuous-time dynamics of wildfires. Specifically, we represent the Earth system as a multi-level graph hierarchy and propose an adaptive filtering message passing mechanism for both intra- and inter-level information flow, enabling more effective feature extraction and fusion. Furthermore, we incorporate GNN-parameterized Neural ODE modules at multiple levels to explicitly learn the continuous dynamics inherent to each scale. Through extensive experiments on the SeasFire Cube dataset, we demonstrate that HiGO significantly outperforms state-of-the-art baselines on long-range wildfire forecasting. Moreover, its continuous-time predictions exhibit strong observational consistency, highlighting its potential for real-world applications.

cs.LG↗

arXiv2025

$η$ and $η'$ mesons from $N_f = 2+1$ lattice QCD at the physical point using topological charge operators

By fitting the two-point correlation functions of topological charge density operators calculated on two $2+1$-flavor gauge ensembles with physical pion mass, we determine both the $η$ and $η'$ masses and also the mixing angle to be $m_η= 0.505(72)(75)$ GeV, $m_{η'}=0.952(47)(40)$ GeV, and $θ_1 = -8.9(2.1)(1.8)^\circ$, respectively, where the first error is the statistical uncertainty and the second one is the systematic uncertainty. This is the first extraction of both $η/η'$ masses and the mixing angle $θ_1$ using topological charge operators. Compared with previous studies using quark bilinear operators, the error of the $η$ mass is relatively large, but the mixing angle has comparable precision. This demonstrates that the topological charge operators are well suited to study the $η$ and $η'$ mesons.

hep-lat↗

arXiv2025

Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monocular depth, causing holes and temporally unstable estimates. Our key observation is that modern video diffusion models already synthesize convincing transparent phenomena, suggesting they have internalized the optical rules. We build TransPhy3D, a synthetic video corpus of transparent/reflective scenes: 11k sequences rendered with Blender/Cycles. Scenes are assembled from a curated bank of category-rich static assets and shape-rich procedural assets paired with glass/plastic/metal materials. We render RGB + depth + normals with physically based ray tracing and OptiX denoising. Starting from a large video diffusion model, we learn a video-to-video translator for depth (and normals) via lightweight LoRA adapters. During training we concatenate RGB and (noisy) depth latents in the DiT backbone and co-train on TransPhy3D and existing frame-wise synthetic datasets, yielding temporally consistent predictions for arbitrary-length input videos. The resulting model, DKT, achieves zero-shot SOTA on real and synthetic video benchmarks involving transparency: ClearPose, DREDS (CatKnown/CatNovel), and TransPhy3D-Test. It improves accuracy and temporal consistency over strong image/video baselines, and a normal variant sets the best video normal estimation results on ClearPose. A compact 1.3B version runs at ~0.17 s/frame. Integrated into a grasping stack, DKT's depth boosts success rates across translucent, reflective and diffuse surfaces, outperforming prior estimators. Together, these results support a broader claim: "Diffusion knows transparency." Generative video priors can be repurposed, efficiently and label-free, into robust, temporally coherent perception for challenging real-world manipulation.

cs.CV↗

arXiv2025

AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model

In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in memory, power consumption, and computing capacity of edge devices such as mobile phones. This paper introduces AndesVL, a suite of mobile-side MLLMs with 0.6B to 4B parameters based on Qwen3's LLM and various visual encoders. We comprehensively outline the model architectures, training pipeline, and training data of AndesVL, which achieves first-tier performance across a wide range of open-source benchmarks, including fields such as text-rich image understanding, reasoning and math, multi-image comprehension, general VQA, hallucination mitigation, multilingual understanding, and GUI-related tasks when compared with state-of-the-art models of a similar scale. Furthermore, we introduce a 1+N LoRA architecture alongside a Quantization-Aware LoRA Fine-Tuning (QALFT) framework to facilitate efficient task adaptation and model compression during mobile-side deployment of AndesVL. Moreover, utilizing our cache eviction algorithm -- OKV -- along with customized speculative decoding and compression strategies, we achieve a 6.7x peak decoding speedup ratio, up to 30.9% memory reduction, and 1.8 bits-per-weight when deploying AndesVL-4B on MediaTek Dimensity 9500 chips. We release all models on https://huggingface.co/OPPOer.

cs.CV↗

arXiv2025

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images

Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows, making them slow and impractical. We revisit this problem from a feedforward perspective and introduce \textbf{Driving Gaussian Grounded Transformer (DGGT)}, a unified framework for pose-free dynamic scene reconstruction. We note that the existing formulations, treating camera pose as a required input, limit flexibility and scalability. Instead, we reformulate pose as an output of the model, enabling reconstruction directly from sparse, unposed images and supporting an arbitrary number of views for long sequences. Our approach jointly predicts per-frame 3D Gaussian maps and camera parameters, disentangles dynamics with a lightweight dynamic head, and preserves temporal consistency with a lifespan head that modulates visibility over time. A diffusion-based rendering refinement further reduces motion/interpolation artifacts and improves novel-view quality under sparse inputs. The result is a single-pass, pose-free algorithm that achieves state-of-the-art performance and speed. Trained and evaluated on large-scale driving benchmarks (Waymo, nuScenes, Argoverse2), our method outperforms prior work both when trained on each dataset and in zero-shot transfer across datasets, and it scales well as the number of input frames increases.

cs.CV↗

arXiv2025

A dynamic shim approach for correcting eddy current effects in diffusion-prepared MRI acquisition using a multi-coil AC/DC shim-array

Purpose: We developed a dynamic B0 shimming approach using a 46-channel AC/DC shim array to correct phase errors caused by eddy currents from diffusion-encoding gradients in diffusion-prepared MRI, enabling high b-value imaging without the SNR loss from the use of magnitude stabilizer. Methods: A 46-channel AC/DC shim array and corresponding amplifier system were built. Spin echo prescans with and without diffusion preparation were then used to rapidly measure eddy current induced phase differences. These phase maps were used as targets in an optimization framework to compute compensatory shim currents for multi-shot 3D diffusion-prepared acquisitions. Results: The proposed method allows flexible use of the AC/DC shim array to correct undesirable eddy current effects in diffusion-prepared MRI. Phantom and in vivo experiments demonstrate whole-brain, cardiac-gated, multi-shot 3D diffusion-prepared imaging without the use of magnitude stabilizers. The approach enables preservation of full SNR while achieving reliable diffusion encoding at b-values up to 2000 s/mm2. Conclusions: This work demonstrates a new strategy for applying an AC/DC shim array to compensate for eddy current induced phase errors in diffusion-prepared MRI. By eliminating the need for magnitude stabilizer, it enables efficient high-quality diffusion imaging with full signal sensitivity retained.

physics.med-ph↗

arXiv2025

Unlocking Out-of-Distribution Generalization in Dynamics through Physics-Guided Augmentation

In dynamical system modeling, traditional numerical methods are limited by high computational costs, while modern data-driven approaches struggle with data scarcity and distribution shifts. To address these fundamental limitations, we first propose SPARK, a physics-guided quantitative augmentation plugin. Specifically, SPARK utilizes a reconstruction autoencoder to integrate physical parameters into a physics-rich discrete state dictionary. This state dictionary then acts as a structured dictionary of physical states, enabling the creation of new, physically-plausible training samples via principled interpolation in the latent space. Further, for downstream prediction, these augmented representations are seamlessly integrated with a Fourier-enhanced Graph ODE, a combination designed to robustly model the enriched data distribution while capturing long-term temporal dependencies. Extensive experiments on diverse benchmarks demonstrate that SPARK significantly outperforms state-of-the-art baselines, particularly in challenging out-of-distribution scenarios and data-scarce regimes, proving the efficacy of our physics-guided augmentation paradigm.

cs.LG↗

arXiv2025

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

The modeling of complicated time-evolving physical dynamics from partial observations is a long-standing challenge. Particularly, observations can be sparsely distributed in a seemingly random or unstructured manner, making it difficult to capture highly nonlinear features in a variety of scientific and engineering problems. However, existing data-driven approaches are often constrained by fixed spatial and temporal discretization. While some researchers attempt to achieve spatio-temporal continuity by designing novel strategies, they either overly rely on traditional numerical methods or fail to truly overcome the limitations imposed by discretization. To address these, we propose CoPS, a purely data-driven methods, to effectively model continuous physics simulation from partial observations. Specifically, we employ multiplicative filter network to fuse and encode spatial information with the corresponding observations. Then we customize geometric grids and use message-passing mechanism to map features from original spatial domain to the customized grids. Subsequently, CoPS models continuous-time dynamics by designing multi-scale graph ODEs, while introducing a Markov-based neural auto-correction module to assist and constrain the continuous extrapolations. Comprehensive experiments demonstrate that CoPS advances the state-of-the-art methods in space-time continuous modeling across various scenarios.

cs.CV↗

arXiv2025

Driving factors of auditory category learning success

Our brain learns to update its mental model of the environment by abstracting sensory experiences for adaptation and survival. Learning to categorize sounds is one essential abstracting process for high-level human cognition, such as speech perception, but it is also challenging due to the variable nature of auditory signals and their dynamic contexts. To overcome these learning challenges and enhance learner performance, it is essential to identify the impact of learning-related factors in developing better training protocols. Here, we conducted an extensive meta-analysis of auditory category learning studies, including a total of 111 experiments and 4,521 participants, and examined to what extent three hidden factors (i.e., variability, intensity, and engagement) derived from 12 experimental variables contributed to learning success (i.e., effect sizes). Variables related to intensity and training variability outweigh others in predicting learning effect size. Activation likelihood estimation (ALE) meta-analysis of the neuroimaging studies revealed training-induced systematic changes in the frontotemporal-parietal networks. Increased brain activities in speech and motor-related auditory-frontotemporal regions and decreased activities in cuneus and precuneus areas are associated with increased learning effect sizes. These findings not only enhance our understanding of the driving forces behind speech and auditory category learning success, along with its neural changes, but also guide researchers and practitioners in designing more effective training protocols that consider the three key aspects of learning to facilitate learner success.

q-bio.NC↗

arXiv2025

Theoretical Performance Limit for Radar Parameter Estimation

In this paper, we employ the thoughts and methodologies of Shannon's information theory to solve the problem of the optimal radar parameter estimation. Based on a general radar system model, the \textit{a posteriori} probability density function of targets' parameters is derived. Range information (RI) and entropy error (EE) are defined to evaluate the performance. It is proved that acquiring 1 bit of the range information is equivalent to reducing estimation deviation by half. The closed-form approximation for the EE is deduced in all signal-to-noise ratio (SNR) regions, which demonstrates that the EE degenerates to the mean square error (MSE) when the SNR is tending to infinity. Parameter estimation theorem is then proved, which claims that the theoretical RI is achievable. The converse claims that there exists no unbiased estimator whose empirical RI is larger than the theoretical RI. Simulation result demonstrates that the theoretical EE is tighter than the commonly used Cramér-Rao bound and the ZivZakai bound.

cs.IT↗