Searcharxiv⌕ Search

arXiv subjects

Shanwen Wang

Publications and source records attributed to Shanwen Wang.

At least 19 recordsLinked to original sources
arXiv2026

Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank

Although semi-supervised semantic segmentation ($\text{S}^4$) utilizes abundant unlabeled data to reduce manual labeling burdens, independent training of labeled and unlabeled data causes the former to dominate, which severely degrades pseudo-label quality. To address this challenges, we propose a novel remote sensing (RS) $\text{S}^4$ method via unified flow with feature memory bank (UFFM). Specifically, UFFM comprises two key innovations: unified flow (UF) and feature memory bank (FMB). The UF is a new training flow that generates less biased pseudo-labels by combining an external visual foundation model (VFM) with an RS domain teacher, and jointly optimizes labeled and pseudo-labeled data under a unified training objective. The FMB is a novel memory module for $\text{S}^4$ that dynamically updates class-specific features during training and reduces the feature discrepancy between labeled and unlabeled data through class-feature alignment. To verify the effectiveness of our model, we conduct extensive experiments on RS datasets. The experimental results show the superiority of our method over SOTA $\text{S}^4$ methods. Moreover, the results demonstrate the effectiveness of our contributions in bridging the optimization and feature representation gap between labeled and unlabeled data. Our code is released at \href{https://github.com/wangshanwen001/RS-UFFM}{https://github.com/wangshanwen001/RS-UFFM}.

cs.CV↗
arXiv2026

$p$-adic Hahn series with sparse support

Let $p$ be a prime number. We introduce a sparseness condition on the supports of $p$-adic Hahn series, and prove that this condition implies transcendence over $\breve{\mathbf Q}_p$, the completed maximal unramified extension of $\mathbf{Q}_p$. As an application, we prove the order-type conjecture of $\mathbf{Q}_p$-algebraic $p$-adic Hahn series with bounded support under the condition that the support has only finitely many accumulation points. All results in this paper have been fully formalized in the Lean theorem prover (v 4.31.0), building over Mathlib.

math.NT↗
arXiv2026

RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation

Open-vocabulary semantic segmentation (OVSS) enables text-guided segmentation of unseen objects, breaking fixed-class limitations to achieve open-world understanding. However, existing OVSS methods primarily focus on modifying the CLIP attention mechanism, which still suffers from unstable local segmentation for remote sensing (RS) domain. To address these limitations, we propose RSGPNet, a training-free geometric prompting framework for RS OVSS that refines segmentation by leveraging object geometric areas and consistency constraints. Specifically, RSGPNet comprises three core modules: a Text-guided Coarse Mask module (TCM), a Geometric Re-prompting Module (GRP), and a Coarse-to-fine Consistency Verification Mechanism (CVM). TCM utilizes text prompts and the input image to construct initial coarse segmentation masks. GRP then converts these coarse masks into geometric box prompts, feeding them back into the segmentation model to generate refined masks. Finally, CVM employs consistency computation to prevent prompting from reinforcing erroneous regions. They allow the model to improve segmentation accuracy in complex areas, such as category boundaries. Extensive experiments on RS datasets demonstrate that RSGPNet significantly outperforms state-of-the-art methods across both quantitative and qualitative metrics while exhibiting excellent interpretability. The code is released at \href{https://github.com/wangshanwen001/RSGPNet}{https://github.com/wangshanwen001/RSGPNet}.

cs.CV↗
arXiv2026

Hyper-algebraic invariants of $p$-adic algebraic numbers

Let $p\geq 3$ be a prime. The hyper-algebraic elements in the $p$-adic Mal'cev-Neumann field $\mathbb{L}_p$ form an algebraically closed subfield $\mathbb{L}_p^{\operatorname{ha}}$. In this article, we clarify the relations among the fields $\mathbb{L}_p^{\operatorname{ha}}$, $\overline{\mathbb{Q}}_p$ and $\mathbb{C}_p$. We introduce two arithmetic invariants (hyper-tame index and hyper-inertia index) of hyper-algebraic elements and study the relation between these invariants and classical arithmetic invariants of $p$-adic algebraic numbers. Finally, we give a criterion for hyper-algebraic elements to be tamely ramified over $\mathbb{Q}_p$.

math.NT↗
arXiv2026

Log $p$-divisible groups and semi-stable representations

Let $\mathscr{O}_K$ be a henselian DVR with field of fractions $K$ and residue field of characteristic $p>0$. Let $S$ denote $\mathop{\mathrm{Spec}} \mathscr{O}_K$ endowed with the canonical log structure. We show that the generic fiber functor $\mathbf{BT}_{S, {\mathrm{d}}}^{\log}\to \mathbf{BT}^{\mathrm{st}}_K$ between the category of dual representable log $p$-divisible groups over $S$ and the category of $p$-divisible groups with semistable reduction over $K$ is an equivalence. If $\mathscr{O}_K$ is further complete with perfect residue field and of mixed characteristic, we show that $\mathbf{BT}_{S, {\mathrm{d}}}^{\log}$ is also equivalent to the category of semistable Galois $\mathbb{Z}_p$-representations with Hodge-Tate weights in $\{0,1\}$. Finally, we show that the above equivalences respect monodromies.

math.NT↗
arXiv2026

Vision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing Images

The semi-supervised semantic segmentation (S4) can learn rich visual knowledge from low-cost unlabeled images. However, traditional S4 architectures all face the challenge of low-quality pseudo-labels, especially for the teacher-student framework.We propose a novel SemiEarth model that introduces vision-language models (VLMs) to address the S4 issues for the remote sensing (RS) domain. Specifically, we invent a VLM pseudo-label purifying (VLM-PP) structure to purify the teacher network's pseudo-labels, achieving substantial improvements. Especially in multi-class boundary regions of RS images, the VLM-PP module can significantly improve the quality of pseudo-labels generated by the teacher, thereby correctly guiding the student model's learning. Moreover, since VLM-PP equips VLMs with open-world capabilities and is independent of the S4 architecture, it can correct mispredicted categories in low-confidence pseudo-labels whenever a discrepancy arises between its prediction and the pseudo-label. We conducted extensive experiments on multiple RS datasets, which demonstrate that our SemiEarth achieves SOTA performance. More importantly, unlike previous SOTA RS S4 methods, our model not only achieves excellent performance but also offers good interpretability. The code is released at https://github.com/wangshanwen001/SemiEarth.

cs.CV↗
arXiv2026

Rethinking Residual Distribution in Locate-then-Edit Model Editing

Model editing enables targeted updates to the knowledge of large language models (LLMs) with minimal retraining. Among existing approaches, locate-then-edit methods constitute a prominent paradigm: they first identify critical layers, then compute residuals at the final critical layer based on the target edit, and finally apply least-squares-based multi-layer updates via $\textbf{residual distribution}$. While empirically effective, we identify a counterintuitive failure mode: residual distribution, a core mechanism in these methods, introduces weight shift errors that undermine editing precision. Through theoretical and empirical analysis, we show that such errors increase with the distribution distance, batch size, and edit sequence length, ultimately leading to inaccurate or suboptimal edits. To address this, we propose the $\textbf{B}$oundary $\textbf{L}$ayer $\textbf{U}$pdat$\textbf{E (BLUE)}$ strategy to enhance locate-then-edit methods. Sequential batch editing experiments on three LLMs and two datasets demonstrate that BLUE not only delivers an average performance improvement of 35.59\%, significantly advancing the state of the art in model editing, but also enhances the preservation of LLMs' general capabilities. Our code is available at https://github.com/xpq-tech/BLUE.

cs.CL↗
arXiv2025

Parameters and Theta lifts

In this note, we make explicit the correspondence between Harish-Chandra parameters and Langlands-Vogan parameters for symplectic groups and orthogonal groups of equal rank over reals. As an application, we reformulate Moeglin's results and Paul's work on the Howe correspondence for symplectic-orthogonal dual pairs using Langlands-Vogan parameters.

math.RT↗
arXiv2025

PRISM: Progressive Rain removal with Integrated State-space Modeling

Image deraining is an essential vision technique that removes rain streaks and water droplets, enhancing clarity for critical vision tasks like autonomous driving. However, current single-scale models struggle with fine-grained recovery and global consistency. To address this challenge, we propose Progressive Rain removal with Integrated State-space Modeling (PRISM), a progressive three-stage framework: Coarse Extraction Network (CENet), Frequency Fusion Network (SFNet), and Refine Network (RNet). Specifically, CENet and SFNet utilize a novel Hybrid Attention UNet (HA-UNet) for multi-scale feature aggregation by combining channel attention with windowed spatial transformers. Moreover, we propose Hybrid Domain Mamba (HDMamba) for SFNet to jointly model spatial semantics and wavelet domain characteristics. Finally, RNet recovers the fine-grained structures via an original-resolution subnetwork. Our model learns high-frequency rain characteristics while preserving structural details and maintaining global context, leading to improved image quality. Our method achieves competitive results on multiple datasets against recent deraining methods.

cs.CV↗
arXiv2025

On the $p$-adic transcendence of $\sum_{k=1}^\infty p^{-1/p^k}$

Let $p$ be a prime number. In this article, we prove that the $p$-adic Hahn series $\sum_{k=1}^\infty p^{-1/p^k}$, which is the mixed-characteristic analogue of Abhyankar's solution $\sum_{k=1}^\infty t^{-1/p^k}$ to the Artin-Schreier equation $X^p-X-t^{-1}=0$ over $\mathbf{F}_p\left(\!\left(t\right)\!\right)$, is a $p$-adic complex number, but not a $p$-adic algebraic number. Based on this result, we formulate a conjecture about the possible order type of the support of an algebraic $p$-adic Hahn series and prove that it is implied by a tentative observation of Kedlaya.

math.NT↗
arXiv2025

Learning an Effective Premise Retrieval Model for Efficient Mathematical Formalization

Formalized mathematics has recently garnered significant attention for its ability to assist mathematicians across various fields. Premise retrieval, as a common step in mathematical formalization, has been a challenge, particularly for inexperienced users. Existing retrieval methods that facilitate natural language queries require a certain level of mathematical expertise from users, while approaches based on formal languages (e.g., Lean) typically struggle with the scarcity of training data, hindering the training of effective and generalizable retrieval models. In this work, we introduce a novel method that leverages data extracted from Mathlib to train a lightweight and effective premise retrieval model. In particular, the proposed model embeds queries (i.e., proof state provided by Lean) and premises in a latent space, featuring a tokenizer specifically trained on formal corpora. The model is learned in a contrastive learning framework, in which a fine-grained similarity calculation method and a re-ranking module are applied to enhance the retrieval performance. Experimental results demonstrate that our model outperforms existing baselines, achieving higher accuracy while maintaining a lower computational load. We have released an open-source search engine based on our retrieval model at https://premise-search.com/. The source code and the trained model can be found at https://github.com/ruc-ai4math/Premise-Retrieval.

cs.CL↗
arXiv2025

Semi-supervised Semantic Segmentation for Remote Sensing Images via Multi-scale Uncertainty Consistency and Cross-Teacher-Student Attention

Semi-supervised learning offers an appealing solution for remote sensing (RS) image segmentation to relieve the burden of labor-intensive pixel-level labeling. However, RS images pose unique challenges, including rich multi-scale features and high inter-class similarity. To address these problems, this paper proposes a novel semi-supervised Multi-Scale Uncertainty and Cross-Teacher-Student Attention (MUCA) model for RS image semantic segmentation tasks. Specifically, MUCA constrains the consistency among feature maps at different layers of the network by introducing a multi-scale uncertainty consistency regularization. It improves the multi-scale learning capability of semi-supervised algorithms on unlabeled data. Additionally, MUCA utilizes a Cross-Teacher-Student attention mechanism to guide the student network, guiding the student network to construct more discriminative feature representations through complementary features from the teacher network. This design effectively integrates weak and strong augmentations (WA and SA) to further boost segmentation performance. To verify the effectiveness of our model, we conduct extensive experiments on ISPRS-Potsdam and LoveDA datasets. The experimental results show the superiority of our method over state-of-the-art semi-supervised methods. Notably, our model excels in distinguishing highly similar objects, showcasing its potential for advancing semi-supervised RS image segmentation tasks.

cs.CV↗
arXiv2025

Fiber Signal Denoising Algorithm using Hybrid Deep Learning Networks

With the applicability of optical fiber-based distributed acoustic sensing (DAS) systems, effective signal processing and analysis approaches are needed to promote its popularization in the field of intelligent transportation systems (ITS). This paper presents a signal denoising algorithm using a hybrid deep-learning network (HDLNet). Without annotated data and time-consuming labeling, this self-supervised network runs in parallel, combining an autoencoder for denoising (DAE) and a long short-term memory (LSTM) for sequential processing. Additionally, a line-by-line matching algorithm for vehicle detection and tracking is introduced, thus realizing the complete processing of fiber signal denoising and feature extraction. Experiments were carried out on a self-established real highway tunnel dataset, showing that our proposed hybrid network yields more satisfactory denoising performance than Spatial-domain DAE.

eess.SP↗
arXiv2025

Traffic Flow and Speed Monitoring Based On Optical Fiber Distributed Acoustic Sensor

In the realm of intelligent transportation systems, accurate and reliable traffic monitoring is crucial. Traditional devices, such as cameras and lidars, face limitations in adverse weather conditions and complex traffic scenarios, prompting the need for more resilient technologies. Thispaperpresentstrafficflowmonitoringmethodusingopticalfiber-baseddistributedacoustic sensors(DAS).Aninnovativevehicletrajectoryextractionalgorithmisproposedtoderivetraffic flow statistics. In the processing of optical fiber waterfall diagrams, Butterworth low-pass filter and peaks location search algorithm are employed to determine the entry position of vehicles. Subsequently, line-by-line matching algorithm is proposed to effectively track the trajectories. Experiments were conducted in highway, tunnel and city scenarios. Visualizations show that ourapproachnotonlyextractsvehicletrajectoriesmoreaccuratelythantheclassicalHoughand Radon transform-based methods and MUSIC beamforming algorithm, but also facilitates the calculation of traffic flow information using the low-cost acoustic sensors. It provides a new reliable means for traffic flow monitoring which can be integrated with existing methods like vision-based method.

eess.SP↗
arXiv2024

Online Mean Estimation for Multi-frame Optical Fiber Signals On Highways

In the era of Big Data, prompt analysis and processing of data sets is critical. Meanwhile, statistical methods provide key tools and techniques to extract valuable insights and knowledge from complex data sets. This paper creatively applies statistical methods to the field of traffic, particularly focusing on the preprocessing of multi-frame signals obtained by optical fiber-based Distributed Acoustic Sensing (DAS) system. An online non-parametric regression model based on Local Polynomial Regression (LPR) and variable bandwidth selection is employed to dynamically update the estimation of mean function as signals flow in. This mean estimation method can derive average information of multi-frame fiber signals, thus providing the basis for the subsequent vehicle trajectory extraction algorithms. To further evaluate the effectiveness of the proposed method, comparison experiments were conducted under real highway scenarios, showing that our approach not only deals with multi-frame signals more accurately than the classical filter-based Kalman and Wavelet methods, but also meets the needs better under the condition of saving memory and rapid responses. It provides a new reliable means for signal processing which can be integrated with other existing methods.

eess.SP↗
arXiv2024

Une factorisation de la cohomologie complétée et du système de Beilinson-Kato

We show that the modular symbol $(0,\infty)$, considered as an element of the dual of Emerton's completed cohomology, interpolates Kato's Euler system at classical points, and we deduce from this a factorisation of Beilinson-Kato's system as a product of two symbols $(0,\infty)$ (an algebraic analog of Rankin's method). The proof uses the $p$-adic local Langlands correspondence for ${\mathbf GL}_2({\mathbf Q}_p)$ and Emerton's factorization of the completed cohomology of the tower of modular curves for which we provide a new proof resting upon the construction of a Kirillov model for the completed cohomology, and which we refine by imposing conditions at classical points; the existence of such a refinement is a manifestation of an analyticity property for $p$-adic periods of modular forms.

math.NT↗
arXiv2023

Uniformizer of the False Tate Curve Extension of $\mathbb{Q}_p$ (II)

In this article, we investigate the explicit formula for the uniformizers of the false-Tate curve extension of $\mathbb{Q}_p$. More precisely, we establish the formula for the fields ${\mathbb{K}}_p^{m,1}={\mathbb{Q}}_p(ζ_{p^m}, p^{1/p})$ with $m\geq 1$ and for general $n\geq 2$, we prove the existence of the recurrence polynomials ${\mathcal{R}}_p^{m,n}$ for general field extensions ${\mathbb{K}}_p^{m, n}$ of ${\mathbb{Q}}_p$, which shows the possibility to construct the uniformizers systematically.

math.NT↗