Searcharxiv⌕ Search

arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 379 records · Page 21Linked to original sources
arXiv2025

Partition subcubic planar graphs into independent sets

A packing $(1^{\ell}, 2^k)$-coloring of a graph $G$ is a partition of $V(G)$ into $\ell$ independent sets and $k$ $2$-packings (whose pairwise vertex distance is at least $3$). The square coloring of planar graphs was first studied by Wegner in 1977. Thomassen and independently Hartke et al. proved one can always square color a cubic planar graph with $7$ colors, i.e., every subcubic planar graph is packing $(2^7)$-colorable. We focus on packing $(1^{\ell}, 2^k)$-colorings, which lie between proper coloring and square coloring. Gastineau and Togni proved every subcubic graph is packing $(1,2^6)$-colorable and asked whether every subcubic graph except the Petersen graph is packing $(1,2^5)$-colorable. In this paper, we prove an analogue result of Thomassen and Hartke et al. on packing coloring that every subcubic planar graph is packing $(1,2^5)$-colorable. This also answers the question of Gastineau and Togni affirmatively for subcubic planar graphs. Moreover, we prove that there exists an infinite family of subcubic planar graphs that are not packing $(1,2^4)$-colorable, which shows that our result is the best possible. Besides, our result is also sharp in the sense that the disjoint union of Petersen graphs is subcubic and non-planar, but not packing $(1,2^5)$-colorable.

math.CO↗
arXiv2025

Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models

Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in standard decoder-only Transformers. Although powerful, this method can be inefficient for long sequences and may overlook inherent input structures. To address these problems, an alternative approach is parallel context encoding, which splits the context into sub-pieces and encodes them parallelly. Because parallel patterns are not encountered during training, naively applying parallel encoding leads to performance degradation. However, the underlying reasons and potential mitigations are unclear. In this work, we provide a detailed analysis of this issue and identify that unusually high attention entropy can be a key factor. Furthermore, we adopt two straightforward methods to reduce attention entropy by incorporating attention sinks and selective mechanisms. Experiments on various tasks reveal that these methods effectively lower irregular attention entropy and narrow performance gaps. We hope this study can illuminate ways to enhance context modeling mechanisms.

cs.CL↗
arXiv2025

Historical Report Guided Bi-modal Concurrent Learning for Pathology Report Generation

Automated pathology report generation from Whole Slide Images (WSIs) faces two key challenges: (1) lack of semantic content in visual features and (2) inherent information redundancy in WSIs. To address these issues, we propose a novel Historical Report Guided \textbf{Bi}-modal Concurrent Learning Framework for Pathology Report \textbf{Gen}eration (BiGen) emulating pathologists' diagnostic reasoning, consisting of: (1) A knowledge retrieval mechanism to provide rich semantic content, which retrieves WSI-relevant knowledge from pre-built medical knowledge bank by matching high-attention patches and (2) A bi-modal concurrent learning strategy instantiated via a learnable visual token and a learnable textual token to dynamically extract key visual features and retrieved knowledge, where weight-shared layers enable cross-modal alignment between visual features and knowledge features. Our multi-modal decoder integrates both modals for comprehensive diagnostic reports generation. Experiments on the PathText (BRCA) dataset demonstrate our framework's superiority, achieving state-of-the-art performance with 7.4\% relative improvement in NLP metrics and 19.1\% enhancement in classification metrics for Her-2 prediction versus existing methods. Ablation studies validate the necessity of our proposed modules, highlighting our method's ability to provide WSI-relevant rich semantic content and suppress information redundancy in WSIs. Code is publicly available at https://github.com/DeepMed-Lab-ECNU/BiGen.

cs.CV↗
arXiv2025

Fast Training-free Perceptual Image Compression

Training-free perceptual image codec adopt pre-trained unconditional generative model during decoding to avoid training new conditional generative model. However, they heavily rely on diffusion inversion or sample communication, which take 1 min to intractable amount of time to decode a single image. In this paper, we propose a training-free algorithm that improves the perceptual quality of any existing codec with theoretical guarantee. We further propose different implementations for optimal perceptual quality when decoding time budget is $\approx 0.1$s, $0.1-10$s and $\ge 10$s. Our approach: 1). improves the decoding time of training-free codec from 1 min to $0.1-10$s with comparable perceptual quality. 2). can be applied to non-differentiable codec such as VTM. 3). can be used to improve previous perceptual codecs, such as MS-ILLM. 4). can easily achieve perception-distortion trade-off. Empirically, we show that our approach successfully improves the perceptual quality of ELIC, VTM and MS-ILLM with fast decoding. Our approach achieves comparable FID to previous training-free codec with significantly less decoding time. And our approach still outperforms previous conditional generative model based codecs such as HiFiC and MS-ILLM in terms of FID. The source code is provided in the supplementary material.

eess.IV↗
arXiv2025

High-efficiency WSe$_2$ photovoltaics enabled by ultra-clean van der Waals contacts

Layered transition metal dichalcogenide semiconductors are interesting for photovoltaics owing to their high solar absorbance and efficient carrier diffusion. Tungsten diselenide (WSe$_2$), in particular, has emerged as a promising solar cell absorber. However, defective metal-semiconductor interfaces have restricted the power conversion efficiency (PCE) to approximately 6%. Here we report WSe$_2$ photovoltaics with a record-high PCE of approximately 11% enabled by ultra-clean indium/gold (In/Au) van der Waals (vdW) contacts. Using grid-patterned top vdW electrodes, we demonstrate near-ideal diodes with a record-high on/off ratio of $1.0\times 10^9$. Open-circuit voltage (VOC) of 571 +/- 9 mV, record-high short-circuit current density (JSC) of 27.19 +/- 0.45 mA cm$^{-2}$ -- approaching the theoretical limit (34.5 mA cm$^{-2}$) -- and fill factor of 69.2 +/- 0.7% resulting in PCE of 10.8 +/- 0.2% under 1-Sun illumination on large active area (approximately 0.13x0.13 mm$^2$) devices have been realised. The excellent device performance is consistent with the high external quantum efficiency (up to approximately 93%) measured across a broad spectral range of 500-830 nm. Our results suggest that ultra-clean vdW contacts on WSe$_2$ enable high-efficiency photovoltaics and form the foundation for further optimisation.

cond-mat.mtrl-sci↗
arXiv2025

Large Scale Manufacture of Phase Pure Two-Dimensional Metallic MoS2 Nanosheets

Metallic monolayered [or two - dimensional (2D)] MoS2 nanosheets show tremendous promise for energy storage and catalysis applications. However, state-of-the-art chemical exfoliation methods require > 48 hours to produce milligrams of metallic 2D MoS2. Further, chemically exfoliated MoS2 nanosheets are a mixture of metallic (1T or 1T prime 50% to 70%) and semiconducting (2H 30% to 50%) phases. Here, we demonstrate large-scale and rapid (>600 grams per hour) production of purely metallic phase 2D MoS2 (and WS2, MoSe2) nanosheets using microwave irradiation. Atomic resolution imaging shows 1T or 1T prime metallic phase in basal plane - consistent with close to 100% metallic phase concentration measured by X-ray photoelectron spectroscopy. The high 1T phase concentration results in the highest exchange current density of 0.175 plus-minus 0.03 mA cm-2 and among the lowest Tafel slopes (39 - 43 mV dec-1) measured to date for the hydrogen evolution reaction. In supercapacitors and lithium-sulfur pouch cell batteries, record-high volumetric capacitance of 753 plus-minus 3.6 F cm-3 and specific capacity of 1245 plus-minus 16 mAh g-1 (at exceptionally low electrolyte to sulfur ratio = 2 microlitre g-1), respectively, are obtained. Our method provides a practical pathway for producing high quality purely metallic phase 2D materials for high performance energy devices.

cond-mat.mtrl-sci↗
arXiv2025

Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance

As the fundamental capability behind decision-making in finance, financial reasoning poses distinct challenges for LLMs. Although reinforcement learning (RL) have boosted generic reasoning, the progress in finance is hindered by the absence of empirical study of building effective financial chain-of-thought (CoT) corpus, a systematic comparison of different RL methods, and comprehensive benchmarks. To address these gaps, we introduce FinCoT, the first open high-fidelity CoT corpus for finance, distilled from seven QA datasets by a novel three-stage pipeline that incorporates domain supervision, iterative LLM refinement, and difficulty-aware filtering. Based on FinCoT, we develop Fin-o1, the first open financial reasoning models trained via supervised fine-tuning and GRPO-based RL. Our models outperform existing financial reasoning models and SOTA general models such as GPT-o1, DeepSeek-R1, and GPT-4.5. We also investigate the effectiveness of three different RL methods in improving domain-specific reasoning, offering the first such empirical study. We finally propose FinReason, the first financial reasoning benchmark covering multi-table analysis, long-context reasoning, and equation-based tasks, and evaluate 29 LLMs. Our extensive experiments reveal general reasoning models excel on standard benchmarks yet exhibit obvious performance degradation in financial contexts; even finance-tuned models like Dianjin-R1 and FinR1 degrade on lengthy documents. In contrast, our Fin-o1 models consistently outperform their backbones and larger GPT-o1 and DeepSeek-R1, confirming the effectiveness of our data building and model training strategy. Our study further shows that GRPO yields reliable gains whereas PPO and DPO do not, highlighting the need for targeted data and optimisation rather than scale alone.

cs.CL↗
arXiv2025

Zero-energy band observation in an interfacial chalcogen-organic network

Structurally-defined molecule-based lattices such as covalent organic or metal-organic networks on substrates, have emerged as highly tunable, modular platforms for two-dimensional band structure engineering. The ability to grow molecule-based lattices on diverse platforms, such as metal dichalcogenides, would further enable band structure tuning and alignment to the Fermi level, which is crucial for the exploration and design of quantum matter. In this work, we study the emergence of a zero-energy band in a triarylamine-based network on semiconducting 1T-TiSe2 at low temperatures, by means of scanning probe microscopy and photoemission spectroscopy, together with density-functional theory. Hybridization between the position-selective nitrogens and selenium p-states results in CN-Se interfacial coordination motifs, leading to a hybrid molecule-semiconductor band at the Fermi level. Our findings introduce chalcogen-organic networks and showcase an approach for the engineering of organic-inorganic quantum matter.

physics.chem-ph↗
arXiv2025

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding

While Large Language Models (LLMs) support long contexts, they struggle with performance degradation within the context window. Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored. From the decoding perspective, we identify the Posterior Salience Attenuation (PSA) phenomenon, where the salience ratio correlates with long-text performance degradation. Notably, despite the attenuation, gold tokens still occupy high-ranking positions in the decoding space. Motivated by it, we propose the training-free Positional Contrastive Decoding (PCD) that contrasts the logits derived from long-aware attention with those from designed local-aware attention, enabling the model to focus on the gains introduced by large-scale short-to-long training. Through the analysis of long-term decay simulation, we demonstrate that PCD effectively alleviates attention score degradation. Experimental results show that PCD achieves state-of-the-art performance on long-context benchmarks.

cs.CL↗
arXiv2025

Enhanced channel estimation for near-field IRS-aided multi-user MIMO system via a large deep residual network

In this paper, the channel estimation (CE) of intelligent reflecting surface-aided near-field (NF) multi-user communication is investigated. Initially, the least square (LS) estimator and minimum mean square error (MMSE) estimator for the estimated channel are designed, their mean square errors (MSEs) are derived, and the Cramer-Rao lower bound (CRLB) is derived to serve as a benchmark for performance evaluation. Subsequently, in view of the fact that the NF channel model is more sensitive to distance variations compared to the far-field model, this leads to pronounced discrepancies in the user channel characteristics in different regions. To effectively capture and utilize these diverse channel features, users are initially divided into distinct regions predicated on pivotal parameters, such as channel angle and distance. Correspondingly, a user region classifier based on convolutional neural networks is designed. Then, to fully harness the potential of deep residual networks (DRNs) in denoising, the aforementioned CE problem is reconceptualized as a denoising task, and a DRN-driven single region NF CE network, named SR-DRN-NFCE, is proposed. In addition, by integrating SR-DRN-NFCE networks corresponding to different regions and conducting joint training in a federated learning (FL) manner, a new network is obtained, named FL-DRN-NFCE. Simulation results demonstrate that the proposed FL-DRN-NFCE network outperforms LS, MMSE, and no residual connections in terms of MSE, and the proposed FL-DRN-NFCE method has higher CE accuracy than the SR-DRN-NFCE method.

eess.SP↗
arXiv2025

Smartphone-integrated RPA-CRISPR-Cas12a Detection System with Microneedle Sampling for Point-of-Care Diagnosis of Potato Late Blight in Early Stage

Potato late blight, caused by the oomycete pathogen Phytophthora infestans, is one of the most devastating diseases affecting potato crops in the history. Although conventional detection methods of plant diseases such as PCR and LAMP are highly sensitive and specific, they rely on bulky and expensive laboratory equipment and involve complex operations, making them impracticable for point-of care diagnosis in the field. Here in this study, we report a portable RPA-CRISPR based diagnosis system for plant disease, integrating smartphone for acquisition and analysis of fluorescent images. A polyvinyl alcohol (PVA) microneedle patch was employed for sample extraction on the plant leaves within one minute, the DNA extraction efficiency achieved 56 ug/mg, which is approximately 3 times to the traditional CTAB methods (18 ug/mg). The system of RPA-CRISPR-Cas12a isothermal assay was established to specifically target P. infestans with no cross-reactivity observed against closely-related species (P. sojae, P. capsici). The system demonstrated a detection limit of 2 pg/uL for P. infestans genomic DNA, offering sensitivity comparable to that of benchtop laboratory equipment. The system demonstrates the early-stage diagnosis capability by achieving a approximately 80% and 100% detection rate on the third and fourth day post-inoculation respectively, before visible symptoms observed on the leaves. The smartphone-based "sample-to-result" system decouples the limitations of traditional methods that rely heavily on specialized equipment, offering a promising way for early-stage plant disease detection and control in the field.

q-bio.QM↗
arXiv2025

Geodesic-based Predictive Shape Modeling of the Right Ventricle in Patients with Hypoplastic Left Heart Syndrome

Hypoplastic left heart syndrome (HLHS) is characterized by severe underdevelopment of left ventricle requiring staged surgical reconstruction (stages) to allow the right ventricle (RV) alone to support the circulation. In this setting changes in RV size and shape over time reflect adaptations to single-ventricle physiology, dysfunction of the associated tricuspid valve (TV), and are associated with circulatory failure. As such, an accurate prediction of the RV shape of a patient would inform understanding of both RV and TV failure, as well as clinical prognosis and associated decision making. We present a geodesic-based predictive shape modeling framework applied a cohort of RVs obtained from 15 HLHS patients at three individual time points. Reasonable predictions on stage 1 RV shapes can generated using pre-stage 1 RV shapes and two predictors from prior clinical and demographic measures. Our results demonstrate the future potential for a data-driven method to predict how the morphology of the RV of an individual patient will change in size and shape over time. Future studies will seek to expand the training sample size and integrate more comprehensive demographic and morphological data into the proposed predictive model.

physics.med-ph↗
arXiv2025

Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications

Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \textit{Open-FinLLMs}, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data, excelling in zero-shot, few-shot, and fine-tuning settings. The suite includes FinLLaMA, pre-trained on a comprehensive 52-billion-token corpus; FinLLaMA-Instruct, fine-tuned with 573K financial instructions; and FinLLaVA, enhanced with 1.43M multimodal tuning pairs for strong cross-modal reasoning. We comprehensively evaluate Open-FinLLMs across 14 financial tasks, 30 datasets, and 4 multimodal tasks in zero-shot, few-shot, and supervised fine-tuning settings, introducing two new multimodal evaluation datasets. Our results show that Open-FinLLMs outperforms afvanced financial and general LLMs such as GPT-4, across financial NLP, decision-making, and multi-modal tasks, highlighting their potential to tackle real-world challenges. To foster innovation and collaboration across academia and industry, we release all codes (https://anonymous.4open.science/r/PIXIU2-0D70/B1D7/LICENSE) and models under OSI-approved licenses.

cs.CL↗
arXiv2025

RKEFino1: A Regulation Knowledge-Enhanced Large Language Model

Recent advances in large language models (LLMs) hold great promise for financial applications but introduce critical accuracy and compliance challenges in Digital Regulatory Reporting (DRR). To address these issues, we propose RKEFino1, a regulation knowledge-enhanced financial reasoning model built upon Fino1, fine-tuned with domain knowledge from XBRL, CDM, and MOF. We formulate two QA tasks-knowledge-based and mathematical reasoning-and introduce a novel Numerical NER task covering financial entities in both sentences and tables. Experimental results demonstrate the effectiveness and generalization capacity of RKEFino1 in compliance-critical financial tasks. We have released our model on Hugging Face.

cs.CL↗
arXiv2025

Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems

Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by incorporating external retrieved information, mitigating issues such as hallucination and outdated knowledge. However, RAG systems are highly sensitive to retrieval noise prevalent in real-world scenarios. Existing benchmarks fail to emulate the complex and heterogeneous noise distributions encountered in real-world retrieval environments, undermining reliable robustness assessment. In this paper, we define four categories of retrieval noise based on linguistic properties and noise characteristics, aiming to reflect the heterogeneity of noise in real-world scenarios. Building on this, we introduce Magic Mushroom, a benchmark for replicating "magic mushroom" noise: contexts that appear relevant on the surface but covertly mislead RAG systems. Magic Mushroom comprises 7,468 single-hop and 3,925 multi-hop question-answer pairs. More importantly, Magic Mushroom enables researchers to flexibly configure combinations of retrieval noise according to specific research objectives or application scenarios, allowing for highly controlled evaluation setups. We evaluate LLM generators of varying parameter scales and classic RAG denoising strategies under diverse noise distributions to investigate their performance dynamics during progressive noise encroachment. Our analysis reveals that both generators and denoising strategies have significant room for improvement and exhibit extreme sensitivity to noise distributions. Magic Mushroom emerges as a promising tool for evaluating and advancing noise-robust RAG systems, accelerating their widespread deployment in real-world applications. The Magic Mushroom benchmark is available at https://drive.google.com/file/d/1aP5kyPuk4L-L_uoI6T9UhxuTyt8oMqjT/view?usp=sharing.

cs.CL↗
arXiv2025

UniPTMs: The First Unified Multi-type PTM Site Prediction Model via Master-Slave Architecture-Based Multi-Stage Fusion Strategy and Hierarchical Contrastive Loss

As a core mechanism of epigenetic regulation in eukaryotes, protein post-translational modifications (PTMs) require precise prediction to decipher dynamic life activity networks. To address the limitations of existing deep learning models in cross-modal feature fusion, domain generalization, and architectural optimization, this study proposes UniPTMs: the first unified framework for multi-type PTM prediction. The framework innovatively establishes a "Master-Slave" dual-path collaborative architecture: The master path dynamically integrates high-dimensional representations of protein sequences, structures, and evolutionary information through a Bidirectional Gated Cross-Attention (BGCA) module, while the slave path optimizes feature discrepancies and recalibration between structural and traditional features using a Low-Dimensional Fusion Network (LDFN). Complemented by a Multi-scale Adaptive convolutional Pyramid (MACP) for capturing local feature patterns and a Bidirectional Hierarchical Gated Fusion Network (BHGFN) enabling multi-level feature integration across paths, the framework employs a Hierarchical Dynamic Weighting Fusion (HDWF) mechanism to intelligently aggregate multimodal features. Enhanced by a novel Hierarchical Contrastive loss function for feature consistency optimization, UniPTMs demonstrates significant performance improvements (3.2%-11.4% MCC and 4.2%-14.3% AP increases) over state-of-the-art models across five modification types and transcends the Single-Type Prediction Paradigm. To strike a balance between model complexity and performance, we have also developed a lightweight variant named UniPTMs-mini.

cs.LG↗
arXiv2025

Self-consistent theory of $2\times2$ pair density waves in kagome superconductors

Pair density wave (PDW) is an intriguing quantum matter proposed in the frontier of condensed matter physics. However, the existence of PDW in microscopic models has been rare. In this work, we obtain, by Ginzburg-Landau arguments and self-consistent mean field theory, novel $2a_0\times2a_0$ PDW on the kagome lattice arising from attractive on-bond pairing interactions and the distinct Bloch wave functions near the p-type van Hove singularity. The PDW state carrying three independent wave-vectors, the so-called 3Q PDW, is nodeless and falls into two topological classes characterized by the Chern number $C = 0$ or $C = \pm2$. The chiral ($C=\pm2$) PDW state presents a rare case of interaction driven topological quantum state without the requirement of spin-orbit coupling. Finally, we analyze the stabilities and properties of these PDWs intertwining with charge orders, and discuss the relevance of our minimal model to recent experimental observations in kagome superconductors. Our theory not only elucidates the driving force of the chiral PDW, but also predicts strongly anisotropic superconducting gap structure in the momentum space and quantized transverse thermal conductivity that can be tested in future experiments.

cond-mat.supr-con↗