arXiv subjects

Yuanyuan Wang

Publications and source records attributed to Yuanyuan Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Revealing Neurocognitive and Behavioral Patterns by Unsupervised Manifold Learning from Dynamic Brain Data

Dynamic brain data, teeming with biological and functional insights, are becoming increasingly accessible through advanced measurements, providing a gateway to understanding the inner workings of the brain in living subjects. However, the vast size and intricate complexity of the data also pose a daunting challenge in reliably extracting meaningful information across various data sources. This paper introduces a generalizable unsupervised deep manifold learning for exploration of neurocognitive and behavioral patterns. Unlike existing methods that extract patterns directly from the input data as in the existing methods, the proposed Brain-dynamic Convolutional-Network-based Embedding (BCNE) seeks to capture the brain-state trajectories by deciphering the temporospatial correlations within the data and subsequently applying manifold learning to this correlative representation. The performance of BCNE is showcased through the analysis of several important dynamic brain datasets. The results, both visual and quantitative, reveal a diverse array of intriguing and interpretable patterns. BCNE effectively delineates scene transitions, underscores the involvement of different brain regions in memory and narrative processing, distinguishes various stages of dynamic learning processes, and identifies differences between active and passive behaviors. BCNE provides an effective tool for exploring general neuroscience inquiries or individual-specific patterns.

q-bio.NC↗

arXiv2025

ABench-Physics: Benchmarking Physical Reasoning in LLMs via High-Difficulty and Dynamic Physics Problems

Large Language Models (LLMs) have shown impressive performance in domains such as mathematics and programming, yet their capabilities in physics remain underexplored and poorly understood. Physics poses unique challenges that demand not only precise computation but also deep conceptual understanding and physical modeling skills. Existing benchmarks often fall short due to limited difficulty, multiple-choice formats, and static evaluation settings that fail to capture physical modeling ability. In this paper, we introduce ABench-Physics, a novel benchmark designed to rigorously evaluate LLMs' physical reasoning and generalization capabilities. ABench-Physics consists of two components: Phy_A, a static set of 400 graduate- or Olympiad-level problems; and Phy_B, a dynamic subset of 100 problems equipped with an automatic variation engine to test model robustness across changing conditions. All questions require precise numerical answers, with strict formatting and tolerance constraints. Our evaluation of several state-of-the-art LLMs reveals substantial performance gaps, highlighting persistent limitations in physical reasoning, especially in generalization to dynamic variants. ABench-Physics provides a challenging and diagnostic framework for advancing scientific reasoning in LLMs.

cs.LG↗

arXiv2025

VAP-Diffusion: Enriching Descriptions with MLLMs for Enhanced Medical Image Generation

As the appearance of medical images is influenced by multiple underlying factors, generative models require rich attribute information beyond labels to produce realistic and diverse images. For instance, generating an image of skin lesion with specific patterns demands descriptions that go beyond diagnosis, such as shape, size, texture, and color. However, such detailed descriptions are not always accessible. To address this, we explore a framework, termed Visual Attribute Prompts (VAP)-Diffusion, to leverage external knowledge from pre-trained Multi-modal Large Language Models (MLLMs) to improve the quality and diversity of medical image generation. First, to derive descriptions from MLLMs without hallucination, we design a series of prompts following Chain-of-Thoughts for common medical imaging tasks, including dermatologic, colorectal, and chest X-ray images. Generated descriptions are utilized during training and stored across different categories. During testing, descriptions are randomly retrieved from the corresponding category for inference. Moreover, to make the generator robust to unseen combination of descriptions at the test time, we propose a Prototype Condition Mechanism that restricts test embeddings to be similar to those from training. Experiments on three common types of medical imaging across four datasets verify the effectiveness of VAP-Diffusion.

cs.CV↗

arXiv2025

GlobalBuildingAtlas: An Open Global and Complete Dataset of Building Polygons, Heights and LoD1 3D Models

We introduce GlobalBuildingAtlas, a publicly available dataset providing global and complete coverage of building polygons, heights and Level of Detail 1 (LoD1) 3D building models. This is the first open dataset to offer high quality, consistent, and complete building data in 2D and 3D form at the individual building level on a global scale. Towards this dataset, we developed machine learning-based pipelines to derive building polygons and heights (called GBA.Height) from global PlanetScope satellite data, respectively. Also a quality-based fusion strategy was employed to generate higher-quality polygons (called GBA.Polygon) based on existing open building polygons, including our own derived one. With more than 2.75 billion buildings worldwide, GBA.Polygon surpasses the most comprehensive database to date by more than 1 billion buildings. GBA.Height offers the most detailed and accurate global 3D building height maps to date, achieving a spatial resolution of 3x3 meters-30 times finer than previous global products (90 m), enabling a high-resolution and reliable analysis of building volumes at both local and global scales. Finally, we generated a global LoD1 building model (called GBA.LoD1) from the resulting GBA.Polygon and GBA.Height. GBA.LoD1 represents the first complete global LoD1 building models, including 2.68 billion building instances with predicted heights, i.e., with a height completeness of more than 97%, achieving RMSEs ranging from 1.5 m to 8.9 m across different continents. With its height accuracy, comprehensive global coverage and rich spatial details, GlobalBuildingAltas offers novel insights on the status quo of global buildings, which unlocks unprecedented geospatial analysis possibilities, as showcased by a better illustration of where people live and a more comprehensive monitoring of the progress on the 11th Sustainable Development Goal of the United Nations.

cs.CV↗

arXiv2025

Implications of electromagnetic scale anomaly to QCD chiral phase transition in smaller quark mass regime: $T_{\mathrm{pc}}$ does not drop with eB

The decrease of the chiral pseudocritical temperature $T_{\mathrm{pc}}$ with an applied strong magnetic field has been extensively investigated by various QCD low-energy effective models and lattice QCD at physical point. We find that this decreasing feature may not hold in the case with a weak magnetic field and still depends on quark masses: when the quark masses get smaller, $T_{\mathrm{pc}}$ turns to increase with the weak magnetic field. This happens due to the significant electromagnetic-scale anomaly contribution in the thermomagnetic medium. We demonstrate this salient feature by employing the Nambu-Jona-Lasinio model with 2 + 1 quark flavors including the electromagnetic-scale anomaly contribution. We observe that at $(m_{0c}, m_{sc}) \simeq (2, 20) \mathrm{MeV}$ for the isospin symmetric mass for up and down quarks, $m_0$, and the strange quark mass, $m_s$, $T_{\mathrm{pc}}$ decreases with the magnetic field if the quark masses exceed the critical values, and increases as the quark masses become smaller. Related cosmological implications, arising when the supercooled electroweak phase transition or dark QCD cosmological phase transition is considered along with a primordial magnetic field, are also briefly addressed.

hep-ph↗

arXiv2025

Paving the way to carbon neutrality: Evaluating the decarbonization of residential building electrification worldwide

In the context of increasing global climate change, decarbonizing the residential building sector is crucial for sustainable development. This study aims to analyze the role of various influencing factors in carbon intensity changes using the decomposing structural decomposition (DSD) to assess and compare the potential and effectiveness of electrifying end-use activities during the operational phase of residential buildings worldwide for decarbonization. The results show that (1) while the electrification rate varied in its impact on emissions across different countries and regions, the overall increase in electrification contributed to higher carbon intensity. In contrast, changes in the emission factor of electricity generally made a positive contribution to emission reduction globally. (2) The global electrification level has significantly increased, with the electrification rate rising from 29.9% in 2000 to 40.1% in 2021. A 39.8% increase in the electricity-related carbon emissions of global residential buildings was observed, increasing from 1452 MtCO2 to 2032 MtCO2, 2000-2021. (3) From 2000 to 2021, electrification of space heating was the main contributor to carbon reduction, whereas the contributions of electrification to cooling and lighting were relatively limited. Emission reductions from appliances and others remained stable. The electrification of water heating and cooking had varying effects on emission reductions in different countries. Furthermore, this study proposes a series of electrification decarbonization strategies. Overall, this study analyzes and contrasts decarbonization efforts from building electrification at the global and regional levels, explores the key motivations behind these efforts to aid national net-zero emission targets and accelerate the transition of the global residential building sector toward a carbon-neutral future.

physics.soc-ph↗

arXiv2025

ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling

Recent advancements in audio language models have underscored the pivotal role of audio tokenization, which converts audio signals into discrete tokens, thereby facilitating the application of language model architectures to the audio domain. In this study, we introduce ALMTokenizer, a novel low-bitrate and semantically rich audio codec tokenizer for audio language models. Prior methods, such as Encodec, typically encode individual audio frames into discrete tokens without considering the use of context information across frames. Unlike these methods, we introduce a novel query-based compression strategy to capture holistic information with a set of learnable query tokens by explicitly modeling the context information across frames. This design not only enables the codec model to capture more semantic information but also encodes the audio signal with fewer token sequences. Additionally, to enhance the semantic information in audio codec models, we introduce the following: (1) A masked autoencoder (MAE) loss, (2) Vector quantization based on semantic priors, and (3) An autoregressive (AR) prediction loss. As a result, ALMTokenizer achieves competitive reconstruction performance relative to state-of-the-art approaches while operating at a lower bitrate. Within the same audio language model framework, ALMTokenizer outperforms previous tokenizers in audio understanding and generation tasks.

cs.SD↗

arXiv2025

HarmonySeg: Tubular Structure Segmentation with Deep-Shallow Feature Fusion and Growth-Suppression Balanced Loss

Accurate segmentation of tubular structures in medical images, such as vessels and airway trees, is crucial for computer-aided diagnosis, radiotherapy, and surgical planning. However, significant challenges exist in algorithm design when faced with diverse sizes, complex topologies, and (often) incomplete data annotation of these structures. We address these difficulties by proposing a new tubular structure segmentation framework named HarmonySeg. First, we design a deep-to-shallow decoder network featuring flexible convolution blocks with varying receptive fields, which enables the model to effectively adapt to tubular structures of different scales. Second, to highlight potential anatomical regions and improve the recall of small tubular structures, we incorporate vesselness maps as auxiliary information. These maps are aligned with image features through a shallow-and-deep fusion module, which simultaneously eliminates unreasonable candidates to maintain high precision. Finally, we introduce a topology-preserving loss function that leverages contextual and shape priors to balance the growth and suppression of tubular structures, which also allows the model to handle low-quality and incomplete annotations. Extensive quantitative experiments are conducted on four public datasets. The results show that our model can accurately segment 2D and 3D tubular structures and outperform existing state-of-the-art methods. External validation on a private dataset also demonstrates good generalizability.

eess.IV↗

arXiv2025

AudioComposer: Towards Fine-grained Audio Generation with Natural Language Descriptions

Current Text-to-audio (TTA) models mainly use coarse text descriptions as inputs to generate audio, which hinders models from generating audio with fine-grained control of content and style. Some studies try to improve the granularity by incorporating additional frame-level conditions or control networks. However, this usually leads to complex system design and difficulties due to the requirement for reference frame-level conditions. To address these challenges, we propose AudioComposer, a novel TTA generation framework that relies solely on natural language descriptions (NLDs) to provide both content specification and style control information. To further enhance audio generative modeling, we employ flow-based diffusion transformers with the cross-attention mechanism to incorporate text descriptions effectively into audio generation processes, which can not only simultaneously consider the content and style information in the text inputs, but also accelerate generation compared to other architectures. Furthermore, we propose a novel and comprehensive automatic data simulation pipeline to construct data with fine-grained text descriptions, which significantly alleviates the problem of data scarcity in the area. Experiments demonstrate the effectiveness of our framework using solely NLDs as inputs for content specification and style control. The generation quality and controllability surpass state-of-the-art TTA models, even with a smaller model size.

eess.AS↗

arXiv2025

UniSep: Universal Target Audio Separation with Language Models at Scale

We propose Universal target audio Separation (UniSep), addressing the separation task on arbitrary mixtures of different types of audio. Distinguished from previous studies, UniSep is performed on unlimited source domains and unlimited source numbers. We formulate the separation task as a sequence-to-sequence problem, and a large language model (LLM) is used to model the audio sequence in the discrete latent space, leveraging the power of LLM in handling complex mixture audios with large-scale data. Moreover, a novel pre-training strategy is proposed to utilize audio-only data, which reduces the efforts of large-scale data simulation and enhances the ability of LLMs to understand the consistency and correlation of information within audio sequences. We also demonstrate the effectiveness of scaling datasets in an audio separation task: we use large-scale data (36.5k hours), including speech, music, and sound, to train a universal target audio separation model that is not limited to a specific domain. Experiments show that UniSep achieves competitive subjective and objective evaluation results compared with single-task models.

cs.SD↗

arXiv2025

First-order CP phase transition in two-flavor QCD at $θ= π$ under electromagnetic scale anomaly via a Nambu-Jona-Lasinio description

We discuss the thermal CP phase transition in QCD at $θ=π$ under a weak magnetic field background, where the electromagnetic scale anomaly gets significant. To explicitize, we work on a two-flavor Nambu-Jona-Lasinio model at $θ=π$ in the mean field approximation, including the electromagnetic-scale anomaly term. We find that the thermal CP phase transition becomes first order and the strength of the first order gets more prominent as the magnetic field increases. The associated potential barrier is thermally created by the electromagnetic scale anomaly and gives rise to criticality due to the induced potential of a non-perturbative form $\sim \frac{|eB|^3}{f_π} \frac{|P|}{P^2 + m_0^2}$, where $eB$ denotes the magnetic field strength; $P$ the CP order parameter, and $m_0$ the isospin-symmetric current-quark mass.

hep-ph↗

arXiv2025

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two differently sized MoE large language models (LLMs), namely Ling-Lite and Ling-Plus (referred to as "Bailing" in Chinese, spelled Bǎilíng in Pinyin). Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters. Both models exhibit comparable performance to leading industry benchmarks. This report offers actionable insights to improve the efficiency and accessibility of AI development in resource-constrained settings, promoting more scalable and sustainable technologies. Specifically, to reduce training costs for large-scale MoE models, we propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency. Additionally, leveraging high-quality data generated from knowledge graphs, our models demonstrate superior capabilities in tool use compared to other models. Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models. Compared to high-performance devices, utilizing a lower-specification hardware system during the pre-training phase demonstrates significant cost savings, reducing computing costs by approximately 20%. The models can be accessed at https://huggingface.co/inclusionAI.

cs.LG↗

arXiv2025

Idempotence and Perceptual Image Compression

Idempotence is the stability of image codec to re-compression. At the first glance, it is unrelated to perceptual image compression. However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec. Based on this newfound equivalence, we propose a new paradigm of perceptual image codec by inverting unconditional generative model with idempotence constraints. Our codec is theoretically equivalent to conditional generative codec, and it does not require training new models. Instead, it only requires a pre-trained mean-square-error codec and unconditional generative model. Empirically, we show that our proposed approach outperforms state-of-the-art methods such as HiFiC and ILLM, in terms of Fréchet Inception Distance (FID). The source code is provided in https://github.com/tongdaxu/Idempotence-and-Perceptual-Image-Compression.

eess.IV↗

arXiv2025

An ab initio dataset of size-dependent effective thermal conductivity for advanced technology transistors

As the size of transistors shrinks and power density increases, thermal simulation has become an indispensable part of the device design procedure. However, existing works for advanced technology transistors use simplified empirical models to calculate effective thermal conductivity in the simulations. In this work, we present a dataset of size-dependent effective thermal conductivity with electron and phonon properties extracted from ab initio computations. Absolute in-plane and cross-plane thermal conductivity data of eight semiconducting materials (Si, Ge, GaN, AlN, 4H-SiC, GaAs, InAs, BAs) and four metallic materials (Al, W, TiN, Ti) with the characteristic length ranging from 5 to 50 nanometers have been provided. Besides the absolute value, normalized effective thermal conductivity is also given, in case it needs to be used with updated bulk thermal conductivity in the future. The dataset presented in this paper are openly available at https://doi.org/10.57760/sciencedb.j00113.00154.

cond-mat.mtrl-sci↗

arXiv2025

Is Your Autonomous Vehicle Safe? Understanding the Threat of Electromagnetic Signal Injection Attacks on Traffic Scene Perception

Autonomous vehicles rely on camera-based perception systems to comprehend their driving environment and make crucial decisions, thereby ensuring vehicles to steer safely. However, a significant threat known as Electromagnetic Signal Injection Attacks (ESIA) can distort the images captured by these cameras, leading to incorrect AI decisions and potentially compromising the safety of autonomous vehicles. Despite the serious implications of ESIA, there is limited understanding of its impacts on the robustness of AI models across various and complex driving scenarios. To address this gap, our research analyzes the performance of different models under ESIA, revealing their vulnerabilities to the attacks. Moreover, due to the challenges in obtaining real-world attack data, we develop a novel ESIA simulation method and generate a simulated attack dataset for different driving scenarios. Our research provides a comprehensive simulation and evaluation framework, aiming to enhance the development of more robust AI models and secure intelligent systems, ultimately contributing to the advancement of safer and more reliable technology across various fields.

cs.CR↗

arXiv2024

How Certain are Uncertainty Estimates? Three Novel Earth Observation Datasets for Benchmarking Uncertainty Quantification in Machine Learning

Uncertainty quantification (UQ) is essential for assessing the reliability of Earth observation (EO) products. However, the extensive use of machine learning models in EO introduces an additional layer of complexity, as those models themselves are inherently uncertain. While various UQ methods do exist for machine learning models, their performance on EO datasets remains largely unevaluated. A key challenge in the community is the absence of the ground truth for uncertainty, i.e. how certain the uncertainty estimates are, apart from the labels for the image/signal. This article fills this gap by introducing three benchmark datasets specifically designed for UQ in EO machine learning models. These datasets address three common problem types in EO: regression, image segmentation, and scene classification. They enable a transparent comparison of different UQ methods for EO machine learning models. We describe the creation and characteristics of each dataset, including data sources, preprocessing steps, and label generation, with a particular focus on calculating the reference uncertainty. We also showcase baseline performance of several machine learning models on each dataset, highlighting the utility of these benchmarks for model development and comparison. Overall, this article offers a valuable resource for researchers and practitioners working in artificial intelligence for EO, promoting a more accurate and reliable quality measure of the outputs of machine learning models. The dataset and code are accessible via https://gitlab.lrz.de/ai4eo/WG_Uncertainty.

cs.LG↗

arXiv2024

SAM-MPA: Applying SAM to Few-shot Medical Image Segmentation using Mask Propagation and Auto-prompting

Medical image segmentation often faces the challenge of prohibitively expensive annotation costs. While few-shot learning offers a promising solution to alleviate this burden, conventional approaches still rely heavily on pre-training with large volumes of labeled data from known categories. To address this issue, we propose leveraging the Segment Anything Model (SAM), pre-trained on over 1 billion masks, thus circumventing the need for extensive domain-specific annotated data. In light of this, we developed SAM-MPA, an innovative SAM-based framework for few-shot medical image segmentation using Mask Propagation-based Auto-prompting. Initially, we employ k-centroid clustering to select the most representative examples for labelling to construct the support set. These annotated examples are registered to other images yielding deformation fields that facilitate the propagation of the mask knowledge to obtain coarse masks across the dataset. Subsequently, we automatically generate visual prompts based on the region and boundary expansion of the coarse mask, including points, box and a coarse mask. Finally, we can obtain the segmentation predictions by inputting these prompts into SAM and refine the results by post refinement module. We validate the performance of the proposed framework through extensive experiments conducted on two medical image datasets with different modalities. Our method achieves Dices of 74.53%, 94.36% on Breast US, Chest X-ray, respectively. Experimental results substantiate that SAM-MPA yields high-accuracy segmentations within 10 labeled examples, outperforming other state-of-the-art few-shot auto-segmentation methods. Our method enables the customization of SAM for any medical image dataset with a small number of labeled examples.

cs.CV↗

arXiv2024

The Fairness of Maximum Nash Social Welfare Under Matroid Constraints and Beyond

We study the problem of fair allocation of a set of indivisible items among agents with additive valuations, under matroid constraints and two generalizations: $p$-extendible system and independence system constraints. The objective is to find fair and efficient allocations in which the subset of items assigned to every agent satisfies the given constraint. We focus on a common fairness notion of envy-freeness up to one item (EF1) and a well-known efficient (and fair) notion of the maximum Nash social welfare (Max-NSW). By using properties of matroids, we demonstrate that the Max-NSW allocation, implying Pareto optimality (PO), achieves a tight $1/2$-EF1 under matroid constraints. This result resolves an open question proposed in prior literature [26]. In particular, if agents have 2-valued ($\{1, a\}$) valuations, we prove that the Max-NSW allocation admits $\max\{1/a^2, 1/2\}$-EF1 and PO. Under strongly $p$-extendible system constraints, we show that the Max-NSW allocation guarantees $\max\{1/p, 1/4\}$-EF1 and PO for identical binary valuations. Indeed, the approximation of $1/4$ is the ratio for independence system constraints and additive valuations. Additionally, for lexicographic preferences, we study possibly feasible allocations other than Max-NSW admitting exactly EF1 and PO under the above constraints.

cs.GT↗