arXiv subjects

Zheng Wang

Publications and source records attributed to Zheng Wang.

At least 181 records · Page 10Linked to original sources

arXiv2025

FW-VTON: Flattening-and-Warping for Person-to-Person Virtual Try-on

Traditional virtual try-on methods primarily focus on the garment-to-person try-on task, which requires flat garment representations. In contrast, this paper introduces a novel approach to the person-to-person try-on task. Unlike the garment-to-person try-on task, the person-to-person task only involves two input images: one depicting the target person and the other showing the garment worn by a different individual. The goal is to generate a realistic combination of the target person with the desired garment. To this end, we propose Flattening-and-Warping Virtual Try-On (\textbf{FW-VTON}), a method that operates in three stages: (1) extracting the flattened garment image from the source image; (2) warping the garment to align with the target pose; and (3) integrating the warped garment seamlessly onto the target person. To overcome the challenges posed by the lack of high-quality datasets for this task, we introduce a new dataset specifically designed for person-to-person try-on scenarios. Experimental evaluations demonstrate that FW-VTON achieves state-of-the-art performance, with superior results in both qualitative and quantitative assessments, and also excels in garment extraction subtasks.

cs.CV↗

arXiv2025

Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfer

Animal motion embodies species-specific behavioral habits, making the transfer of motion across categories a critical yet complex task for applications in animation and virtual reality. Existing motion transfer methods, primarily focused on human motion, emphasize skeletal alignment (motion retargeting) or stylistic consistency (motion style transfer), often neglecting the preservation of distinct habitual behaviors in animals. To bridge this gap, we propose a novel habit-preserved motion transfer framework for cross-category animal motion. Built upon a generative framework, our model introduces a habit-preservation module with category-specific habit encoder, allowing it to learn motion priors that capture distinctive habitual characteristics. Furthermore, we integrate a large language model (LLM) to facilitate the motion transfer to previously unobserved species. To evaluate the effectiveness of our approach, we introduce the DeformingThings4D-skl dataset, a quadruped dataset with skeletal bindings, and conduct extensive experiments and quantitative analyses, which validate the superiority of our proposed model.

cs.CV↗

arXiv2025

BlueLM-2.5-3B Technical Report

We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reasoning capabilities. To the best of our knowledge, this is the first 3B-scale MLLM to support both thinking and non-thinking modes, while also enabling explicit control over thinking token budget. BlueLM-2.5-3B is developed through diversified data curation, key data resampling, hybrid heterogeneous reinforcement learning, and a high-performance training infrastructure. Our model achieves superior multimodal capacity while preserving competitive pure-text performance with only 2.9 billion parameters. We conduct comprehensive evaluations across a broad range of multimodal and text-only benchmarks. In thinking mode, BlueLM-2.5-3B achieves comparable performance to Qwen3-4B on text-only benchmarks, and trails the larger Kimi-VL-A3B-16B by only about 5% on average across multimodal evaluations. In non-thinking mode, it outperforms Qwen2.5-VL-3B on the majority of multimodal benchmarks. Additionally, BlueLM-2.5-3B exhibits exceptional data efficiency. All of the aforementioned performance is achieved with substantially less total training data than Qwen2.5-VL-3B and Qwen3-4B. We hope our work contributes to the advancement of high-performance, on-device MLLMs and provides meaningful insights to the research community.

cs.AI↗

arXiv2025

Convergent and divergent connectivity patterns of the arcuate fasciculus in macaques and humans

The organization and connectivity of the arcuate fasciculus (AF) in nonhuman primates remain contentious, especially concerning how its anatomy diverges from that of humans. Here, we combined cross-scale single-neuron tracing - using viral-based genetic labeling and fluorescence micro-optical sectioning tomography in macaques (n = 4; age 3 - 11 years) - with whole-brain tractography from 11.7T diffusion MRI. Complemented by spectral embedding analysis of 7.0T MRI in humans, we performed a comparative connectomic analysis of the AF across species. We demonstrate that the macaque AF originates in the temporal-parietal cortex, traverses the auditory cortex and parietal operculum, and projects into prefrontal regions. In contrast, the human AF exhibits greater expansion into the middle temporal gyrus and stronger prefrontal and parietal operculum connectivity - divergences quantified by Kullback-Leibler analysis that likely underpin the evolutionary specialization of human language networks. These interspecies differences - particularly the human AF's broader temporal integration and strengthened frontoparietal linkages - suggest a connectivity-based substrate for the emergence of advanced language processing unique to humans. Furthermore, our findings offer a neuroanatomical framework for understanding AF-related disorders such as aphasia and dyslexia, where aberrant connectivity disrupts language function.

q-bio.NC↗

arXiv2025

You Think, You ACT: The New Task of Arbitrary Text to Motion Generation

Text to Motion aims to generate human motions from texts. Existing settings rely on limited Action Texts that include action labels, which limits flexibility and practicability in scenarios difficult to describe directly. This paper extends limited Action Texts to arbitrary ones. Scene texts without explicit action labels can enhance the practicality of models in complex and diverse industries such as virtual human interaction, robot behavior generation, and film production, while also supporting the exploration of potential implicit behavior patterns. However, newly introduced Scene Texts may yield multiple reasonable output results, causing significant challenges in existing data, framework, and evaluation. To address this practical issue, we first create a new dataset HUMANML3D++ by extending texts of the largest existing dataset HUMANML3D. Secondly, we propose a simple yet effective framework that extracts action instructions from arbitrary texts and subsequently generates motions. Furthermore, we also benchmark this new setting with multi-solution metrics to address the inadequacies of existing single-solution metrics. Extensive experiments indicate that Text to Motion in this realistic setting is challenging, fostering new research in this practical direction.

cs.CV↗

arXiv2025

Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection

One-shot subset selection serves as an effective tool to reduce deep learning training costs by identifying an informative data subset based on the information extracted by an information extractor (IE). Traditional IEs, typically pre-trained on the target dataset, are inherently dataset-dependent. Foundation models (FMs) offer a promising alternative, potentially mitigating this limitation. This work investigates two key questions: (1) Can FM-based subset selection outperform traditional IE-based methods across diverse datasets? (2) Do all FMs perform equally well as IEs for subset selection? Extensive experiments uncovered surprising insights: FMs consistently outperform traditional IEs on fine-grained datasets, whereas their advantage diminishes on coarse-grained datasets with noisy labels. Motivated by these finding, we propose RAM-APL (RAnking Mean-Accuracy of Pseudo-class Labels), a method tailored for fine-grained image datasets. RAM-APL leverages multiple FMs to enhance subset selection by exploiting their complementary strengths. Our approach achieves state-of-the-art performance on fine-grained datasets, including Oxford-IIIT Pet, Food-101, and Caltech-UCSD Birds-200-2011.

cs.CV↗

arXiv2025

Rethinking Cancer Gene Identification through Graph Anomaly Analysis

Graph neural networks (GNNs) have shown promise in integrating protein-protein interaction (PPI) networks for identifying cancer genes in recent studies. However, due to the insufficient modeling of the biological information in PPI networks, more faithfully depiction of complex protein interaction patterns for cancer genes within the graph structure remains largely unexplored. This study takes a pioneering step toward bridging biological anomalies in protein interactions caused by cancer genes to statistical graph anomaly. We find a unique graph anomaly exhibited by cancer genes, namely weight heterogeneity, which manifests as significantly higher variance in edge weights of cancer gene nodes within the graph. Additionally, from the spectral perspective, we demonstrate that the weight heterogeneity could lead to the "flattening out" of spectral energy, with a concentration towards the extremes of the spectrum. Building on these insights, we propose the HIerarchical-Perspective Graph Neural Network (HIPGNN) that not only determines spectral energy distribution variations on the spectral perspective, but also perceives detailed protein interaction context on the spatial perspective. Extensive experiments are conducted on two reprocessed datasets STRINGdb and CPDB, and the experimental results demonstrate the superiority of HIPGNN.

cs.CE↗

arXiv2025

Optical Control of Fluorescence Spatial Hole Burning Effect in Monolayer WS2

Doping plays a crucial role in both electrical and optical properties of semiconductors. In this work, we report observation, as well as optical control, of fluorescence spatial hole burning effect in monolayer WS2. We demonstrate that the pronounced exciton-exciton annihilation process, in combination with the efficient capture of holes by intrinsic sulfur vacancy defects, induces significant photo-doping effect and eventually leads to fluorescence spatial hole burning. By means of a dual-beam pumping fluorescence imaging technique, we reveal that the recovery process of the spatial hole burning effect exhibits a double-exponential behavior. The fast recovery process originates from the release of trapped holes under the illumination of the probe beam, while the slow process corresponds to the re-adsorption of electronegative gas molecules. Surprisingly, our results demonstrate that the electronegative sulfur vacancies can achieve ultralong-term storage of holes. Moreover, both the release and the rate of release of holes can be fully controlled by laser irradiation. These findings demonstrate the great potential of transition metal dichalcogenides in the development of optically-control excitonic devices.

physics.optics↗

arXiv2025

Tensor Manipulation Unit (TMU): Reconfigurable, Near-Memory Tensor Manipulation for High-Throughput AI SoC

While recent advances in AI SoC design have focused heavily on accelerating tensor computation, the equally critical task of tensor manipulation, centered on high,volume data movement with minimal computation, remains underexplored. This work addresses that gap by introducing the Tensor Manipulation Unit (TMU), a reconfigurable, near-memory hardware block designed to efficiently execute data-movement-intensive operators. TMU manipulates long datastreams in a memory-to-memory fashion using a RISC-inspired execution model and a unified addressing abstraction, enabling broad support for both coarse- and fine-grained tensor transformations. Integrated alongside a TPU within a high-throughput AI SoC, the TMU leverages double buffering and output forwarding to improve pipeline utilization. Fabricated in SMIC 40nm technology, the TMU occupies only 0.019 mm2 while supporting over 10 representative tensor manipulation operators. Benchmarking shows that TMU alone achieves up to 1413 and 8.54 operator-level latency reduction compared to ARM A72 and NVIDIA Jetson TX2, respectively. When integrated with the in-house TPU, the complete system achieves a 34.6% reduction in end-to-end inference latency, demonstrating the effectiveness and scalability of reconfigurable tensor manipulation in modern AI SoCs.

cs.AR↗

arXiv2025

Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning

Masked autoencoding and generative pretraining have achieved remarkable success in computer vision and natural language processing, and more recently, they have been extended to the point cloud domain. Nevertheless, existing point cloud models suffer from the issue of information leakage due to the pre-sampling of center points, which leads to trivial proxy tasks for the models. These approaches primarily focus on local feature reconstruction, limiting their ability to capture global patterns within point clouds. In this paper, we argue that the reduced difficulty of pretext tasks hampers the model's capacity to learn expressive representations. To address these limitations, we introduce a novel solution called the Differentiable Center Sampling Network (DCS-Net). It tackles the information leakage problem by incorporating both global feature reconstruction and local feature reconstruction as non-trivial proxy tasks, enabling simultaneous learning of both the global and local patterns within point cloud. Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models and effectively addresses the issue of information leakage.

cs.CV↗

arXiv2025

From Swath to Full-Disc: Advancing Precipitation Retrieval with Multimodal Knowledge Expansion

Accurate near-real-time precipitation retrieval has been enhanced by satellite-based technologies. However, infrared-based algorithms have low accuracy due to weak relations with surface precipitation, whereas passive microwave and radar-based methods are more accurate but limited in range. This challenge motivates the Precipitation Retrieval Expansion (PRE) task, which aims to enable accurate, infrared-based full-disc precipitation retrievals beyond the scanning swath. We introduce Multimodal Knowledge Expansion, a two-stage pipeline with the proposed PRE-Net model. In the Swath-Distilling stage, PRE-Net transfers knowledge from a multimodal data integration model to an infrared-based model within the scanning swath via Coordinated Masking and Wavelet Enhancement (CoMWE). In the Full-Disc Adaptation stage, Self-MaskTune refines predictions across the full disc by balancing multimodal and full-disc infrared knowledge. Experiments on the introduced PRE benchmark demonstrate that PRE-Net significantly advanced precipitation retrieval performance, outperforming leading products like PERSIANN-CCS, PDIR, and IMERG. The code will be available at https://github.com/Zjut-MultimediaPlus/PRE-Net.

cs.CV↗

arXiv2025

How do higher-order interactions shape the energy landscape?

Understanding how higher-order interactions shape the energy landscape of coupled oscillator networks is crucial for characterizing complex synchronization phenomena. Here, we investigate a generalized Kuramoto model with triadic interactions, combining deterministic basin analysis, noise-induced transitions, and quantum annealing methods. We uncover a dual effect of higher-order interactions: they simultaneously expand basins for non-twisted states while contracting those of twisted states, yet modify potential well depths for both. As triadic coupling strengthens, higher-winding-number states and non-twisted states gain stability relative to synchronized states. The system exhibits remarkable stability asymmetry, where states with small basins can possess deep potential wells, making them highly resistant to noise-induced transitions once formed. These findings extend quasipotential theory to high-dimensional networked systems and offer new insights for controlling synchronization in complex systems.

nlin.AO↗

arXiv2025

Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias

Node representation learning on attributed graphs -- whose nodes are associated with rich attributes (e.g., texts and protein sequences) -- plays a crucial role in many important downstream tasks. To encode the attributes and graph structures simultaneously, recent studies integrate pre-trained models with graph neural networks (GNNs), where pre-trained models serve as node encoders (NEs) to encode the attributes. As jointly training large NEs and GNNs on large-scale graphs suffers from severe scalability issues, many methods propose to train NEs and GNNs separately. Consequently, they do not take feature convolutions in GNNs into consideration in the training phase of NEs, leading to a significant learning bias relative to the joint training. To address this challenge, we propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias. More importantly, we show that LD converges to the optimal objective function values by the joint training under mild assumptions. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.

cs.LG↗

arXiv2025

SASP: Strip-Aware Spatial Perception for Fine-Grained Bird Image Classification

Fine-grained bird image classification (FBIC) is not only of great significance for ecological monitoring and species identification, but also holds broad research value in the fields of image recognition and fine-grained visual modeling. Compared with general image classification tasks, FBIC poses more formidable challenges: 1) the differences in species size and imaging distance result in the varying sizes of birds presented in the images; 2) complex natural habitats often introduce strong background interference; 3) and highly flexible poses such as flying, perching, or foraging result in substantial intra-class variability. These factors collectively make it difficult for traditional methods to stably extract discriminative features, thereby limiting the generalizability and interpretability of models in real-world applications. To address these challenges, this paper proposes a fine-grained bird classification framework based on strip-aware spatial perception, which aims to capture long-range spatial dependencies across entire rows or columns in bird images, thereby enhancing the model's robustness and interpretability. The proposed method incorporates two novel modules: extensional perception aggregator (EPA) and channel semantic weaving (CSW). Specifically, EPA integrates local texture details with global structural cues by aggregating information across horizontal and vertical spatial directions. CSW further refines the semantic representations by adaptively fusing long-range and short-range information along the channel dimension. Built upon a ResNet-50 backbone, the model enables jump-wise connection of extended structural features across the spatial domain. Experimental results on the CUB-200-2011 dataset demonstrate that our framework achieves significant performance improvements while maintaining architectural efficiency.

cs.CV↗

arXiv2025

Emergent rigidity percolation of five-fold aggregates enables controllable glass properties

Metallic glasses possess outstanding mechanical and physical properties, making them promising candidates for advanced structural and functional applications; however, the lack of understanding and control over their glass transition and solidification processes remains a significant barrier to practical design. The glass transition from liquid to amorphous solid has remained an open problem in physics despite many theories and recent advances in computational efforts. The question of identifying a clear and well-defined diverging length scale accompanying the glass transition has remained unanswered, as has the nature of the transition and, indeed, the presence of a transition at all, as opposed to a mere dynamical crossover. Here we answer these questions using numerical results and theoretical analysis showing that, in atomic (metallic) glass formers, the glass transition coincides with, and is caused by, a continuous rigidity percolation transition from a liquid-like to a solid-like material. The transition occurs as five-fold symmetric atomic clusters progressively aggregate, forming a system-spanning rigid network that marks the onset of mechanical stability. This percolation-driven rigidity growth is accompanied by a sharp increase in the shear modulus G', indicating the emergence of macroscopic solid-like behavior. Beyond this point, which coincides with the Maxwell isostatic point of the percolating structure, dynamical arrest or "freezing-in" prevents further evolution. The long-sought diverging length scale is thus identified as the percolation-driven growth of rigid five-fold clusters, providing a direct link between local structural motifs and macroscopic mechanical properties at the glass transition. These insights offer practical routes to rationally engineer metallic glasses with targeted mechanical stiffness, hardness, and toughness.

cond-mat.soft↗

arXiv2025

Substrate Effect on Electronic Band Structure and Topological Property in Monolayer V2O3 Magnetic Topological Insulator

Monolayer V2O3, a two-dimensional magnetic topological insulator with intrinsic ferromagnetic order and a nontrivial band gap, offers a promising platform for realizing quantum anomalous Hall (QAH) states. Using first-principles density functional theory calculations, we systematically investigate the impact of substrate selection on its electronic and topological properties. By modeling heterostructures with van der Waals (vdW) substrates, we demonstrate that non-magnetic substrates such as h-BN preserve the QAH phase with a Chern number C = 1, maintaining gapless chiral edge states. In contrast, ferromagnetic substrates induce extra electrons, destroying the topological order by shifting the Fermi level. These findings establish substrate engineering as a pivotal strategy for experimental realization of dissipationless edge transport in V2O3-based vdW heterostructures, advancing their potential applications as low-power topological electronics.

cond-mat.mtrl-sci↗

arXiv2025

Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs

Proteins, as essential biomolecules, play a central role in biological processes, including metabolic reactions and DNA replication. Accurate prediction of their properties and functions is crucial in biological applications. Recent development of protein language models (pLMs) with supervised fine tuning provides a promising solution to this problem. However, the fine-tuned model is tailored for particular downstream prediction task, and achieving general-purpose protein understanding remains a challenge. In this paper, we introduce Structure-Enhanced Protein Instruction Tuning (SEPIT) framework to bridge this gap. Our approach incorporates a novel structure-aware module into pLMs to enrich their structural knowledge, and subsequently integrates these enhanced pLMs with large language models (LLMs) to advance protein understanding. In this framework, we propose a novel instruction tuning pipeline. First, we warm up the enhanced pLMs using contrastive learning and structure denoising. Then, caption-based instructions are used to establish a basic understanding of proteins. Finally, we refine this understanding by employing a mixture of experts (MoEs) to capture more complex properties and functional information with the same number of activated parameters. Moreover, we construct the largest and most comprehensive protein instruction dataset to date, which allows us to train and evaluate the general-purpose protein understanding model. Extensive experiments on both open-ended generation and closed-set answer tasks demonstrate the superior performance of SEPIT over both closed-source general LLMs and open-source LLMs trained with protein knowledge.

cs.CL↗

arXiv2025

A Survey of LLM-based Agents in Medicine: How far are we from Baymax?

Large Language Models (LLMs) are transforming healthcare through the development of LLM-based agents that can understand, reason about, and assist with medical tasks. This survey provides a comprehensive review of LLM-based agents in medicine, examining their architectures, applications, and challenges. We analyze the key components of medical agent systems, including system profiles, clinical planning mechanisms, medical reasoning frameworks, and external capacity enhancement. The survey covers major application scenarios such as clinical decision support, medical documentation, training simulations, and healthcare service optimization. We discuss evaluation frameworks and metrics used to assess these agents' performance in healthcare settings. While LLM-based agents show promise in enhancing healthcare delivery, several challenges remain, including hallucination management, multimodal integration, implementation barriers, and ethical considerations. The survey concludes by highlighting future research directions, including advances in medical reasoning inspired by recent developments in LLM architectures, integration with physical systems, and improvements in training simulations. This work provides researchers and practitioners with a structured overview of the current state and future prospects of LLM-based agents in medicine.

cs.CL↗