arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 307 records · Page 17Linked to original sources

arXiv2025

M3D: Manifold-based Domain Adaptation with Dynamic Distribution for Non-Deep Transfer Learning in Cross-subject and Cross-session EEG-based Emotion Recognition

Emotion decoding using Electroencephalography (EEG)-based affective brain-computer interfaces (aBCIs) plays a crucial role in affective computing but is limited by challenges such as EEG's non-stationarity, individual variability, and the high cost of large labeled datasets. While deep learning methods are effective, they require extensive computational resources and large data volumes, limiting their practical application. To overcome these issues, we propose Manifold-based Domain Adaptation with Dynamic Distribution (M3D), a lightweight, non-deep transfer learning framework. M3D consists of four key modules: manifold feature transformation, dynamic distribution alignment, classifier learning, and ensemble learning. The data is mapped to an optimal Grassmann manifold space, enabling dynamic alignment of source and target domains. This alignment is designed to prioritize both marginal and conditional distributions, improving adaptation efficiency across diverse datasets. In classifier learning, the principle of structural risk minimization is applied to build robust classification models. Additionally, dynamic distribution alignment iteratively refines the classifier. The ensemble learning module aggregates classifiers from different optimization stages to leverage diversity and enhance prediction accuracy. M3D is evaluated on two EEG emotion recognition datasets using two validation protocols (cross-subject single-session and cross-subject cross-session) and a clinical EEG dataset for Major Depressive Disorder (MDD). Experimental results show that M3D outperforms traditional non-deep learning methods with a 4.47% average improvement and achieves deep learning-level performance with reduced data and computational requirements, demonstrating its potential for real-world aBCI applications.

cs.HC↗

arXiv2025

Progressive Modality Cooperation for Multi-Modality Domain Adaptation

In this work, we propose a new generic multi-modality domain adaptation framework called Progressive Modality Cooperation (PMC) to transfer the knowledge learned from the source domain to the target domain by exploiting multiple modality clues (\eg, RGB and depth) under the multi-modality domain adaptation (MMDA) and the more general multi-modality domain adaptation using privileged information (MMDA-PI) settings. Under the MMDA setting, the samples in both domains have all the modalities. In two newly proposed modules of our PMC, the multiple modalities are cooperated for selecting the reliable pseudo-labeled target samples, which captures the modality-specific information and modality-integrated information, respectively. Under the MMDA-PI setting, some modalities are missing in the target domain. Hence, to better exploit the multi-modality data in the source domain, we further propose the PMC with privileged information (PMC-PI) method by proposing a new multi-modality data generation (MMG) network. MMG generates the missing modalities in the target domain based on the source domain data by considering both domain distribution mismatch and semantics preservation, which are respectively achieved by using adversarial learning and conditioning on weighted pseudo semantics. Extensive experiments on three image datasets and eight video datasets for various multi-modality cross-domain visual recognition tasks under both MMDA and MMDA-PI settings clearly demonstrate the effectiveness of our proposed PMC framework.

cs.CV↗

arXiv2025

Genome-Anchored Foundation Model Embeddings Improve Molecular Prediction from Histology Images

Precision oncology requires accurate molecular insights, yet obtaining these directly from genomics is costly and time-consuming for broad clinical use. Predicting complex molecular features and patient prognosis directly from routine whole-slide images (WSI) remains a major challenge for current deep learning methods. Here we introduce PathLUPI, which uses transcriptomic privileged information during training to extract genome-anchored histological embeddings, enabling effective molecular prediction using only WSIs at inference. Through extensive evaluation across 49 molecular oncology tasks using 11,257 cases among 20 cohorts, PathLUPI demonstrated superior performance compared to conventional methods trained solely on WSIs. Crucially, it achieves AUC $\geq$ 0.80 in 14 of the biomarker prediction and molecular subtyping tasks and C-index $\geq$ 0.70 in survival cohorts of 5 major cancer types. Moreover, PathLUPI embeddings reveal distinct cellular morphological signatures associated with specific genotypes and related biological pathways within WSIs. By effectively encoding molecular context to refine WSI representations, PathLUPI overcomes a key limitation of existing models and offers a novel strategy to bridge molecular insights with routine pathology workflows for wider clinical application.

cs.CV↗

arXiv2025

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis

Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are unable to produce correct answers when all candidates are incorrect. In this paper, we propose a novel inference scaling strategy, CoT-based Synthesizer, which leverages CoT reasoning to synthesize superior answers by analyzing complementary information from multiple candidate responses, even when all candidate responses are flawed. To enable a lightweight and cost-effective implementation, we introduce an automated data generation pipeline that creates diverse training data. This allows smaller LLMs trained on this data to improve the inference accuracy of larger models, including API-based LLMs. Experimental results across four benchmark datasets with seven policy models demonstrate that our method significantly enhances performance, with gains of 11.8% for Llama3-8B and 10.3% for GPT-4o on the MATH dataset. The corresponding training data and code are publicly available on https://github.com/RUCKBReasoning/CoT-based-Synthesizer.

cs.CL↗

arXiv2025

Topologically nontrivial and trivial flat bands via weak and strong interlayer coupling in twisted bilayer honeycomb optical lattices for ultracold atoms

In recent years, flat electronic bands in twisted bilayer graphene (TBG) have attracted significant attention due to their intriguing topological properties, extremely slow electron velocities, and enhanced density of states. Extending twisted bilayer systems to new configurations is highly desirable, as it offers promising opportunities to explore flat bands beyond TBG. Here, we study both topological and trivial flat bands in a twisted bilayer honeycomb lattice for ultracold atoms and present the evolution of the flat bands with different interlayer coupling strength (ICS). Our results demonstrate that an isolated topological flat band can emerge at the Dirac point energy for a specific value of weak ICS, referred to as the ``critical coupling". This occurs over a wide range of twist angles, surpassing the limits of the magic angle in TBG systems. When the ICS is slightly increased beyond the critical coupling value, the topological flat band exhibits degenerate band crossings with both the upper and lower adjacent bands at the high-symmetry $Γ_s$ point. As the ICS is further increased into the strong coupling regime, trivial flat bands arise around Dirac point energy. Meanwhile, more trivial flat bands appear, extending from the lowest to higher energy bands, and remain flat as the ICS increases. The topological properties of the flat bands are studied through the winding pattern of the Wilson loop spectrum. Our research provides deeper insights into the formation of flat bands in ultracold atoms with highly controllable twisted bilayer optical lattices, and may contribute to the discovery of new strongly correlated states of matter.

cond-mat.quant-gas↗

arXiv2025

VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors

We introduce VectorPainter, a novel framework designed for reference-guided text-to-vector-graphics synthesis. Based on our observation that the style of strokes can be an important aspect to distinguish different artists, our method reforms the task into synthesize a desired vector graphics by rearranging stylized strokes, which are vectorized from the reference images. Specifically, our method first converts the pixels of the reference image into a series of vector strokes, and then generates a vector graphic based on the input text description by optimizing the positions and colors of these vector strokes. To precisely capture the style of the reference image in the vectorized strokes, we propose an innovative vectorization method that employs an imitation learning strategy. To preserve the style of the strokes throughout the generation process, we introduce a style-preserving loss function. Extensive experiments have been conducted to demonstrate the superiority of our approach over existing works in stylized vector graphics synthesis, as well as the effectiveness of the various components of our method.

cs.CV↗

arXiv2025

The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception

While nighttime image dehazing has been extensively studied, converting nighttime hazy images to daytime-equivalent brightness remains largely unaddressed. Existing methods face two critical limitations: (1) datasets overlook the brightness relationship between day and night, resulting in the brightness mapping being inconsistent with the real world during image synthesis; and (2) models do not explicitly incorporate daytime brightness knowledge, limiting their ability to reconstruct realistic lighting. To address these challenges, we introduce the Diffusion-Based Nighttime Dehazing (DiffND) framework, which excels in both data synthesis and lighting reconstruction. Our approach starts with a data synthesis pipeline that simulates severe distortions while enforcing brightness consistency between synthetic and real-world scenes, providing a strong foundation for learning night-to-day brightness mapping. Next, we propose a restoration model that integrates a pre-trained diffusion model guided by a brightness perception network. This design harnesses the diffusion model's generative ability while adapting it to nighttime dehazing through brightness-aware optimization. Experiments validate our dataset's utility and the model's superior performance in joint haze removal and brightness mapping.

cs.CV↗

arXiv2025

ISMAF: Intrinsic-Social Modality Alignment and Fusion for Multimodal Rumor Detection

The rapid dissemination of rumors on social media highlights the urgent need for automatic detection methods to safeguard societal trust and stability. While existing multimodal rumor detection models primarily emphasize capturing consistency between intrinsic modalities (e.g., news text and images), they often overlook the intricate interplay between intrinsic and social modalities. This limitation hampers the ability to fully capture nuanced relationships that are crucial for a comprehensive understanding. Additionally, current methods struggle with effectively fusing social context with textual and visual information, resulting in fragmented interpretations. To address these challenges, this paper proposes a novel Intrinsic-Social Modality Alignment and Fusion (ISMAF) framework for multimodal rumor detection. ISMAF first employs a cross-modal consistency alignment strategy to align complex interactions between intrinsic and social modalities. It then leverages a mutual learning approach to facilitate collaborative refinement and integration of complementary information across modalities. Finally, an adaptive fusion mechanism is incorporated to dynamically adjust the contribution of each modality, tackling the complexities of three-modality fusion. Extensive experiments on both English and Chinese real-world multimedia datasets demonstrate that ISMAF consistently outperforms state-of-the-art models.

cs.MM↗

arXiv2025

What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?

Recent prosperity of text-to-image diffusion models, e.g. Stable Diffusion, has stimulated research to adapt them to 360-degree panorama generation. Prior work has demonstrated the feasibility of using conventional low-rank adaptation techniques on pre-trained diffusion models to generate panoramic images. However, the substantial domain gap between perspective and panoramic images raises questions about the underlying mechanisms enabling this empirical success. We hypothesize and examine that the trainable counterparts exhibit distinct behaviors when fine-tuned on panoramic data, and such an adaptation conceals some intrinsic mechanism to leverage the prior knowledge within the pre-trained diffusion models. Our analysis reveals the following: 1) the query and key matrices in the attention modules are responsible for common information that can be shared between the panoramic and perspective domains, thus are less relevant to panorama generation; and 2) the value and output weight matrices specialize in adapting pre-trained knowledge to the panoramic domain, playing a more critical role during fine-tuning for panorama generation. We empirically verify these insights by introducing a simple framework called UniPano, with the objective of establishing an elegant baseline for future research. UniPano not only outperforms existing methods but also significantly reduces memory usage and training time compared to prior dual-branch approaches, making it scalable for end-to-end panorama generation with higher resolution. The code will be released.

cs.CV↗

arXiv2025

P$^2$ Law: Scaling Law for Post-Training After Model Pruning

Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs). To recover model performance after pruning, post-training is commonly employed to mitigate the resulting performance degradation. While post-training benefits from larger datasets, once the dataset size is already substantial, increasing the training data provides only limited performance gains. To balance post-training cost and model performance, it is necessary to explore the optimal amount of post-training data.Through extensive experiments on the Llama-3 and Qwen-2.5 series models, pruned using various common pruning methods, we uncover the scaling \textbf{Law} for \textbf{P}ost-training after model \textbf{P}runing, referred to as the P$^2$ Law.This law identifies four key factors for predicting the pruned model's post-training loss: the model size before pruning, the number of post-training tokens, the pruning rate, and the model's loss before pruning. Moreover, P$^2$ Law can generalize to larger dataset sizes, larger model sizes, and higher pruning rates, offering valuable insights for the post-training of pruned LLMs.

cs.AI↗

arXiv2025

PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology

The emergence of pathology foundation models has revolutionized computational histopathology, enabling highly accurate, generalized whole-slide image analysis for improved cancer diagnosis, and prognosis assessment. While these models show remarkable potential across cancer diagnostics and prognostics, their clinical translation faces critical challenges including variability in optimal model across cancer types, potential data leakage in evaluation, and lack of standardized benchmarks. Without rigorous, unbiased evaluation, even the most advanced PFMs risk remaining confined to research settings, delaying their life-saving applications. Existing benchmarking efforts remain limited by narrow cancer-type focus, potential pretraining data overlaps, or incomplete task coverage. We present PathBench, the first comprehensive benchmark addressing these gaps through: multi-center in-hourse datasets spanning common cancers with rigorous leakage prevention, evaluation across the full clinical spectrum from diagnosis to prognosis, and an automated leaderboard system for continuous model assessment. Our framework incorporates large-scale data, enabling objective comparison of PFMs while reflecting real-world clinical complexity. All evaluation data comes from private medical providers, with strict exclusion of any pretraining usage to avoid data leakage risks. We have collected 15,888 WSIs from 8,549 patients across 10 hospitals, encompassing over 64 diagnosis and prognosis tasks. Currently, our evaluation of 19 PFMs shows that Virchow2 and H-Optimus-1 are the most effective models overall. This work provides researchers with a robust platform for model development and offers clinicians actionable insights into PFM performance across diverse clinical scenarios, ultimately accelerating the translation of these transformative technologies into routine pathology practice.

cs.CV↗

arXiv2025

Photon emission gain in Er doped Si light emitting diodes by impact excitation

This work demonstrates photon emission gain, i.e., emission of multiple photons per injected electron, through impact excitation in Er-doped silicon light-emitting diodes (LEDs). Conventional methods for exciting Er ions in silicon suffer from low efficiency due to mismatched energy transfer between exciton recombination and Er excitation. Here, we propose a reverse-biased Si PN junction diode where ballistically accelerated electrons induce inelastic collisions with Er ions, enabling tunable excitation via electric field modulation. Theoretical modeling reveals that photon emission gain arises from multiple impact excitations by a single electron traversing the electroluminescence region, with the gain value approximating the ratio of emission region width to electron mean free path, i.e., G = Lex/l. Experimental results show an internal quantum efficiency (IQE) of 1.84% at 78 K, representing a 20-fold enhancement over room-temperature performance. This work provides a critical foundation for on-chip integration of silicon-based communication-band lasers and quantum light sources.

physics.optics↗

arXiv2025

Advances in Radiance Field for Dynamic Scene: From Neural Field to Gaussian Field

Dynamic scene representation and reconstruction have undergone transformative advances in recent years, catalyzed by breakthroughs in neural radiance fields and 3D Gaussian splatting techniques. While initially developed for static environments, these methodologies have rapidly evolved to address the complexities inherent in 4D dynamic scenes through an expansive body of research. Coupled with innovations in differentiable volumetric rendering, these approaches have significantly enhanced the quality of motion representation and dynamic scene reconstruction, thereby garnering substantial attention from the computer vision and graphics communities. This survey presents a systematic analysis of over 200 papers focused on dynamic scene representation using radiance field, spanning the spectrum from implicit neural representations to explicit Gaussian primitives. We categorize and evaluate these works through multiple critical lenses: motion representation paradigms, reconstruction techniques for varied scene dynamics, auxiliary information integration strategies, and regularization approaches that ensure temporal consistency and physical plausibility. We organize diverse methodological approaches under a unified representational framework, concluding with a critical examination of persistent challenges and promising research directions. By providing this comprehensive overview, we aim to establish a definitive reference for researchers entering this rapidly evolving field while offering experienced practitioners a systematic understanding of both conceptual principles and practical frontiers in dynamic scene reconstruction.

cs.CV↗

arXiv2025

Privacy-Preserving Socialized Recommendation based on Multi-View Clustering in a Cloud Environment

Recommendation as a service has improved the quality of our lives and plays a significant role in variant aspects. However, the preference of users may reveal some sensitive information, so that the protection of privacy is required. In this paper, we propose a privacy-preserving, socialized, recommendation protocol that introduces information collected from online social networks to enhance the quality of the recommendation. The proposed scheme can calculate the similarity between users to determine their potential relationships and interests, and it also can protect the users' privacy from leaking to an untrusted third party. The security analysis and experimental results showed that our proposed scheme provides excellent performance and is feasible for real-world applications.

cs.CR↗

arXiv2025

FIOVA: A Multi-Annotator Benchmark for Human-Aligned Video Captioning

Despite rapid progress in large vision-language models (LVLMs), existing video caption benchmarks remain limited in evaluating their alignment with human understanding. Most rely on a single annotation per video and lexical similarity-based metrics, failing to capture the variability in human perception and the cognitive importance of events. These limitations hinder accurate diagnosis of model capabilities in producing coherent, complete, and human-aligned descriptions. To address this, we introduce FIOVA (Five-In-One Video Annotations), a human-centric benchmark tailored for evaluation. It comprises 3,002 real-world videos (about 33.6s each), each annotated independently by five annotators. This design enables modeling of semantic diversity and inter-subjective agreement, offering a richer foundation for measuring human-machine alignment. We further propose FIOVA-DQ, an event-level evaluation metric that incorporates cognitive weights derived from annotator consensus, providing fine-grained assessment of event relevance and semantic coverage. Leveraging FIOVA, we conduct a comprehensive evaluation of nine representative LVLMs and introduce a complexity-aware analysis framework based on inter-annotator variation (CV). This reveals consistency gaps across difficulty levels and identifies structural issues such as event under-description and template convergence. Our results highlight FIOVA's diagnostic value for understanding LVLM behavior under varying complexity, setting a new standard for cognitively aligned evaluation in long-video captioning. The benchmark, annotations, metric, and model outputs are publicly released to support future evaluation-driven research in video understanding. More detailed information can be found at https://huuuuusy.github.io/fiova/.

cs.CV↗

arXiv2025

Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?

Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple visual question answering, visual-text parsing, etc. However, the extent to which LMMs can deal with complex logical reasoning problems based on OCR cues is relatively unexplored. To this end, we introduce the Reasoning-OCR benchmark, which challenges LMMs to solve complex reasoning problems based on the cues that can be extracted from rich visual-text. Reasoning-OCR covers six visual scenarios and encompasses 150 meticulously designed questions categorized into six reasoning challenges. Additionally, Reasoning-OCR minimizes the impact of field-specialized knowledge. Our evaluation offers some insights for proprietary and open-source LMMs in different reasoning challenges, underscoring the urgent to improve the reasoning performance. We hope Reasoning-OCR can inspire and facilitate future research on enhancing complex reasoning ability based on OCR cues. Reasoning-OCR is publicly available at https://github.com/Hxyz-123/ReasoningOCR.

cs.CV↗

arXiv2025

Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis

Pathological diagnosis is vital for determining disease characteristics, guiding treatment, and assessing prognosis, relying heavily on detailed, multi-scale analysis of high-resolution whole slide images (WSI). However, existing large vision-language models (LVLMs) are limited by input resolution constraints, hindering their efficiency and accuracy in pathology image analysis. To overcome these issues, we propose two innovative strategies: the mixed task-guided feature enhancement, which directs feature extraction toward lesion-related details across scales, and the prompt-guided detail feature completion, which integrates coarse- and fine-grained features from WSI based on specific prompts without compromising inference speed. Leveraging a comprehensive dataset of 490K samples from diverse pathology tasks, we trained the pathology-specialized LVLM, OmniPath. Extensive experiments demonstrate that this model significantly outperforms existing methods in diagnostic accuracy and efficiency, providing an interactive, clinically aligned approach for auxiliary diagnosis in a wide range of pathology applications.

cs.CV↗

arXiv2025

TiMo: Spatiotemporal Foundation Model for Satellite Image Time Series

Satellite image time series (SITS) provide continuous observations of the Earth's surface, making them essential for applications such as environmental management and disaster assessment. However, existing spatiotemporal foundation models rely on plain vision transformers, which encode entire temporal sequences without explicitly capturing multiscale spatiotemporal relationships between land objects. This limitation hinders their effectiveness in downstream tasks. To overcome this challenge, we propose TiMo, a novel hierarchical vision transformer foundation model tailored for SITS analysis. At its core, we introduce a spatiotemporal gyroscope attention mechanism that dynamically captures evolving multiscale patterns across both time and space. For pre-training, we curate MillionST, a large-scale dataset of one million images from 100,000 geographic locations, each captured across 10 temporal phases over five years, encompassing diverse geospatial changes and seasonal variations. Leveraging this dataset, we adapt masked image modeling to pre-train TiMo, enabling it to effectively learn and encode generalizable spatiotemporal representations.Extensive experiments across multiple spatiotemporal tasks-including deforestation monitoring, land cover segmentation, crop type classification, and flood detection-demonstrate TiMo's superiority over state-of-the-art methods. Code, model, and dataset will be released at https://github.com/MiliLab/TiMo.

cs.CV↗