arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 541 records · Page 30Linked to original sources

arXiv2025

Spontaneous Spatial Cognition Emerges during Egocentric Video Viewing through Non-invasive BCI

Humans possess a remarkable capacity for spatial cognition, allowing for self-localization even in novel or unfamiliar environments. While hippocampal neurons encoding position and orientation are well documented, the large-scale neural dynamics supporting spatial representation, particularly during naturalistic, passive experience, remain poorly understood. Here, we demonstrate for the first time that non-invasive brain-computer interfaces (BCIs) based on electroencephalography (EEG) can decode spontaneous, fine-grained egocentric 6D pose, comprising three-dimensional position and orientation, during passive viewing of egocentric video. Despite EEG's limited spatial resolution and high signal noise, we find that spatially coherent visual input (i.e., continuous and structured motion) reliably evokes decodable spatial representations, aligning with participants' subjective sense of spatial engagement. Decoding performance further improves when visual input is presented at a frame rate of 100 ms per image, suggesting alignment with intrinsic neural temporal dynamics. Using gradient-based backpropagation through a neural decoding model, we identify distinct EEG channels contributing to position -- and orientation specific -- components, revealing a distributed yet complementary neural encoding scheme. These findings indicate that the brain's spatial systems operate spontaneously and continuously, even under passive conditions, challenging traditional distinctions between active and passive spatial cognition. Our results offer a non-invasive window into the automatic construction of egocentric spatial maps and advance our understanding of how the human mind transforms everyday sensory experience into structured internal representations.

q-bio.NC↗

arXiv2025

Nexus-Gen: Unified Image Understanding, Generation, and Editing via Prefilled Autoregression in Shared Embedding Space

Unified multimodal generative models aim to integrate image understanding and generation abilities, offering significant advantages in harnessing multimodal corpora, particularly interleaved text-image data. However, existing unified models exhibit limitations in image synthesis quality, autoregressive error accumulation, and image editing capability. In this work, we propose Nexus-Gen, a novel architecture that unifies image understanding, generation, and editing tasks in a shared image embedding space. This shared space serves as a bridge for the autoregressive and diffusion models, which seamlessly integrates their complementary strengths in cross-modal modeling. To mitigate the severe error accumulation during autoregressive embedding prediction, we propose a novel prefilled autoregression strategy that aligns training-inference dynamics by prefilling input sequences with learnable embeddings. After multi-stage and multi-task training on our constructed large-scale dataset with 26.3 million samples, Nexus-Gen achieves state-of-the-art performance on the evaluation benchmarks spanning image understanding, generation and editing tasks. All models, datasets, and source codes are released in https://github.com/modelscope/Nexus-Gen to facilitate further advancements across the field.

cs.CV↗

arXiv2025

Assessing Color Vision Test in Large Vision-language Models

With the widespread adoption of large vision-language models, the capacity for color vision in these models is crucial. However, the color vision abilities of large visual-language models have not yet been thoroughly explored. To address this gap, we define a color vision testing task for large vision-language models and construct a dataset \footnote{Anonymous Github Showing some of the data https://anonymous.4open.science/r/color-vision-test-dataset-3BCD} that covers multiple categories of test questions and tasks of varying difficulty levels. Furthermore, we analyze the types of errors made by large vision-language models and propose fine-tuning strategies to enhance their performance in color vision tests.

cs.CV↗

arXiv2025

Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models

Automated Program Repair (APR) is essential for ensuring software reliability and quality while enhancing efficiency and reducing developers' workload. Although rule-based and learning-based APR methods have demonstrated their effectiveness, their performance was constrained by the defect type of repair, the quality of training data, and the size of model parameters. Recently, Large Language Models (LLMs) combined with Retrieval-Augmented-Generation (RAG) have been increasingly adopted in APR tasks. However, current code LLMs and RAG designs neither fully address code repair tasks nor consider code-specific features. To overcome these limitations, we propose SelRepair, a novel APR approach with integration of a fine-tuned LLM with a newly-designed dual RAG module. This approach uses a bug-fix pair dataset for fine-tuning and incorporates semantic and syntactic/structural similarity information through an RAG selection gate. This design ensures relevant information is retrieved efficiently, thereby reducing token length and inference time. Evaluations on Java datasets show SelRepair outperforms other APR methods, achieving 26.29% and 17.64% in terms of exact match (EM) on different datasets while reducing inference time by at least 6.42% with controlled input lengths.

cs.SE↗

arXiv2025

Structural Representations and Identification of Marginal Policy Effects

This paper investigates the structural interpretation of the marginal policy effect (MPE) within nonseparable models. We demonstrate that, for a smooth functional of the outcome distribution, the MPE equals its functional derivative evaluated at the outcome-conditioned weighted average structural derivative. This equivalence is definitional rather than identification-based. Building on this theoretical result, we propose an alternative identification strategy for the MPE that complements existing methods.

econ.EM↗

arXiv2025

STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation

Recent breakthroughs in singing voice synthesis (SVS) have heightened the demand for high-quality annotated datasets, yet manual annotation remains prohibitively labor-intensive and resource-intensive. Existing automatic singing annotation (ASA) methods, however, primarily tackle isolated aspects of the annotation pipeline. To address this fundamental challenge, we present STARS, which is, to our knowledge, the first unified framework that simultaneously addresses singing transcription, alignment, and refined style annotation. Our framework delivers comprehensive multi-level annotations encompassing: (1) precise phoneme-audio alignment, (2) robust note transcription and temporal localization, (3) expressive vocal technique identification, and (4) global stylistic characterization including emotion and pace. The proposed architecture employs hierarchical acoustic feature processing across frame, word, phoneme, note, and sentence levels. The novel non-autoregressive local acoustic encoders enable structured hierarchical representation learning. Experimental validation confirms the framework's superior performance across multiple evaluation dimensions compared to existing annotation approaches. Furthermore, applications in SVS training demonstrate that models utilizing STARS-annotated data achieve significantly enhanced perceptual naturalness and precise style control. This work not only overcomes critical scalability challenges in the creation of singing datasets but also pioneers new methodologies for controllable singing voice synthesis. Audio samples are available at https://gwx314.github.io/stars-demo/.

cs.SD↗

arXiv2025

Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG

Effectively utilizing extensive unlabeled high-density EEG data to improve performance in scenarios with limited labeled low-density EEG data presents a significant challenge. In this paper, we address this challenge by formulating it as a graph transfer learning and knowledge distillation problem. We propose a Unified Pre-trained Graph Contrastive Masked Autoencoder Distiller, named EEG-DisGCMAE, to bridge the gap between unlabeled and labeled as well as high- and low-density EEG data. Our approach introduces a novel unified graph self-supervised pre-training paradigm, which seamlessly integrates the graph contrastive pre-training with the graph masked autoencoder pre-training. Furthermore, we propose a graph topology distillation loss function, allowing a lightweight student model trained on low-density data to learn from a teacher model trained on high-density data during pre-training and fine-tuning. This method effectively handles missing electrodes through contrastive distillation. We validate the effectiveness of EEG-DisGCMAE across four classification tasks using two clinical EEG datasets with abundant data. The source code is available at https://github.com/weixinxu666/EEG_DisGCMAE.

cs.LG↗

arXiv2025

PAST: A multimodal single-cell foundation model for histopathology and spatial transcriptomics in cancer

While pathology foundation models have transformed cancer image analysis, they often lack integration with molecular data at single-cell resolution, limiting their utility for precision oncology. Here, we present PAST, a pan-cancer single-cell foundation model trained on 20 million paired histopathology images and single-cell transcriptomes spanning multiple tumor types and tissue contexts. By jointly encoding cellular morphology and gene expression, PAST learns unified cross-modal representations that capture both spatial and molecular heterogeneity at the cellular level. This approach enables accurate prediction of single-cell gene expression, virtual molecular staining, and multimodal survival analysis directly from routine pathology slides. Across diverse cancers and downstream tasks, PAST consistently exceeds the performance of existing approaches, demonstrating robust generalizability and scalability. Our work establishes a new paradigm for pathology foundation models, providing a versatile tool for high-resolution spatial omics, mechanistic discovery, and precision cancer research.

q-bio.QM↗

arXiv2025

SimVecVis: A Dataset for Enhancing MLLMs in Visualization Understanding

Current multimodal large language models (MLLMs), while effective in natural image understanding, struggle with visualization understanding due to their inability to decode the data-to-visual mapping and extract structured information. To address these challenges, we propose SimVec, a novel simplified vector format that encodes chart elements such as mark type, position, and size. The effectiveness of SimVec is demonstrated by using MLLMs to reconstruct chart information from SimVec formats. Then, we build a new visualization dataset, SimVecVis, to enhance the performance of MLLMs in visualization understanding, which consists of three key dimensions: bitmap images of charts, their SimVec representations, and corresponding data-centric question-answering (QA) pairs with explanatory chain-of-thought (CoT) descriptions. We finetune state-of-the-art MLLMs (e.g., MiniCPM and Qwen-VL), using SimVecVis with different dataset dimensions. The experimental results show that it leads to substantial performance improvements of MLLMs with good spatial perception capabilities (e.g., MiniCPM) in data-centric QA tasks. Our dataset and source code are available at: https://github.com/VIDA-Lab/SimVecVis.

cs.HC↗

arXiv2025

An RRT* algorithm based on Riemannian metric model for optimal path planning

This paper presents a Riemannian metric-based model to solve the optimal path planning problem on two-dimensional smooth submanifolds in high-dimensional space. Our model is based on constructing a new Riemannian metric on a two-dimensional projection plane, which is induced by the high-dimensional Euclidean metric on two-dimensional smooth submanifold and reflects the environmental information of the robot. The optimal path planning problem in high-dimensional space is therefore transformed into a geometric problem on the two-dimensional plane with new Riemannian metric. Based on the new Riemannian metric, we proposed an incremental algorithm RRT*-R on the projection plane. The experimental results show that the proposed algorithm is suitable for scenarios with uneven fields in multiple dimensions. The proposed algorithm can help the robot to effectively avoid areas with drastic changes in height, ground resistance and other environmental factors. More importantly, the RRT*-R algorithm shows better smoothness and optimization properties compared with the original RRT* algorithm using Euclidean distance in high-dimensional workspace. The length of the entire path by RRT*-R is a good approximation of the theoretical minimum geodesic distance on projection plane.

cs.RO↗

arXiv2025

ASTARS empowered Satellite Positioning Approach for Urban Canyons and Indoor Environments

To mitigate the loss of satellite navigation signals in urban canyons and indoor environments, we propose an active simultaneous transmitting and reflecting reconfigurable intelligent surface (ASTARS) empowered satellite positioning approach. Deployed on building structures, ASTARS reflects navigation signals to outdoor receivers in urban canyons and transmits signals indoors to bypass obstructions, providing high-precision positioning services to receivers in non-line-of-sight (NLoS) areas. The path between ASTARS and the receiver is defined as the extended line-of-sight (ELoS) path and an improved carrier phase observation equation is derived to accommodate that. The receiver compensates for its clock bias through network time synchronization, corrects the actual signal path distance to the satellite-to-receiver distance through a distance correction algorithm, and determines its position by using the least squares (LS) method. Mathematical modeling of the errors introduced by the proposed method is conducted, followed by simulation analysis to assess their impact. Simulation results show that: 1) in areas where GNSS signals are blocked, with time synchronization accuracy within a 10 ns error range, the proposed method provides positioning services with errors not exceeding 4 m for both indoor and outdoor receivers, outperforming conventional NLoS methods with positioning errors of more than 7 m; 2) the additional errors introduced by the proposed method do not exceed 3 m for time synchronization errors within 10 ns, which includes the phase shift, beamwidth error, time synchronization errors, and satellite distribution errors, outperforming traditional NLoS methods, which typically produce positioning errors greater than 5 m.

cs.IT↗

arXiv2025

ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data

With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required for developing reliable computer-aided extraction protocols. Here, we present ChemActor, a fully fine-tuned large language model (LLM), as a chemical executor to convert between unstructured experimental procedures and structured action sequences. We propose a sequential LLM-generated data framework to address the challenges of insufficient and low-quality annotated data. This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input. Additionally, we introduce a novel multi-round LLMs circle review metric, which reflects the model's advanced understanding of chemical experimental procedures. Extensive experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor, augmented by LLM-generated data, achieves state-of-the-art performance, outperforming the baseline model by 10%. The code is available at: https://github.com/Zhanghahah/ChemActor.

cs.AI↗

arXiv2025

RM-Dijkstra: A surface optimal path planning algorithm based on Riemannian metric

The Dijkstra algorithm is a classic path planning method, which operates in a discrete graph space to determine the shortest path from a specified source point to a target node or all other nodes based on non-negative edge weights. Numerous studies have focused on the Dijkstra algorithm due to its potential application. However, its application in surface path planning for mobile robots remains largely unexplored. In this letter, a surface optimal path planning algorithm called RM-Dijkstra is proposed, which is based on Riemannian metric model. By constructing a new Riemannian metric on the 2D projection plane, the surface optimal path planning problem is therefore transformed into a geometric problem on the 2D plane with new Riemannian metric. Induced by the standard Euclidean metric on surface, the constructed new metric reflects environmental information of the robot and ensures that the projection map is an isometric immersion. By conducting a series of simulation tests, the experimental results demonstrate that the RM-Dijkstra algorithm not only effectively solves the optimal path planning problem on surfaces, but also outperforms traditional path planning algorithms in terms of path accuracy and smoothness, particularly in complex scenarios.

cs.RO↗

arXiv2025

Strategic A/B testing via Maximum Probability-driven Two-armed Bandit

Detecting a minor average treatment effect is a major challenge in large-scale applications, where even minimal improvements can have a significant economic impact. Traditional methods, reliant on normal distribution-based or expanded statistics, often fail to identify such minor effects because of their inability to handle small discrepancies with sufficient sensitivity. This work leverages a counterfactual outcome framework and proposes a maximum probability-driven two-armed bandit (TAB) process by weighting the mean volatility statistic, which controls Type I error. The implementation of permutation methods further enhances the robustness and efficacy. The established strategic central limit theorem (SCLT) demonstrates that our approach yields a more concentrated distribution under the null hypothesis and a less concentrated one under the alternative hypothesis, greatly improving statistical power. The experimental results indicate a significant improvement in the A/B testing, highlighting the potential to reduce experimental costs while maintaining high statistical power.

stat.ML↗

arXiv2025

L-2 Regularized maximum likelihood for $β$-model in large and sparse networks

The $β$-model is a powerful tool for modeling large and sparse networks driven by degree heterogeneity, where many network models become infeasible due to computational challenge and network sparsity. However, existing estimation algorithms for $β$-model do not scale up. Also, theoretical understandings remain limited to dense networks. This paper brings several significant improvements over existing results to address the urgent needs of practice. We propose a new $\ell_2$-penalized MLE algorithm that can comfortably handle sparse networks of millions of nodes with much-improved memory parsimony. We establish the first rate-optimal error bounds and high-dimensional asymptotic normality results for $β$-models, under much weaker network sparsity assumptions than best existing results. Application of our method to large COVID-19 network data sets discovered meaningful results.

stat.ME↗

arXiv2025

LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution

Visual analytics (VA) requires analysts to iteratively propose analysis tasks based on observations and execute tasks by creating visualizations and interactive exploration to gain insights. This process demands skills in programming, data processing, and visualization tools, highlighting the need for a more intelligent, streamlined VA approach. Large language models (LLMs) have recently been developed as agents to handle various tasks with dynamic planning and tool-using capabilities, offering the potential to enhance the efficiency and versatility of VA. We propose LightVA, a lightweight VA framework that supports task decomposition, data analysis, and interactive exploration through human-agent collaboration. Our method is designed to help users progressively translate high-level analytical goals into low-level tasks, producing visualizations and deriving insights. Specifically, we introduce an LLM agent-based task planning and execution strategy, employing a recursive process involving a planner, executor, and controller. The planner is responsible for recommending and decomposing tasks, the executor handles task execution, including data analysis, visualization generation and multi-view composition, and the controller coordinates the interaction between the planner and executor. Building on the framework, we develop a system with a hybrid user interface that includes a task flow diagram for monitoring and managing the task planning process, a visualization panel for interactive data exploration, and a chat view for guiding the model through natural language instructions. We examine the effectiveness of our method through a usage scenario and an expert study.

cs.HC↗

arXiv2025

Exceedingly large in-plane critical field of finite-momentum pairing state in bulk superlattices

Magnetic flux profoundly influences the phase factor of charge particles, leading to exotic quantum phenomena. A recent example is that the orbital effect of magnetic field could induce finite-momentum pairing state in nanoflakes, which offers a new pathway to realize the spatially modulated superconductivity distinct from the Fulde-Ferrell-Larkin-Ovchinnikov (FFLO) state induced by Zeeman effect. However, whether such intriguing state can exist in the bulk materials under extremely large magnetic field remains elusive. Here we report the orbital effect induced finite-momentum pairing state with exceedingly large in-plane critical field in a bulk superconducting superlattice. Remarkably, the in-plane critical field shows a pronounced upturn behavior, exceeding eight times the Pauli limit which is comparable to monolayer Ising superconductor. Under high in-plane magnetic fields, significant anisotropic transport behavior between the interlayer and intralayer directions is detected, highlighting the critical role of suppressed interlayer coherence in the orbital effect induced finite-momentum pairing state. Crucially, this finite-momentum pairing state remains robust against moderate disorder. Our findings suggest that van der Waals superlattices, with strong Ising spin-orbit coupling and tunable interlayer coherence, offer new avenues for constructing and modulating unconventional superconducting states.

cond-mat.supr-con↗

arXiv2025

KG-FGNN: Knowledge-guided GNN Foundation Model for Fertilisation-oriented Soil GHG Flux Prediction

Precision soil greenhouse gas (GHG) flux prediction is essential in agricultural systems for assessing environmental impacts, developing emission mitigation strategies and promoting sustainable agriculture. Due to the lack of advanced sensor and network technologies on majority of farms, there are challenges in obtaining comprehensive and diverse agricultural data. As a result, the scarcity of agricultural data seriously obstructs the application of machine learning approaches in precision soil GHG flux prediction. This research proposes a knowledge-guided graph neural network framework that addresses the above challenges by integrating knowledge embedded in an agricultural process-based model and graph neural network techniques. Specifically, we utilise the agricultural process-based model to simulate and generate multi-dimensional agricultural datasets for 47 countries that cover a wide range of agricultural variables. To extract key agricultural features and integrate correlations among agricultural features in the prediction process, we propose a machine learning framework that integrates the autoencoder and multi-target multi-graph based graph neural networks, which utilises the autoencoder to selectively extract significant agricultural features from the agricultural process-based model simulation data and the graph neural network to integrate correlations among agricultural features for accurately predict fertilisation-oriented soil GHG fluxes. Comprehensive experiments were conducted with both the agricultural simulation dataset and real-world agricultural dataset to evaluate the proposed approach in comparison with well-known baseline and state-of-the-art regression methods. The results demonstrate that our proposed approach provides superior accuracy and stability in fertilisation-oriented soil GHG prediction.

cs.LG↗