arXiv subjects

Yumeng Zhang

Publications and source records attributed to Yumeng Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registration

Accurate localization using visual information is a critical yet challenging task, especially in urban environments where nearby buildings and construction sites significantly degrade GNSS (Global Navigation Satellite System) signal quality. This issue underscores the importance of visual localization techniques in scenarios where GNSS signals are unreliable. This paper proposes U-ViLAR, a novel uncertainty-aware visual localization framework designed to address these challenges while enabling adaptive localization using high-definition (HD) maps or navigation maps. Specifically, our method first extracts features from the input visual data and maps them into Bird's-Eye-View (BEV) space to enhance spatial consistency with the map input. Subsequently, we introduce: a) Perceptual Uncertainty-guided Association, which mitigates errors caused by perception uncertainty, and b) Localization Uncertainty-guided Registration, which reduces errors introduced by localization uncertainty. By effectively balancing the coarse-grained large-scale localization capability of association with the fine-grained precise localization capability of registration, our approach achieves robust and accurate localization. Experimental results demonstrate that our method achieves state-of-the-art performance across multiple localization tasks. Furthermore, our model has undergone rigorous testing on large-scale autonomous driving fleets and has demonstrated stable performance in various challenging urban scenarios.

cs.CV↗

arXiv2026

Generative Models for Crystalline Materials

Understanding structure-property relationships in materials is fundamental in condensed matter physics and materials science. Over the past few years, machine learning (ML) has emerged as a powerful tool for advancing this understanding and accelerating materials discovery. Early ML approaches primarily focused on constructing and screening large material spaces to identify promising candidates for various applications. More recently, research efforts have increasingly shifted toward generating crystal structures using end-to-end generative models. This review analyzes the current state of generative modeling for crystal structure prediction and de novo generation. It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations. Furthermore, the review highlights experimental considerations for evaluating generated structures and provides recommendations for suitable existing software tools. Emerging topics, such as modeling disorder and defects, integration in advanced characterization, incorporating synthetic feasibility constraints, and model explainability are explored. Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.

cond-mat.mtrl-sci↗

arXiv2026

UniFuture: A 4D Driving World Model for Future Generation and Perception

We present UniFuture, a unified 4D Driving World Model designed to simulate the dynamic evolution of the 3D physical world. Unlike existing driving world models that focus solely on 2D pixel-level video generation (lacking geometry) or static perception (lacking temporal dynamics), our approach bridges appearance and geometry to construct a holistic 4D representation. Specifically, we treat future RGB images and depth maps as coupled projections of the same 4D reality and model them jointly within a single framework. To achieve this, we introduce a Dual-Latent Sharing (DLS) scheme, which maps visual and geometric modalities into a shared spatio-temporal latent space, implicitly entangling texture with structure. Furthermore, we propose a Multi-scale Latent Interaction (MLI) mechanism, which enforces bidirectional consistency: geometry constrains visual synthesis to prevent structural hallucinations, while visual semantics refine geometric estimation. During inference, UniFuture can forecast high-fidelity, geometrically consistent 4D scene sequences (image-depth pairs) from a single current frame. Extensive experiments on the nuScenes and Waymo datasets demonstrate that our method outperforms specialized models in both future generation and geometry perception, highlighting the efficacy of unified 4D modeling for autonomous driving. The code is available at https://github.com/dk-liang/UniFuture.

cs.CV↗

arXiv2026

Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization

Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly align with long-horizon task success. To address this, we propose Goal-Oriented Preference Optimization (GOPO), a hierarchical reinforcement learning framework that decouples strategy planning from response generation via an Expert Agent and a Customer Service Agent. The Expert Agent optimizes multi-turn goal preferences at the dialogue-trajectory level, while the Customer Service Agent generates responses strictly aligned with the selected strategy. We evaluate GOPO on public benchmarks and e-commerce customer service datasets, and introduce Task-focused Sequential Engagement (TSE), a sequence-level metric derived from real e-commerce interaction data. On the Mgshop dataset, GOPO improves TSE by 7.7% and 10.3% over PPO and Memento, with consistent gains in sequence-level reward and generation quality. Furthermore, a 14B model trained with GOPO achieves 2.7% and 1.5% higher TSE than Qwen-235B and GPT-5.2, respectively. Ablation studies confirm the Expert Agent's critical role in long-horizon optimization. GOPO demonstrates consistent improvements across other datasets as well. This work establishes a new paradigm for task-oriented dialogue systems in commercial scenarios, with code and datasets to be made public.

cs.CL↗

arXiv2026

The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey

The Driving World Model (DWM), which focuses on predicting scene evolution during the driving process, has emerged as a promising paradigm in the pursuit of autonomous driving (AD). DWMs enable AD systems to better perceive, understand, and interact with dynamic driving environments. In this survey, we provide a comprehensive overview of the latest progress in DWM. First, we review the DWM ecosystem, which is constructed using mainstream simulators, high-impact datasets, and various metrics that evaluate DWMs across multiple dimensions. We then categorize existing approaches based on the modalities of the predicted scenes, including video, point cloud, occupancy, latent feature, and traffic map, and summarize their specific applications in AD research. In addition, the performance of representative approaches across generating and driving tasks is presented. Finally, we discuss the potential limitations of current research and propose future directions. This survey provides valuable insights into the development and application of DWM, fostering its broader adoption in AD. The relevant papers are collected at https://github.com/LMD0311/Awesome-World-Model.

cs.CV↗

arXiv2026

A Pre-trained Foundation Model Framework for Multiplanar MRI Classification of Extramural Vascular Invasion and Mesorectal Fascia Invasion in Rectal Cancer

Objectives Accurate MRI-based identification of extramural vascular invasion (EVI) and mesorectal fascia invasion (MFI) is crucial for risk-stratified rectal cancer treatment. However, subjective visual assessment and inter-institutional variability limit diagnostic consistency. This study developed and externally evaluated a multi-centre, foundation model-driven framework that automatically classifies EVI and MFI on axial and sagittal MRI. Methods A total of 331 pre-treatment rectal cancer T2-weighted MRI scans from three European hospitals were retrospectively recruited. A self-supervised frequency domain harmonization strategy was applied to reduce scanner variability. Three classifiers, SeResNet, the universal biomedical pretrained model (UMedPT) with a multilayer perceptron head, and a logistic-regression variant using frozen UMedPT features (UMedPT_LR), were trained (n=265) and tested (n=66). Gradient-weighted class activation mapping (Grad-CAM) visualized model predictions. Results UMedPT_LR achieved the best EVI performance with multiplanar fusion (AUC=0.82, test set). For MFI, UMedPT trained on axial harmonized images yielded the highest performance (AUC = 0.77). Both tasks outperformed the CHAIMELEON 2024 benchmark (EVI: 0.82 vs 0.74; MFI: 0.77 vs 0.75). Harmonization enhanced MFI classification, and multiplanar fusion further boosted EVI performance. Grad-CAM confirmed biologically plausible attention on peritumoral regions (EVI) and mesorectal fascia margins (MFI). Conclusion The proposed foundation model-driven framework, leveraging frequency domain harmonization and multiplanar fusion, achieves state-of-the-art performance for automated EVI and MFI classification on MRI, demonstrating strong generalizability across multiple centers.

eess.IV↗

arXiv2026

Robust Multicentre Detection and Classification of Colorectal Liver Metastases on CT: Application of Foundation Models

Colorectal liver metastases (CRLM) are a major cause of cancer-related mortality, and reliable detection on CT remains challenging in multi-centre settings. We developed a foundation model-based AI pipeline for patient-level classification and lesion-level detection of CRLM on contrast-enhanced CT, integrating uncertainty quantification and explainability. CT data from the EuCanImage consortium (n=2437) and an external TCIA cohort (n=197) were used. Among several pretrained models, UMedPT achieved the best performance and was fine-tuned with an MLP head for classification and an FCOS-based head for lesion detection. The classification model achieved an AUC of 0.90 and a sensitivity of 0.82 on the combined test set, with a sensitivity of 0.85 on the external cohort. Excluding the most uncertain 20 percent of cases improved AUC to 0.91 and balanced accuracy to 0.86. Decision curve analysis showed clinical benefit for threshold probabilities between 0.30 and 0.40. The detection model identified 69.1 percent of lesions overall, increasing from 30 percent to 98 percent across lesion size quartiles. Grad-CAM highlighted lesion-corresponding regions in high-confidence cases. These results demonstrate that foundation model-based pipelines can support robust and interpretable CRLM detection and classification across heterogeneous CT data.

cs.CV↗

arXiv2026

Consensus in the Parliament of AI: Harmonized Multi-Region CT-Radiomics and Foundation-Model Signatures for Multicentre NSCLC Risk Stratification

Purpose: This study evaluates the impact of harmonization and multi-region feature integration on survival prediction in non-small cell lung cancer (NSCLC) patients. We assess the prognostic utility of handcrafted radiomics and pretrained deep features from thoracic CT images, integrating them with clinical data using a multicentre dataset. Methods: Survival models were built using handcrafted radiomic and deep features from lung, tumor, mediastinal nodes, coronary arteries, and coronary artery calcium (CAC) scores from 876 patients across five centres. CT features were harmonized using ComBat, reconstruction kernel normalization (RKN), and RKN-ComBat. Models were constructed at the region of interest (ROI) level and through ensemble strategies. Regularized Cox models estimated overall survival, with performance assessed via the concordance index (C-index), 5-year time-dependent area under the curve (t-AUC), and hazard ratios. SHAP values interpreted feature contributions, while consensus analysis categorized predicted survival probabilities at fixed time points. Results: TNM staging showed prognostic value (C-index = 0.67; hazard ratio = 2.70; t-AUC = 0.85). The clinical and tumor texture radiomics model with ComBat yielded high performance (C-index = 0.76; t-AUC = 0.88). FM deep features from 50 voxel cubes also showed predictive value (C-index = 0.76; t-AUC = 0.89). An ensemble model combining tumor, lung, mediastinal node, CAC, and FM features achieved a C-index of 0.71 and t-AUC of 0.79. Consensus analysis identified a high-confidence patient subset, resulting in a model with a 5-year t-AUC of 0.92, sensitivity of 96.8%, and specificity of 70.0%. Conclusion: Harmonization and multi-region feature integration enhance survival prediction in NSCLC patients using CT imaging, supporting individualized risk stratification in multicentre settings.

cs.CV↗

arXiv2025

A Uniform Pilot and Data Payload Optimization Framework for OTFS-Based ISAC

The orthogonal time frequency space (OTFS) signal is considered a promising solution for high-mobility wireless environments. It manages Doppler effects by utilizing delay-Doppler (DD) domain processing. However, the relatively long OTFS frame duration could introduce considerable sensing or communication latency when radar and communication are performed separately. By operating in a dual-functional radar and communication (DFRC) mode, the OTFS system performs sensing and data transmission simultaneously, thereby reducing the resulting latency. Nevertheless, the optimal OTFS DFRC signal strategy remains insufficiently explored. This paper investigates the optimal signal design for OTFS DFRC systems, focusing on pilot symbol design and data symbol power allocation. Specifically, we derive a channel capacity lower bound metric for communication that considers channel estimation errors in OTFS. For sensing, we derive an integrated sidelobe level (ISL), accounting for the randomness of the data symbols alongside the deterministic pilot symbols. Leveraging the above metrics, we formulate an optimization problem that balances radar and communication performance, and then solve it using an alternating optimization framework. We validate the proposed signal through numerical analysis and Monte Carlo simulations. Our analysis shows that OTFS DFRC enforces a deterministic pilot signal that is characterized by a concentrated peak in the DD domain, which furnishes a common structure in the DD domain facilitating sensing and channel estimation, with data multiplexed in other DD grids, thereby unifying sensing and communication within a single OTFS signal. Compared with conventional OTFS signals, the proposed OTFS DFRC signal expands the achievable sensing-communication performance region, delivering at least a 9.45 dB ISL suppression for sensing and a 4.82 dB SINR ratio gain for communication.

eess.SP↗

arXiv2025

Robust Design for Multi-Antenna LEO Satellite Communications with Fractional Delay and Doppler Shifts: An RSMA-OTFS Approach

Low-Earth-orbit (LEO) satellite communication systems face challenges due to high satellite mobility, which hinders the reliable acquisition of instantaneous channel state information at the transmitter (CSIT) and subsequently degrades multi-user transmission performance. This paper investigates a downlink multi-user multi-antenna system, and tackles the above challenges by introducing orthogonal time frequency space (OTFS) modulation and rate-splitting multiple access (RSMA) transmission. Specifically, OTFS enables stable characterization of time-varying channels by representing them in the delay-Doppler domain. However, realistic propagation introduces various inter-symbol and inter-user interference due to non-orthogonal yet practical rectangular pulse shaping, fractional delays, Doppler shifts, and imperfect (statistical) CSIT. In this context, RSMA offers promising robustness for interference mitigation and CSIT imperfections, and hence is integrated with OTFS to provide a comprehensive solution. A compact cross-domain input-output relationship for RSMA-OTFS is established, and an ergodic sum-rate maximization problem is formulated and solved using a weighted minimum mean-square-error based alternating optimization algorithm that does not depend on channel sparsity. Simulation results reveal that the considered practical propagation effects significantly degrade performance if unaddressed. Furthermore, the RSMA-OTFS scheme demonstrates improved ergodic sum-rate and robustness against CSIT uncertainty across various user deployments and CSIT qualities.

eess.SP↗

arXiv2025

A Novel Pilot Scheme for Uplink Channel Estimation for Sub-array Structured ELAA in XL-MIMO systems

This paper proposes a novel pilot scheme for multi-user uplink channel estimation in extra-large-scale massive MIMO (XL-MIMO) systems with extremely large aperture arrays (ELAA). The large aperture of ELAA introduces spatial non-stationarity, where far-apart users have significantly distinct visibility at the antennas, thereby reducing inter-user interference. This insight motivates our novel pilot scheme to group users with distinct visibility regions to share the same frequency subcarriers for channel estimation, so that more users can be served with reduced pilot overhead. Specifically, the proposed pilot scheme employs frequency-division multiplexing for inter-group channel estimation, while intra-group users -- benefiting from strong spatial orthogonality -- are distinguished by shifted cyclic codes, similar to code-division multiplexing. Additionally, we introduce a sub-array structured ELAA, where each sub-array is a traditional MIMO array and treated as spatial stationary, while the distances between sub-arrays can be significantly larger to achieve an expanded aperture. The channel support for sub-arrays features clustered sparsity in the antenna-delay domain and is modeled by a 2-dimensional (2-D) Markov random field (MRF). Based on this, we propose a low-complexity channel estimation algorithm within a turbo Bayesian inference framework that incorporates the 2-D MRF prior model. Simulations show that the proposed scheme and algorithm allow the XL-MIMO system to support more users, and deliver superior channel estimation performance.

eess.SP↗

arXiv2025

CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks

Large Vision-Language Models (LVLMs) have demonstrated remarkable success in a broad range of vision-language tasks, such as general visual question answering and optical character recognition (OCR). However, their performance on perception-centric tasks -- such as object detection, semantic segmentation, and depth estimation -- remains significantly inferior to that of task-specific expert models. For example, Qwen2.5-VL-7B-Instruct achieves only 19% mAP on COCO2017 val, particularly struggling with dense scenes and small object recall. In this work, we introduce Chain-of-Thought for Detection (CoT4Det), a simple but efficient strategy that reformulates perception tasks into three interpretable steps: classification, counting, and grounding -- each more naturally aligned with the reasoning capabilities of LVLMs. Extensive experiments demonstrate that our method significantly improves perception performance without compromising general vision language capabilities. With a standard Qwen2.5-VL-7B-Instruct, CoT4Det boosts mAP from 19.0% to 33.0% on COCO2017 val and achieves competitive results across a variety of perception benchmarks, outperforming baselines by +2% on RefCOCO series and 19% on Flickr30k entities.

cs.CV↗

arXiv2025

Video4Edit: Viewing Image Editing as a Degenerate Temporal Process

We observe that recent advances in multimodal foundation models have propelled instruction-driven image generation and editing into a genuinely cross-modal, cooperative regime. Nevertheless, state-of-the-art editing pipelines remain costly: beyond training large diffusion/flow models, they require curating massive high-quality triplets of \{instruction, source image, edited image\} to cover diverse user intents. Moreover, the fidelity of visual replacements hinges on how precisely the instruction references the target semantics. We revisit this challenge through the lens of temporal modeling: if video can be regarded as a full temporal process, then image editing can be seen as a degenerate temporal process. This perspective allows us to transfer single-frame evolution priors from video pre-training, enabling a highly data-efficient fine-tuning regime. Empirically, our approach matches the performance of leading open-source baselines while using only about one percent of the supervision demanded by mainstream editing models.

cs.CV↗

arXiv2025

Signal Design for OTFS Dual-Functional Radar and Communications with Imperfect CSI

Orthogonal time frequency space (OTFS) offers significant advantages in managing mobility for both wireless sensing and communication systems, making it a promising candidate for dual-functional radar-communication (DFRC). However, the optimal signal design that fully exploits OTFS's potential in DFRC has not been sufficiently explored. This paper addresses this gap by formulating an optimization problem for signal design in DFRC-OTFS, incorporating both pilot-symbol design for channel estimation and data-power allocation. Specifically, we employ the integrated sidelobe level (ISL) of the ambiguity function as a radar metric, accounting for the randomness of the data symbols alongside the deterministic pilot symbols. For communication, we derive a channel capacity lower bound metric that considers channel estimation errors in OTFS. We maximize the weighted sum of sensing and communication metrics and solve the optimization problem via an alternating optimization framework. Simulations indicate that the proposed signal significantly improves the sensing-communication performance region compared with conventional signal schemes, achieving at least a 9.44 dB gain in ISL suppression for sensing, and a 4.82 dB gain in the signal-to-interference-plus-noise ratio (SINR) for communication.

eess.SP↗

arXiv2025

LISAC: Learned Coded Waveform Design for ISAC with OFDM

We propose deep learning based coded waveform design for integrated sensing and communication (ISAC) with orthogonal frequency-division multiplexing (OFDM). Our goal is to design a coded waveform capable of delivering accurate target parameter estimation while maintaining high communication quality measured in terms of bit error rate (BER). In the proposed learned coded waveform for ISAC (LISAC), the pilot and data encoding functions at the encoder are parameterized by recurrent neural networks (RNNs) and are trained jointly in an end-to-end fashion. The communication receiver estimates the channel and performs residual-assisted minimum mean square error (MMSE) channel equalization, where a neural network is introduced to calibrate the coarse estimate produced by the standard MMSE channel equalizer. Then, an RNN-based channel decoder is employed to decode the information bits using the equalized signal. Two different sensing loss functions are considered, one calculates the mean square error (MSE) between the original and the estimated sensing parameters, while the other calculates the Cramer-Rao lower bound (CRLB). The LISAC modules are optimized using a weighted combination of communication and sensing losses and different trade-off points between the sensing and communication performances are achieved by adjusting the weights. Simulation results show that the proposed LISAC waveform achieves a better trade-off curve compared to existing alternatives for both AWGN and multi-path fading scenarios. Ablation studies are carried out to demonstrate the gain brought by each design component for a better understanding of the proposed scheme.

eess.SP↗

arXiv2025

Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning

Recently, leveraging pre-training techniques to enhance point cloud models has become a prominent research topic. However, existing approaches typically require full fine-tuning of pre-trained models to achieve satisfactory performance on downstream tasks, which is storage-intensive and computationally demanding. To address this issue, we propose a novel Parameter-Efficient Fine-Tuning (PEFT) method for point cloud, called \textbf{PointGST} (\textbf{Point} cloud \textbf{G}raph \textbf{S}pectral \textbf{T}uning). PointGST freezes the pre-trained model and introduces a lightweight, trainable Point Cloud Spectral Adapter (PCSA) for fine-tuning parameters in the spectral domain. The core idea is built on two observations: 1) The inner tokens from frozen models might present confusion in the spatial domain; 2) Task-specific intrinsic information is important for transferring the general knowledge to the downstream task. Specifically, PointGST transfers the point tokens from the spatial domain to the spectral domain, effectively de-correlating confusion among tokens by using orthogonal components for separation. Moreover, the generated spectral basis involves intrinsic information about the downstream point clouds, enabling more targeted tuning. As a result, PointGST facilitates the efficient transfer of general knowledge to downstream tasks while significantly reducing training costs. Extensive experiments on challenging point cloud datasets across various tasks demonstrate that PointGST not only outperforms its fully fine-tuning counterpart but also significantly reduces trainable parameters, making it a promising solution for efficient point cloud learning. The code will be made available at https://github.com/jerryfeng2003/PointGST

cs.CV↗

arXiv2025

An Interpretable AI framework Quantifying Traditional Chinese Medicine Principles Towards Enhancing and Integrating with Modern Biomedicine

Traditional Chinese Medicine diagnosis and treatment principles, established through centuries of trial-and-error clinical practice, directly maps patient-specific symptom patterns to personalised herbal therapies. These empirical holistic mapping principles offer valuable strategies to address remaining challenges of reductionism methodologies in modern biomedicine. However, the lack of a quantitative framework and molecular-level evidence has limited their interpretability and reliability. Here, we present an AI framework trained on ancient and classical TCM formula records to quantify the symptom pattern-herbal therapy mappings. Interestingly, we find that empirical TCM diagnosis and treatment are consistent with the encoding-decoding processes in the AI model. This enables us to construct an interpretable TCM embedding space (TCM-ES) using the model's quantitative representation of TCM principles. Validated through broad and extensive TCM patient data, the TCM-ES offers universal quantification of the TCM practice and therapeutic efficacy. We further map biomedical entities into the TCM-ES through correspondence alignment. We find that the principal directions of the TCM-ES are significantly associated with key biological functions (such as metabolism, immune, and homeostasis), and that the disease and herb embedding proximity aligns with their genetic relationships in the human protein interactome, which demonstrate the biological significance of TCM principles. Moreover, the TCM-ES uncovers latent disease relationships, and provides alternative metric to assess clinical efficacy for modern disease-drug pairs. Finally, we construct a comprehensive and integrative TCM knowledge graph, which predicts potential associations between diseases and targets, drugs, herbal compounds, and herbal therapies, providing TCM-informed opportunities for disease analysis and drug development.

q-bio.OT↗

arXiv2025

Explainable Anatomy-Guided AI for Prostate MRI: Foundation Models and In Silico Clinical Trials for Virtual Biopsy-based Risk Assessment

We present a fully automated, anatomically guided deep learning pipeline for prostate cancer (PCa) risk stratification using routine MRI. The pipeline integrates three key components: an nnU-Net module for segmenting the prostate gland and its zones on axial T2-weighted MRI; a classification module based on the UMedPT Swin Transformer foundation model, fine-tuned on 3D patches with optional anatomical priors and clinical data; and a VAE-GAN framework for generating counterfactual heatmaps that localize decision-driving image regions. The system was developed using 1,500 PI-CAI cases for segmentation and 617 biparametric MRIs with metadata from the CHAIMELEON challenge for classification (split into 70% training, 10% validation, and 20% testing). Segmentation achieved mean Dice scores of 0.95 (gland), 0.94 (peripheral zone), and 0.92 (transition zone). Incorporating gland priors improved AUC from 0.69 to 0.72, with a three-scale ensemble achieving top performance (AUC = 0.79, composite score = 0.76), outperforming the 2024 CHAIMELEON challenge winners. Counterfactual heatmaps reliably highlighted lesions within segmented regions, enhancing model interpretability. In a prospective multi-center in-silico trial with 20 clinicians, AI assistance increased diagnostic accuracy from 0.72 to 0.77 and Cohen's kappa from 0.43 to 0.53, while reducing review time per case by 40%. These results demonstrate that anatomy-aware foundation models with counterfactual explainability can enable accurate, interpretable, and efficient PCa risk assessment, supporting their potential use as virtual biopsies in clinical practice.

eess.IV↗