arXiv subjects

Ziyu Wang

Publications and source records attributed to Ziyu Wang.

At least 73 records · Page 4Linked to original sources

arXiv2025

autoPET IV challenge: Incorporating organ supervision and human guidance for lesion segmentation in PET/CT

Lesion Segmentation in PET/CT scans is an essential part of modern oncological workflows. To address the challenges of time-intensive manual annotation and high inter-observer variability, the autoPET challenge series seeks to advance automated segmentation methods in complex multi-tracer and multi-center settings. Building on this foundation, autoPET IV introduces a human-in-the-loop scenario to efficiently utilize interactive human guidance in segmentation tasks. In this work, we incorporated tracer classification, organ supervision and simulated clicks guidance into the nnUNet Residual Encoder framework, forming an integrated pipeline that demonstrates robust performance in a fully automated (zero-guidance) context and efficiently leverages iterative interactions to progressively enhance segmentation accuracy.

eess.IV↗

arXiv2025

MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering

Large language models (LLMs) have shown promise in medical question answering but often struggle with hallucinations and shallow reasoning, particularly in tasks requiring nuanced clinical understanding. Retrieval-augmented generation (RAG) offers a practical and privacy-preserving way to enhance LLMs with external medical knowledge. However, most existing approaches rely on surface-level semantic retrieval and lack the structured reasoning needed for clinical decision support. We introduce MedCoT-RAG, a domain-specific framework that combines causal-aware document retrieval with structured chain-of-thought prompting tailored to medical workflows. This design enables models to retrieve evidence aligned with diagnostic logic and generate step-by-step causal reasoning reflective of real-world clinical practice. Experiments on three diverse medical QA benchmarks show that MedCoT-RAG outperforms strong baselines by up to 10.3% over vanilla RAG and 6.4% over advanced domain-adapted methods, improving accuracy, interpretability, and consistency in complex medical tasks.

cs.CL↗

arXiv2025

Linkage Attacks Expose Identity Risks in Public ECG Data Sharing

The increasing availability of publicly shared electrocardiogram (ECG) data raises critical privacy concerns, as its biometric properties make individuals vulnerable to linkage attacks. Unlike prior studies that assume idealized adversarial capabilities, we evaluate ECG privacy risks under realistic conditions where attackers operate with partial knowledge. Using data from 109 participants across diverse real-world datasets, our approach achieves 85% accuracy in re-identifying individuals in public datasets while maintaining a 14.2% overall misclassification rate at an optimal confidence threshold, with 15.6% of unknown individuals misclassified as known and 12.8% of known individuals misclassified as unknown. These results highlight the inadequacy of simple anonymization techniques in preventing re-identification, demonstrating that even limited adversarial knowledge enables effective identity linkage. Our findings underscore the urgent need for privacy-preserving strategies, such as differential privacy, access control, and encrypted computation, to mitigate re-identification risks while ensuring the utility of shared biosignal data in healthcare applications.

cs.CR↗

arXiv2025

Real-World Offline Reinforcement Learning from Vision Language Model Feedback

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert demonstrations is slow, costly, and risky. However, most existing offline RL works assume the dataset is already labeled with the task rewards, a process that often requires significant human effort, especially when ground-truth states are hard to ascertain (e.g., in the real-world). In this paper, we build on prior work, specifically RL-VLM-F, and propose a novel system that automatically generates reward labels for offline datasets using preference feedback from a vision-language model and a text description of the task. Our method then learns a policy using offline RL with the reward-labeled dataset. We demonstrate the system's applicability to a complex real-world robot-assisted dressing task, where we first learn a reward function using a vision-language model on a sub-optimal offline dataset, and then we use the learned reward to employ Implicit Q learning to develop an effective dressing policy. Our method also performs well in simulation tasks involving the manipulation of rigid and deformable objects, and significantly outperform baselines such as behavior cloning and inverse RL. In summary, we propose a new system that enables automatic reward labeling and policy learning from unlabeled, sub-optimal offline datasets.

cs.RO↗

arXiv2025

Automatic Melody Reduction via Shortest Path Finding

Melody reduction, as an abstract representation of musical compositions, serves not only as a tool for music analysis but also as an intermediate representation for structured music generation. Prior computational theories, such as the Generative Theory of Tonal Music, provide insightful interpretations of music, but they are not fully automatic and usually limited to the classical genre. In this paper, we propose a novel and conceptually simple computational method for melody reduction using a graph-based representation inspired by principles from computational music theories, where the reduction process is formulated as finding the shortest path. We evaluate our algorithm on pop, folk, and classical genres, and experimental results show that the algorithm produces melody reductions that are more faithful to the original melody and more musically coherent than other common melody downsampling methods. As a downstream task, we use melody reductions to generate symbolic music variations. Experiments show that our method achieves higher quality than state-of-the-art style transfer methods.

cs.SD↗

arXiv2025

Can Optical Denoising Clean Sonar Images? A Benchmark and Fusion Approach

Object detection in sonar images is crucial for underwater robotics applications including autonomous navigation and resource exploration. However, complex noise patterns inherent in sonar imagery, particularly speckle, reverberation, and non-Gaussian noise, significantly degrade detection accuracy. While denoising techniques have achieved remarkable success in optical imaging, their applicability to sonar data remains underexplored. This study presents the first systematic evaluation of nine state-of-the-art deep denoising models with distinct architectures, including Neighbor2Neighbor with varying noise parameters, Blind2Unblind with different noise configurations, and DSPNet, for sonar image preprocessing. We establish a rigorous benchmark using five publicly available sonar datasets and assess their impact on four representative detection algorithms: YOLOX, Faster R-CNN, SSD300, and SSDMobileNetV2. Our evaluation addresses three unresolved questions: first, how effectively optical denoising architectures transfer to sonar data; second, which model families perform best against sonar noise; and third, whether denoising truly improves detection accuracy in practical pipelines. Extensive experiments demonstrate that while denoising generally improves detection performance, effectiveness varies across methods due to their inherent biases toward specific noise types. To leverage complementary denoising effects, we propose a mutually-supervised multi-source denoising fusion framework where outputs from different denoisers mutually supervise each other at the pixel level, creating a synergistic framework that produces cleaner images.

cs.CV↗

arXiv2025

High-Resolution Sustain Pedal Depth Estimation from Piano Audio Across Room Acoustics

Piano sustain pedal detection has previously been approached as a binary on/off classification task, limiting its application in real-world piano performance scenarios where pedal depth significantly influences musical expression. This paper presents a novel approach for high-resolution estimation that predicts continuous pedal depth values. We introduce a Transformer-based architecture that not only matches state-of-the-art performance on the traditional binary classification task but also achieves high accuracy in continuous pedal depth estimation. Furthermore, by estimating continuous values, our model provides musically meaningful predictions for sustain pedal usage, whereas baseline models struggle to capture such nuanced expressions with their binary detection approach. Additionally, this paper investigates the influence of room acoustics on sustain pedal estimation using a synthetic dataset that includes varied acoustic conditions. We train our model with different combinations of room settings and test it in an unseen new environment using a "leave-one-out" approach. Our findings show that the two baseline models and ours are not robust to unseen room conditions. Statistical analysis further confirms that reverberation influences model predictions and introduces an overestimation bias.

cs.SD↗

arXiv2025

TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure

Hierarchical planning is a powerful approach to model long sequences structurally. Aside from considering hierarchies in the temporal structure of music, this paper explores an even more important aspect: concept hierarchy, which involves generating music ideas, transforming them, and ultimately organizing them--across musical time and space--into a complete composition. To this end, we introduce TOMI (Transforming and Organizing Music Ideas) as a novel approach in deep music generation and develop a TOMI-based model via instruction-tuned foundation LLM. Formally, we represent a multi-track composition process via a sparse, four-dimensional space characterized by clips (short audio or MIDI segments), sections (temporal positions), tracks (instrument layers), and transformations (elaboration methods). Our model is capable of generating multi-track electronic music with full-song structure, and we further integrate the TOMI-based model with the REAPER digital audio workstation, enabling interactive human-AI co-creation. Experimental results demonstrate that our approach produces higher-quality electronic music with stronger structural coherence compared to baselines.

cs.SD↗

arXiv2025

FairCauseSyn: Towards Causally Fair LLM-Augmented Synthetic Data Generation

Synthetic data generation creates data based on real-world data using generative models. In health applications, generating high-quality data while maintaining fairness for sensitive attributes is essential for equitable outcomes. Existing GAN-based and LLM-based methods focus on counterfactual fairness and are primarily applied in finance and legal domains. Causal fairness provides a more comprehensive evaluation framework by preserving causal structure, but current synthetic data generation methods do not address it in health settings. To fill this gap, we develop the first LLM-augmented synthetic data generation method to enhance causal fairness using real-world tabular health data. Our generated data deviates by less than 10% from real data on causal fairness metrics. When trained on causally fair predictors, synthetic data reduces bias on the sensitive attribute by 70% compared to real data. This work improves access to fair synthetic data, supporting equitable health research and healthcare delivery.

cs.LG↗

arXiv2025

DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning

This paper introduces DiffTORI, which utilizes Differentiable Trajectory Optimization as the policy representation to generate actions for deep Reinforcement and Imitation learning. Trajectory optimization is a powerful and widely used algorithm in control, parameterized by a cost and a dynamics function. The key to our approach is to leverage the recent progress in differentiable trajectory optimization, which enables computing the gradients of the loss with respect to the parameters of trajectory optimization. As a result, the cost and dynamics functions of trajectory optimization can be learned end-to-end. DiffTORI addresses the ``objective mismatch'' issue of prior model-based RL algorithms, as the dynamics model in DiffTORI is learned to directly maximize task performance by differentiating the policy gradient loss through the trajectory optimization process. We further benchmark DiffTORI for imitation learning on standard robotic manipulation task suites with high-dimensional sensory observations and compare our method to feed-forward policy classes as well as Energy-Based Models (EBM) and Diffusion. Across 15 model-based RL tasks and 35 imitation learning tasks with high-dimensional image and point cloud inputs, DiffTORI outperforms prior state-of-the-art methods in both domains. Our code is available at https://github.com/wkwan7/DiffTORI.

cs.LG↗

arXiv2025

PPTNet: A Hybrid Periodic Pattern-Transformer Architecture for Traffic Flow Prediction and Congestion Identification

Accurate prediction of traffic flow parameters and real time identification of congestion states are essential for the efficient operation of intelligent transportation systems. This paper proposes a Periodic Pattern Transformer Network (PPTNet) for traffic flow prediction, integrating periodic pattern extraction with the Transformer architecture, coupled with a fuzzy inference method for real-time congestion identification. Firstly, a high-precision traffic flow dataset (Traffic Flow Dataset for China's Congested Highways and Expressways, TF4CHE) suitable for congested highway scenarios in China is constructed based on drone aerial imagery data. Subsequently, the proposed PPTNet employs Fast Fourier Transform to capture multi-scale periodic patterns and utilizes two-dimensional Inception convolutions to efficiently extract intra and inter periodic features. A Transformer decoder dynamically models temporal dependencies, enabling accurate predictions of traffic density and speed. Finally, congestion probabilities are calculated in real-time using the predicted outcomes via a Mamdani fuzzy inference-based congestion identification module. Experimental results demonstrate that the proposed PPTNet significantly outperforms mainstream traffic prediction methods in prediction accuracy, and the congestion identification module effectively identifies real-time road congestion states, verifying the superiority and practicality of the proposed method in real-world traffic scenarios. Project page: https://github.com/ADSafetyJointLab/PPTNet.

cs.LG↗

arXiv2025

Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts

Diffusion models have emerged as mainstream framework in visual generation. Building upon this success, the integration of Mixture of Experts (MoE) methods has shown promise in enhancing model scalability and performance. In this paper, we introduce Race-DiT, a novel MoE model for diffusion transformers with a flexible routing strategy, Expert Race. By allowing tokens and experts to compete together and select the top candidates, the model learns to dynamically assign experts to critical tokens. Additionally, we propose per-layer regularization to address challenges in shallow layer learning, and router similarity loss to prevent mode collapse, ensuring better expert utilization. Extensive experiments on ImageNet validate the effectiveness of our approach, showcasing significant performance gains while promising scaling properties.

cs.CV↗

arXiv2025

Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation

Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch. To address these challenges, we introduce an efficient Fine-Grained Guidance (FGG) approach within diffusion models. FGG guides the diffusion models to generate music that aligns more closely with the control and intent of expert composers, which is critical to improve the accuracy, listenability, and quality of generated music. This approach empowers diffusion models to excel in advanced applications such as improvisation, and interactive music creation. We derive theoretical characterizations for both the challenges in symbolic music generation and the effects of the FGG approach. We provide numerical experiments and subjective evaluation to demonstrate the effectiveness of our approach. We have published a demo page to showcase performances, which enables real-time interactive generation.

cs.SD↗

arXiv2025

UniSTPA: A Safety Analysis Framework for End-to-End Autonomous Driving

As autonomous driving technology continues to advance, end-to-end models have attracted considerable attention owing to their superior generalisation capability. Nevertheless, such learning-based systems entail numerous safety risks throughout development and on-road deployment, and existing safety-analysis methods struggle to identify these risks comprehensively. To address this gap, we propose the Unified System Theoretic Process Analysis (UniSTPA) framework, which extends the scope of STPA from the operational phase to the entire lifecycle of an end-to-end autonomous driving system, including information gathering, data preparation, closed loop training, verification, and deployment. UniSTPA performs hazard analysis not only at the component level but also within the model's internal layers, thereby enabling fine-grained assessment of inter and intra module interactions. Using a highway Navigate on Autopilot function as a case study, UniSTPA uncovers multi-stage hazards overlooked by conventional approaches including scene design defects, sensor fusion biases, and internal model flaws, through multi-level causal analysis, traces these hazards to deeper issues such as data quality, network architecture, and optimisation objectives. The analysis result are used to construct a safety monitoring and safety response mechanism that supports continuous improvement from hazard identification to system optimisation. The proposed framework thus offers both theoretical and practical guidance for the safe development and deployment of end-to-end autonomous driving systems.

cs.RO↗

arXiv2025

ArticuBot: Learning Universal Articulated Object Manipulation Policy via Large Scale Simulation

This paper presents ArticuBot, in which a single learned policy enables a robotics system to open diverse categories of unseen articulated objects in the real world. This task has long been challenging for robotics due to the large variations in the geometry, size, and articulation types of such objects. Our system, Articubot, consists of three parts: generating a large number of demonstrations in physics-based simulation, distilling all generated demonstrations into a point cloud-based neural policy via imitation learning, and performing zero-shot sim2real transfer to real robotics systems. Utilizing sampling-based grasping and motion planning, our demonstration generalization pipeline is fast and effective, generating a total of 42.3k demonstrations over 322 training articulated objects. For policy learning, we propose a novel hierarchical policy representation, in which the high-level policy learns the sub-goal for the end-effector, and the low-level policy learns how to move the end-effector conditioned on the predicted goal. We demonstrate that this hierarchical approach achieves much better object-level generalization compared to the non-hierarchical version. We further propose a novel weighted displacement model for the high-level policy that grounds the prediction into the existing 3D structure of the scene, outperforming alternative policy representations. We show that our learned policy can zero-shot transfer to three different real robot settings: a fixed table-top Franka arm across two different labs, and an X-Arm on a mobile base, opening multiple unseen articulated objects across two labs, real lounges, and kitchens. Videos and code can be found on our project website: https://articubot.github.io/.

cs.RO↗

arXiv2025

CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on semantic similarity and correlation-driven retrieval, limiting their ability to distinguish true causal relationships from spurious associations. This results in responses that may be factually grounded but fail to establish cause-and-effect mechanisms, leading to incomplete or misleading insights. To address this issue, we introduce Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation (CDF-RAG), a framework designed to improve causal consistency, factual accuracy, and explainability in generative reasoning. CDF-RAG iteratively refines queries, retrieves structured causal graphs, and enables multi-hop causal reasoning across interconnected knowledge sources. Additionally, it validates responses against causal pathways, ensuring logically coherent and factually grounded outputs. We evaluate CDF-RAG on four diverse datasets, demonstrating its ability to improve response accuracy and causal correctness over existing RAG-based methods. Our code is publicly available at https://github.com/ elakhatibi/CDF-RAG.

cs.CL↗

arXiv2025

Accelerating Multi-Objective Collaborative Optimization of Doped Thermoelectric Materials via Artificial Intelligence

The thermoelectric performance of materials exhibits complex nonlinear dependencies on both elemental types and their proportions, rendering traditional trial-and-error approaches inefficient and time-consuming for material discovery. In this work, we present a deep learning model capable of accurately predicting thermoelectric properties of doped materials directly from their chemical formulas, achieving state-of-the-art performance. To enhance interpretability, we further incorporate sensitivity analysis techniques to elucidate how physical descriptors affect the thermoelectric figure of merit (zT). Moreover, we establish a coupled framework that integrates a surrogate model with a multi-objective genetic algorithm to efficiently explore the vast compositional space for high-performance candidates. Experimental validation confirms the discovery of a novel thermoelectric material with superior $zT$ values in the medium-temperature regime.

cond-mat.mtrl-sci↗

arXiv2025

Synthetic Video Enhances Physical Fidelity in Video Synthesis

We investigate how to enhance the physical fidelity of video generation models by leveraging synthetic videos derived from computer graphics pipelines. These rendered videos respect real-world physics, such as maintaining 3D consistency, and serve as a valuable resource that can potentially improve video generation models. To harness this potential, we propose a solution that curates and integrates synthetic data while introducing a method to transfer its physical realism to the model, significantly reducing unwanted artifacts. Through experiments on three representative tasks emphasizing physical consistency, we demonstrate its efficacy in enhancing physical fidelity. While our model still lacks a deep understanding of physics, our work offers one of the first empirical demonstrations that synthetic video enhances physical fidelity in video synthesis. Website: https://kevinz8866.github.io/simulation/

eess.IV↗