arXiv subjects

Ziyang He

Publications and source records attributed to Ziyang He.

11 recordsLinked to original sources

arXiv2026

LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

This paper presents a review for the LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aimed to advance research on real-world all-in-one image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provided a unified benchmark to evaluate the robustness and generalization ability of restoration models across multiple degradation categories within a common framework. The competition attracted 124 registered participants and received 9 valid final submissions with corresponding fact sheets, significantly contributing to the progress of real-world all-in-one image restoration. This report provides a detailed analysis of the submitted methods and corresponding results, emphasizing recent progress in unified real-world image restoration. The analysis highlights effective approaches and establishes a benchmark for future research in real-world low-level vision.

cs.CV↗

arXiv2025

TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering

While large language models (LLMs) have shown promise in the table question answering (TQA) task through prompt engineering, they face challenges in industrial applications, including structural heterogeneity, difficulties in target data localization, and bottlenecks in complex reasoning. To address these limitations, this paper presents TableZoomer, a novel LLM-powered, programming-based agent framework. It introduces three key innovations: (1) replacing the original fully verbalized table with structured table schema to bridge the semantic gap and reduce computational complexity; (2) a query-aware table zooming mechanism that dynamically generates sub-table schema through column selection and entity linking, significantly improving target localization efficiency; and (3) a Program-of-Thoughts (PoT) strategy that transforms queries into executable code to mitigate numerical hallucination. Additionally, we integrate the reasoning workflow with the ReAct paradigm to enable iterative reasoning. Extensive experiments demonstrate that our framework maintains the usability advantages while substantially enhancing performance and scalability across tables of varying scales. When implemented with the Qwen3-8B-Instruct LLM, TableZoomer achieves accuracy improvements of 19.34% and 25% over conventional PoT methods on the large-scale DataBench dataset and the small-scale Fact Checking task of TableBench dataset, respectively.

cs.CL↗

arXiv2025

GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging

Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evaluate code agents in such authentic, workflow-driven scenarios. To bridge this gap, we introduce GitTaskBench, a benchmark designed to systematically assess this capability via 54 realistic tasks across 7 modalities and 7 domains. Each task pairs a relevant repository with an automated, human-curated evaluation harness specifying practical success criteria. Beyond measuring execution and task success, we also propose the alpha-value metric to quantify the economic benefit of agent performance, which integrates task success rates, token cost, and average developer salaries. Experiments across three state-of-the-art agent frameworks with multiple advanced LLMs show that leveraging code repositories for complex task solving remains challenging: even the best-performing system, OpenHands+Claude 3.7, solves only 48.15% of tasks (recent progress has pushed the frontier further, with RepoMaster+Claude 3.5 achieving a new record of 62.96%). Error analysis attributes over half of failures to seemingly mundane yet critical steps like environment setup and dependency resolution, highlighting the need for more robust workflow management and increased timeout preparedness. By releasing GitTaskBench, we aim to drive progress and attention toward repository-aware code reasoning, execution, and deployment -- moving agents closer to solving complex, end-to-end real-world tasks. The benchmark and code are open-sourced at https://github.com/QuantaAlpha/GitTaskBench.

cs.SE↗

arXiv2025

RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks typically demand full-fledged code repositories rather than simple scripts. Building such repositories from scratch remains a major challenge. Fortunately, GitHub hosts a vast, evolving collection of open-source repositories, which developers frequently reuse as modular components for complex tasks. Yet, existing frameworks like OpenHands and SWE-Agent still struggle to effectively leverage these valuable resources. Relying solely on README files provides insufficient guidance, and deeper exploration reveals two core obstacles: overwhelming information and tangled dependencies of repositories, both constrained by the limited context windows of current LLMs. To tackle these issues, we propose RepoMaster, an autonomous agent framework designed to explore and reuse GitHub repositories for solving complex tasks. For efficient understanding, RepoMaster constructs function-call graphs, module-dependency graphs, and hierarchical code trees to identify essential components, providing only identified core elements to the LLMs rather than the entire repository. During autonomous execution, it progressively explores related components using our exploration tools and prunes information to optimize context usage. Evaluated on the adjusted MLE-bench, RepoMaster achieves a 110% relative boost in valid submissions over the strongest baseline OpenHands. On our newly released GitTaskBench, RepoMaster lifts the task-pass rate from 40.7% to 62.9% while reducing token usage by 95%. Our code and demonstration materials are publicly available at https://github.com/QuantaAlpha/RepoMaster.

cs.SE↗

arXiv2024

Secure Traffic Sign Recognition: An Attention-Enabled Universal Image Inpainting Mechanism against Light Patch Attacks

Traffic sign recognition systems play a crucial role in assisting drivers to make informed decisions while driving. However, due to the heavy reliance on deep learning technologies, particularly for future connected and autonomous driving, these systems are susceptible to adversarial attacks that pose significant safety risks to both personal and public transportation. Notably, researchers recently identified a new attack vector to deceive sign recognition systems: projecting well-designed adversarial light patches onto traffic signs. In comparison with traditional adversarial stickers or graffiti, these emerging light patches exhibit heightened aggression due to their ease of implementation and outstanding stealthiness. To effectively counter this security threat, we propose a universal image inpainting mechanism, namely, SafeSign. It relies on attention-enabled multi-view image fusion to repair traffic signs contaminated by adversarial light patches, thereby ensuring the accurate sign recognition. Here, we initially explore the fundamental impact of malicious light patches on the local and global feature spaces of authentic traffic signs. Then, we design a binary mask-based U-Net image generation pipeline outputting diverse contaminated sign patterns, to provide our image inpainting model with needed training data. Following this, we develop an attention mechanism-enabled neural network to jointly utilize the complementary information from multi-view images to repair contaminated signs. Finally, extensive experiments are conducted to evaluate SafeSign's effectiveness in resisting potential light patch-based attacks, bringing an average accuracy improvement of 54.8% in three widely-used sign recognition models

cs.CV↗

arXiv2024

A Continuous sEMG-Based Prosthetic Hand Control System Without Motion or Force Sensors

Regressively-based surface electromyography (sEMG) prosthetics are widely used for their ability to continuously convert muscle activity into finger force and motion. However, they typically require additional kinematic or dynamic sensors, which increases complexity and limits practical application. To address this, this paper proposes a method based on the simplified near-linear relationship between sEMG and finger force, using the near-linear model ResDD proposed in this work. By applying the principle that a line can be determined by two points, we eliminate the need for complex sensor calibration. Specifically, by recording the sEMG during maximum finger flexion and extension, and assigning corresponding forces of 1 and -1, the ResDD model can fit the simplified relationship between sEMG signals and force, enabling continuous prediction and control of finger force and gestures. Offline experiments were conducted to evaluate the model's classification accuracy and its ability to learn sufficient information. It uses interpolation analysis to open up the internal structure of the trained model and checks whether the fitted curve of the model conforms to the nearly linear relationship between sEMG and force. Finally, online control and sine wave tracking experiments were carried out to further verify the practicality of the proposed method. The results show that the method effectively extracts meaningful information from sEMG and accurately decodes them. The near-linear model sufficiently reflects the expected relationship between sEMG and finger force. Fitting this simplified near-linear relationship is adequate to achieve continuous and smooth control of finger force and gestures, confirming the feasibility and effectiveness of the proposed approach.

cs.RO↗

arXiv2024

Security Analysis of WiFi-based Sensing Systems: Threats from Perturbation Attacks

Deep learning technologies are pivotal in enhancing the performance of WiFi-based wireless sensing systems. However, they are inherently vulnerable to adversarial perturbation attacks, and regrettably, there is lacking serious attention to this security issue within the WiFi sensing community. In this paper, we elaborate such an attack, called WiIntruder, distinguishing itself with universality, robustness, and stealthiness, which serves as a catalyst to assess the security of existing WiFi-based sensing systems. This attack encompasses the following salient features: (1) Maximizing transferability by differentiating user-state-specific feature spaces across sensing models, leading to a universally effective perturbation attack applicable to common applications; (2) Addressing perturbation signal distortion caused by device synchronization and wireless propagation when critical parameters are optimized through a heuristic particle swarm-driven perturbation generation algorithm; and (3) Enhancing attack pattern diversity and stealthiness through random switching of perturbation surrogates generated by a generative adversarial network. Extensive experimental results confirm the practical threats of perturbation attacks to common WiFi-based services, including user authentication and respiratory monitoring.

cs.CR↗

arXiv2024

Autonomous Guidewire Navigation for Robot-assisted Endovascular Interventions: A Knowledge-Driven Visual Guidance Approach

Autonomous robots for endovascular interventions hold significant potential to enhance procedural safety and reliability by navigating guidewires with precision, minimizing human error, and reducing surgical time. However, existing methods of guidewire navigation rely on manual demonstration data and have a suboptimal success rate. In this work, we propose a knowledge-driven visual guidance (KVG) method that leverages available visual information from interventional imaging to facilitate guidewire navigation. Our approach integrates image segmentation and detection techniques to extract surgical knowledge, including vascular maps and guidewire positions. We introduce BDA-star, a novel path planning algorithm with boundary distance constraints, to optimize trajectory planning for guidewire navigation. To validate the method, we developed the KVD-Reinforcement Learning environment, where observations consist of real-time guidewire feeding images highlighting the guidewire tip position and the planned path. We proposed a reward function based on the distances from both the guidewire tip to the planned path and the target to evaluate the agent's actions.Additionally, to address stability issues and slow convergence rates associated with direct learning from raw pixels, we incorporated a pre-trained convolutional neural network into the policy network for feature extraction. Experiments conducted on the aortic simulation autonomous guidewire navigation platform demonstrated that the proposed method, targeting the left subclavian artery, left carotid artery and the brachiocephalic artery, achieved a 100\% guidewire navigation success rate, along with reduced movement and retraction distances and trajectories tend to the center of the vessels.

cs.RO↗

arXiv2024

Personalised Drug Identifier for Cancer Treatment with Transformers using Auxiliary Information

Cancer remains a global challenge due to its growing clinical and economic burden. Its uniquely personal manifestation, which makes treatment difficult, has fuelled the quest for personalized treatment strategies. Thus, genomic profiling is increasingly becoming part of clinical diagnostic panels. Effective use of such panels requires accurate drug response prediction (DRP) models, which are challenging to build due to limited labelled patient data. Previous methods to address this problem have used various forms of transfer learning. However, they do not explicitly model the variable length sequential structure of the list of mutations in such diagnostic panels. Further, they do not utilize auxiliary information (like patient survival) for model training. We address these limitations through a novel transformer based method, which surpasses the performance of state-of-the-art DRP models on benchmark data. We also present the design of a treatment recommendation system (TRS), which is currently deployed at the National University Hospital, Singapore and is being evaluated in a clinical trial.

cs.LG↗

arXiv2018

Liquid structure changes of Bi under different melt states

This paper is focused on the relationship between solidification and melt sates. An abnormal change which takes place at 744 C from 84 to 120 min indicated a liquid-liquid structure transition in pure Bi melt. Based on liquid-liquid structure transition, experiments of pure Bi were carried out. Cooling from different melt states, the solidification behaviors and structures changed a lot, such as undercooling, solidification time, grain sizes and the number of twins and pedestal sits. Especially, as a semi-metal, a liquid-liquid structure transition greatly increases the metallicity of Bi, and during the solidification Bi turned from smooth to coarse solid/ liquid interface.

cond-mat.mtrl-sci↗

arXiv2015

Data-driven research on chemical features of Jingdezhen and Longquan celadon by energy dispersive X-ray fluorescence

The energy dispersive X-ray fluorescence (EDXRF) is used to determine the chemical composition of celadon body and glaze in Longquan kiln (at Dayao County) and Jingdezhen kiln. Forty typical shards in four cultural eras were selected to investigate the raw materials and firing technology. Random forests, a relatively new statistical technique, has been adopted to identify chemical elements that are strongest explanatory variables to classify samples into defferent cultural eras and kilns. The results indicated that the contents of Na2O, Fe2O3, TiO2, SiO2 and CaO vary in celadon bodies from Longquan and Jingdezhen, which implies that local clay was used to manufacture celadon bodies in Jingdezhen kiln. By comparing the chemical composition in glaze, we find that the chemical elements and firing technology of Jingdezhen kiln are very similar to those in Longquan kiln, especially for Ming dynasty. This study reveals the inheritance between Jingdezhen kiln and Longquan kiln, and explains the differences between those two kilns.

cond-mat.mtrl-sci↗