Author name cluster

Zijiang Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

FM Conference 2026 Conference Paper

ConFixer: Robustness Semantics Based Configuration Bug Fixing for Automated Driving Systems

Xiaodong Zhang
Songyang Yan
Zijiang Yang

Abstract Automated Driving Systems (ADSs) coordinate multiple modules (e. g. , perception, prediction, planning, and control) and expose a large configuration surface that engineers must tune for different platforms and operational conditions. In industrial practice, misconfigured parameters are a common source of unsafe or law-violating behaviors, yet fixing such configuration bugs remains largely overlooked. Debugging is difficult because parameter effects propagate through long, nonlinear pipelines (often involving learning-based components), and manual trial-and-error provides little guidance in high-dimensional spaces while risking regressions in previously passing scenarios. We propose ConFixer, an automated approach for repairing ADS configuration bugs against formal correctness specifications, including traffic laws encoded in signal temporal logic (STL). ConFixer uses robustness semantics to derive gradient-like signals that localize bug-relevant parameters and guide fine-tuning toward compliance. To support adoption in scenario-based validation workflows, ConFixer evaluates candidate fixes on large scenario suites and prioritizes regression-safe solutions. Our evaluation on Baidu Apollo with the LGSVL simulator shows that ConFixer fixes 173 configuration bugs without introducing regressions.

DOI

AAAI Conference 2026 Conference Paper

MUSE: Multi-Scale Dense Self-Distillation for Nucleus Detection and Classification

Zijiang Yang
Hanqing Chao
Bokai Zhao
Yelin Yang
Yunshuo Zhang
Dongmei Fu
Junping Zhang
Le Lu

Nucleus detection and classification (NDC) in histopathology analysis is a fundamental task that underpins a wide range of high-level pathology applications. However, existing methods heavily rely on labor-intensive nucleus-level annotations and struggle to fully exploit large-scale unlabeled data for learning discriminative nucleus representations. In this work, we propose MUSE (MUlti-scale denSE self-distillation), a novel self-supervised learning method tailored for NDC. At its core is NuLo (Nucleus-based Local self-distillation), a coordinate-guided mechanism that enables flexible local self-distillation based on predicted nucleus positions. By removing the need for strict spatial alignment between augmented views, NuLo allows critical cross-scale alignment, thus unlocking the capacity of models for fine-grained nucleus-level representation. To support MUSE, we design a simple yet effective encoder-decoder architecture and a large field-of-view semi-supervised fine-tuning strategy that together maximize the value of unlabeled pathology images. Extensive experiments on three widely used benchmarks demonstrate that MUSE effectively addresses the core challenges of histopathological NDC. The resulting models not only surpass state-of-the-art supervised baselines but also outperform generic pathology foundation models.

PDF Details DOI

AAAI Conference 2023 Conference Paper

DMIS: Dynamic Mesh-Based Importance Sampling for Training Physics-Informed Neural Networks

Zijiang Yang
Zhongwei Qiu
Dongmei Fu

Modeling dynamics in the form of partial differential equations (PDEs) is an effectual way to understand real-world physics processes. For complex physics systems, analytical solutions are not available and numerical solutions are widely-used. However, traditional numerical algorithms are computationally expensive and challenging in handling multiphysics systems. Recently, using neural networks to solve PDEs has made significant progress, called physics-informed neural networks (PINNs). PINNs encode physical laws into neural networks and learn the continuous solutions of PDEs. For the training of PINNs, existing methods suffer from the problems of inefficiency and unstable convergence, since the PDE residuals require calculating automatic differentiation. In this paper, we propose Dynamic Mesh-based Importance Sampling (DMIS) to tackle these problems. DMIS is a novel sampling scheme based on importance sampling, which constructs a dynamic triangular mesh to estimate sample weights efficiently. DMIS has broad applicability and can be easily integrated into existing methods. The evaluation of DMIS on three widely-used benchmarks shows that DMIS improves the convergence speed and accuracy in the meantime. Especially in solving the highly nonlinear Schrödinger Equation, compared with state-of-the-art methods, DMIS shows up to 46% smaller root mean square error and five times faster convergence speed. Code is available at https://github.com/MatrixBrain/DMIS.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

LayoutPrompter: Awaken the Design Ability of Large Language Models

Jiawei Lin
Jiaqi Guo
Shizhao Sun
Zijiang Yang
Jian-Guang Lou
Dongmei Zhang

Conditional graphic layout generation, which automatically maps user constraints to high-quality layouts, has attracted widespread attention today. Although recent works have achieved promising performance, the lack of versatility and data efficiency hinders their practical applications. In this work, we propose LayoutPrompter, which leverages large language models (LLMs) to address the above problems through in-context learning. LayoutPrompter is made up of three key components, namely input-output serialization, dynamic exemplar selection and layout ranking. Specifically, the input-output serialization component meticulously designs the input and output formats for each layout generation task. Dynamic exemplar selection is responsible for selecting the most helpful prompting exemplars for a given input. And a layout ranker is used to pick the highest quality layout from multiple outputs of LLMs. We conduct experiments on all existing layout generation tasks using four public datasets. Despite the simplicity of our approach, experimental results show that LayoutPrompter can compete with or even outperform state-of-the-art approaches on these tasks without any model training or fine-tuning. This demonstrates the effectiveness of this versatile and training-free approach. In addition, the ablation studies show that LayoutPrompter is significantly superior to the training-based baseline in a low-data regime, further indicating the data efficiency of LayoutPrompter. Our project is available at https: //github. com/microsoft/LayoutGeneration/tree/main/LayoutPrompter.

PDF Details

TCS Journal 2008 Journal Article

Efficient SAT-based bounded model checking for software verification

Franjo Ivančić
Zijiang Yang
Malay K. Ganai
Aarti Gupta
Pranav Ashar

This paper discusses our methodology for formal analysis and automatic verification of software programs. It is applicable to a large subset of the C programming language that includes pointer arithmetic and bounded recursion. We consider reachability properties, in particular whether certain assertions or basic blocks are reachable in the source code, or whether certain standard property violations can occur. We perform this analysis via a translation to a Boolean circuit representation based on modeling basic blocks. The program is then analyzed by a back-end SAT-based bounded model checker, where each unrolling is mapped to one step in a block-wise execution of the program. The main contributions of this paper are as follows: (1) Use of basic block-based unrollings with SAT-based bounded model checking of software programs. This allows us to take advantage of SAT-based learning inherent to the best performing bounded model checkers. (2) Various heuristics customized for models automatically generated from software, allowing a more efficient SAT-based analysis. (3) A prototype tool called F-Soft has been implemented using our methodology. We present experimental results based on multiple case studies including a C-based implementation of a network protocol, and compare the performance gains using the proposed heuristics.

Details DOI