arXiv subjects

Jialu Zhang

Publications and source records attributed to Jialu Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

EcoScratch: Cost-Effective Multimodal Repair for Scratch Using Execution Feedback

Scratch is the most popular programming environment for novices, with over 1.15 billion projects created worldwide. Unlike traditional languages, correctness in Scratch is defined by visible behavior on the stage rather than by code structure alone, so programs that appear correct in the workspace can still fail at runtime due to timing, event ordering, or cross-sprite interactions. Visual execution evidence such as gameplay videos can therefore be essential for diagnosis and repair. However, capturing and processing this evidence inside an automated repair loop introduces substantial overhead. Probing execution, recording stage behavior, rebuilding executable .sb3 projects, and verifying candidate fixes consume time, monetary cost, and resources across an entire repair trajectory rather than a single model call. We present EcoScratch, a repair pipeline that uses lightweight runtime signals to decide whether the next attempt stays text-only or escalates to multimodal prompting. The controller also sets the JSON Patch budget and verification effort, so evidence choice and repair budget are coupled inside the same decision. EcoScratch rebuilds candidate fixes into executable .sb3 projects and records per-trajectory traces, monetary cost, local-runtime energy. We evaluate 12 models on 100 executable Scratch repair projects under four controller settings, yielding 4800 repair trajectories. In this matrix, a selective multimodal policy gives the strongest observed success-cost-energy tradeoff. It reaches the highest generation success (30.3%) while using less average cost and local-runtime energy than the two non-adaptive multimodal baselines under the same bounded trajectory budget; text-only remains the lowest-cost floor. Across the evaluated matrix, multimodal evidence helps most when it is used to control escalation within a bounded trajectory budget rather than applied uniformly.

cs.SE↗

arXiv2026

ScratchEval : A Multimodal Evaluation Framework for LLMs in Block-Based Programming

LLMs have achieved strong performance on text-based programming tasks, yet they remain unreliable for block-based languages such as Scratch. Scratch programs exhibit deeply nested, non-linear structures, event-driven concurrency across multiple sprites, and tight coupling between code and multimedia assets, properties that differ fundamentally from textual code. As a result, LLMs often misinterpret Scratch semantics and generate large, invasive edits that are syntactically valid but semantically incorrect when repairing buggy programs. We introduce ScratchEval, the first executable benchmark designed to evaluate LLM-based repair for Scratch programs, covering program understanding, debugging, analysis, and repair. The benchmark contains 100 curated Scratch projects from the public repository, selected for structural and semantic complexity. Each project is paired with executable test suites, bug descriptions with corresponding fixes, block-level edit constraints defining minimal semantically correct repairs, and required multimedia assets. The benchmark is constructed through a human-in-the-loop pipeline combining automated project mining with expert validation of trigger-outcome semantics and representative bug patterns, with emphasis on event ordering, concurrency, and state management. To enable rigorous and reproducible evaluation, we propose a three-layer executable protocol measuring functional correctness via VM-level execution, repair quality using block-level edit distance and behavioral trajectory comparisons, and explanation quality via structured rubrics assessing alignment between model reasoning and generated patches. Using ScratchEval, we study domain-specific fine-tuning, training data effectiveness, and model generalization to unseen bug types. ScratchEval provides a reproducible foundation for evaluating and post-training LLMs on block-based programming tasks.

cs.SE↗

arXiv2026

Integer Linear Programming Preprocessing for Maximum Satisfiability

The Maximum Satisfiability problem (MaxSAT) is a major optimization challenge with numerous practical applications. In recent MaxSAT evaluations, most MaxSAT solvers have incorporated an Integer Linear Programming (ILP) solver into their portfolios. However, a good portfolio strategy requires a lot of tuning work and is limited to the profiling benchmark. This paper proposes a methodology to fully integrate ILP preprocessing techniques into the MaxSAT solving pipeline and investigates the impact on the top-performing MaxSAT solvers. Experimental results show that our approach helps to improve 5 out of 6 state-of-the-art MaxSAT solvers, especially for WMaxCDCL-OpenWbo1200, the winner of the MaxSAT evaluation 2024 on the unweighted track, which is able to solve 15 additional instances using our methodology.

cs.AI↗

arXiv2025

Stitch: Step-by-step LLM Guided Tutoring for Scratch

Block-based environments such as Scratch are increasingly popular in programming education. While block syntax reduces surface errors, semantic bugs remain common and challenging for novices to resolve. Existing debugging workflows typically show the correct program directly to learners, a strategy that may fix errors but undermines the development of problem-solving skills. We present Stitch, an interactive tutoring system that replaces "showing the answer" with step-by-step scaffolding. The system's Diff-Analyze module contrasts a student's project with a reference implementation, identifies the most critical differences, and uses a large language model to explain why these changes matter. Learners inspect highlighted blocks through a custom rendering engine, understand the explanations, and selectively apply partial fixes. This iterative process continues until the intended functionality is achieved. We evaluate Stitch in an empirical study, comparing it against a state-of-the-art automated feedback generation tool for Scratch. Our key insight is that simply presenting the correct program is pedagogically ineffective. In contrast, our interactive, step-by-step guided system promotes a more effective learning experience. More broadly, what constitutes effective feedback in block-based programming remains an open question. Our evaluation provides new evidence that step-by-step tutoring significantly enhances learning outcomes, outperforming both direct-answer approaches and current automated feedback generation tools.

cs.SE↗

arXiv2025

A Systematic Study of Time Limit Exceeded Errors in Online Programming Assignments

Online programming platforms such as Codeforces and LeetCode attract millions of users seeking to learn to program or refine their skills for industry interviews. A major challenge for these users is the Time Limit Exceeded (TLE) error, triggered when a program exceeds the execution time bound. Although designed as a performance safeguard, TLE errors are difficult to resolve: error messages provide no diagnostic insight, platform support is minimal, and existing debugging tools offer little help. As a result, many users abandon their submissions after repeated TLE failures. This paper presents the first large-scale empirical study of TLE errors in online programming. We manually analyzed 1000 Codeforces submissions with TLE errors, classified their root causes, and traced how users attempted to fix them. Our analysis shows that TLE errors often arise not only from inefficient algorithms but also from infinite loops, improper data structure use, and inefficient I/O, challenging the conventional view that TLEs are purely performance issues. Guided by these findings, we introduce Nettle, the first automated repair tool specifically designed for TLE errors, and Nettle-Eval, the first framework for evaluating TLE repairs. Integrating LLMs with targeted automated feedback generated by the compiler and test cases, Nettle produces small, correct code edits that eliminate TLEs while preserving functionality. Evaluated on the same 1000 real-world cases, Nettle achieves a 98.5% fix rate, far exceeding the strongest LLM baseline, and all of its repairs pass both Nettle-Eval and the platform's official checker, confirming the reliability of our framework.

cs.SE↗

arXiv2025

PerchMobi^3: A Multi-Modal Robot with Power-Reuse Quad-Fan Mechanism for Air-Ground-Wall Locomotion

Achieving seamless integration of aerial flight, ground driving, and wall climbing within a single robotic platform remains a major challenge, as existing designs often rely on additional adhesion actuators that increase complexity, reduce efficiency, and compromise reliability. To address these limitations, we present PerchMobi^3, a quad-fan, negative-pressure, air-ground-wall robot that implements a propulsion-adhesion power-reuse mechanism. By repurposing four ducted fans to simultaneously provide aerial thrust and negative-pressure adhesion, and integrating them with four actively driven wheels, PerchMobi^3 eliminates dedicated pumps while maintaining a lightweight and compact design. To the best of our knowledge, this is the first quad-fan prototype to demonstrate functional power reuse for multi-modal locomotion. A modeling and control framework enables coordinated operation across ground, wall, and aerial domains with fan-assisted transitions. The feasibility of the design is validated through a comprehensive set of experiments covering ground driving, payload-assisted wall climbing, aerial flight, and cross-mode transitions, demonstrating robust adaptability across locomotion scenarios. These results highlight the potential of PerchMobi^3 as a novel design paradigm for multi-modal robotic mobility, paving the way for future extensions toward autonomous and application-oriented deployment.

cs.RO↗

arXiv2025

ViScratch: Using Large Language Models and Gameplay Videos for Automated Feedback in Scratch

Block-based programming environments such as Scratch are increasingly popular in programming education, in particular for young learners. While the use of blocks helps prevent syntax errors, semantic bugs remain common and difficult to debug. Existing tools for Scratch debugging rely heavily on predefined rules or user manual inputs, and crucially, they ignore the platform's inherently visual nature. We introduce ViScratch, the first multimodal feedback generation system for Scratch that leverages both the project's block code and its generated gameplay video to diagnose and repair bugs. ViScratch uses a two-stage pipeline: a vision-language model first aligns visual symptoms with code structure to identify a single critical issue, then proposes minimal, abstract syntax tree level repairs that are verified via execution in the Scratch virtual machine. We evaluate ViScratch on a set of real-world Scratch projects against state-of-the-art LLM-based tools and human testers. Results show that gameplay video is a crucial debugging signal: ViScratch substantially outperforms prior tools in both bug identification and repair quality, even without access to project descriptions or goals. This work demonstrates that video can serve as a first-class specification in visual programming environments, opening new directions for LLM-based debugging beyond symbolic code alone.

cs.SE↗

arXiv2025

PEMUTA: Pedagogically-Enriched Multi-Granular Undergraduate Thesis Assessment

The undergraduate thesis (UGTE) plays an indispensable role in assessing a student's cumulative academic development throughout their college years. Although large language models (LLMs) have advanced education intelligence, they typically focus on holistic assessment with only one single evaluation score, but ignore the intricate nuances across multifaceted criteria, limiting their ability to reflect structural criteria, pedagogical objectives, and diverse academic competencies. Meanwhile, pedagogical theories have long informed manual UGTE evaluation through multi-dimensional assessment of cognitive development, disciplinary thinking, and academic performance, yet remain underutilized in automated settings. Motivated by the research gap, we pioneer PEMUTA, a pedagogically-enriched framework that effectively activates domain-specific knowledge from LLMs for multi-granular UGTE assessment. Guided by Vygotsky's theory and Bloom's Taxonomy, PEMUTA incorporates a hierarchical prompting scheme that evaluates UGTEs across six fine-grained dimensions: Structure, Logic, Originality, Writing, Proficiency, and Rigor (SLOWPR), followed by holistic synthesis. Two in-context learning techniques, \ie, few-shot prompting and role-play prompting, are also incorporated to further enhance alignment with expert judgments without fine-tuning. We curate a dataset of authentic UGTEs with expert-provided SLOWPR-aligned annotations to support multi-granular UGTE assessment. Extensive experiments demonstrate that PEMUTA achieves strong alignment with expert evaluations, and exhibits strong potential for fine-grained, pedagogically-informed UGTE evaluations.

cs.CY↗

arXiv2025

Power corrections in the determination of heavy meson LCDAs: A renormalon-based estimation

At leading power accuracy the QCD light-cone distribution amplitudes (LCDAs) for a heavy meson can be matched onto the LCDAs in the framework of heavy-quark effective theory (HQET) through a factorization formula. We examine the power corrections to this factorization in the renormalon model, which can associate the power corrections originating from high-twist contributions to the divergent series in a matching kernel. Our analysis indicates that the dominant power corrections originate from the virtual part of the vertex bubble chain diagrams, which generate poles at $w=n+\frac{1}{2},\forall n\in \mathbb{N}$ and $w=1$ in the Borel plane. Employing phenomenological models for both HQET and QCD LCDA, we present a numerical estimate. The results indicate that the power corrections in the peak region are approximately $22\%$ for the D meson and $7\%$ for the $\overline{\mathrm{B}}$ meson. These findings showcase the magnitude and the potential importance of power corrections in achieving high-precision phenomenological predictions for heavy mesons.

hep-ph↗

arXiv2025

GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Counting

Exemplar-Free Counting aims to count objects of interest without intensive annotations of objects or exemplars. To achieve this, we propose a Gated Context-Aware Swin-UNet (GCA-SUNet) to directly map an input image to the density map of countable objects. Specifically, a set of Swin transformers form an encoder to derive a robust feature representation, and a Gated Context-Aware Modulation block is designed to suppress irrelevant objects or background through a gate mechanism and exploit the attentive support of objects of interest through a self-similarity matrix. The gate strategy is also incorporated into the bottleneck network and the decoder of the Swin-UNet to highlight the features most relevant to objects of interest. By explicitly exploiting the attentive support among countable objects and eliminating irrelevant features through the gate mechanisms, the proposed GCA-SUNet focuses on and counts objects of interest without relying on predefined categories or exemplars. Experimental results on the real-world datasets such as FSC-147 and CARPK demonstrate that GCA-SUNet significantly and consistently outperforms state-of-the-art methods. The code is available at https://github.com/Amordia/GCA-SUNet.

cs.CV↗

arXiv2024

TransMA: an explainable multi-modal deep learning model for predicting properties of ionizable lipid nanoparticles in mRNA delivery

As the primary mRNA delivery vehicles, ionizable lipid nanoparticles (LNPs) exhibit excellent safety, high transfection efficiency, and strong immune response induction. However, the screening process for LNPs is time-consuming and costly. To expedite the identification of high-transfection-efficiency mRNA drug delivery systems, we propose an explainable LNPs transfection efficiency prediction model, called TransMA. TransMA employs a multi-modal molecular structure fusion architecture, wherein the fine-grained atomic spatial relationship extractor named molecule 3D Transformer captures three-dimensional spatial features of the molecule, and the coarse-grained atomic sequence extractor named molecule Mamba captures one-dimensional molecular features. We design the mol-attention mechanism block, enabling it to align coarse and fine-grained atomic features and captures relationships between atomic spatial and sequential structures. TransMA achieves state-of-the-art performance in predicting transfection efficiency using the scaffold and cliff data splitting methods on the current largest LNPs dataset, including Hela and RAW cell lines. Moreover, we find that TransMA captures the relationship between subtle structural changes and significant transfection efficiency variations, providing valuable insights for LNPs design. Additionally, TransMA's predictions on external transfection efficiency data maintain a consistent order with actual transfection efficiencies, demonstrating its robust generalization capability. The code, model and data are made publicly available at https://github.com/wklix/TransMA/tree/master. We hope that high-accuracy transfection prediction models in the future can aid in LNPs design and initial screening, thereby assisting in accelerating the mRNA design process.

cs.AI↗

arXiv2024

A comparative lattice analysis of $SU(2)$ dark gluebal

We study the mass and scattering cross section of $SU(2)$ glueballs as dark matter candidates using lattice simulations. We employ both naive and improved $SU(2)$ gauge actions in $3+1$ dimensions with several $β$ values, and adopt both the traditional Monte Carlo method and the flow-based model based on machine learning techniques to generate lattice configurations. The mass of dark scalar glueball with $J^{PC}=0^{++}$ and the NBS wave function are calculated. Using a coupling constant of $β=2.2$ as an illustration, we compare the dark glueball mass calculated from the configurations generated from the two methods. While consistent results can be achieved, the two methods demonstrate distinct advantages. Using the Runge-Kutta method, we extract the glueball interaction potential and two-body scattering cross section. From the observational constraints, we obtain the lower bound of the mass of scalar glueball as candidates of dark matter.

hep-lat↗

arXiv2023

Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery

Object detection in aerial imagery presents a significant challenge due to large scale variations among objects. This paper proposes an evolutionary reinforcement learning agent, integrated within a coarse-to-fine object detection framework, to optimize the scale for more effective detection of objects in such images. Specifically, a set of patches potentially containing objects are first generated. A set of rewards measuring the localization accuracy, the accuracy of predicted labels, and the scale consistency among nearby patches are designed in the agent to guide the scale optimization. The proposed scale-consistency reward ensures similar scales for neighboring objects of the same category. Furthermore, a spatial-semantic attention mechanism is designed to exploit the spatial semantic relations between patches. The agent employs the proximal policy optimization strategy in conjunction with the evolutionary strategy, effectively utilizing both the current patch status and historical experience embedded in the agent. The proposed model is compared with state-of-the-art methods on two benchmark datasets for object detection on drone imagery. It significantly outperforms all the compared methods.

cs.CV↗

arXiv2023

Light baryon spatial correlators at short distances

To study the light baryon light-cone distribution amplitudes (LCDAs), the spatial correlator of the light baryon has been calculated up to one-loop order in coordinate space. They reveal certain identities that do not appear in the study of mesons DAs and PDFs. Subsequently, it was renormalized using the ratio renormalization scheme involving division by a 0-momentum matrix element. Then through the matching in the coordinate space, the light baryon light-cone correlator can be extracted out from the spatial correlator. %By choosing a specific type of spatial correlator for light baryons, the LCDA is determined from first principles. These results provide insights into both the ultraviolet (UV) and infrared (IR) structures of the light baryon spatial correlator, which is valuable for further exploration in this field. Furthermore, the employed ratio scheme is an efficient and lattice-friendly renormalization approach suitable for short-distance applications. These can be used for studying the light baryon LCDAs using lattice techniques.

hep-ph↗

arXiv2022

Succinct Explanations With Cascading Decision Trees

The decision tree is one of the most popular and classical machine learning models from the 1980s. However, in many practical applications, decision trees tend to generate decision paths with excessive depth. Long decision paths often cause overfitting problems, and make models difficult to interpret. With longer decision paths, inference is also more likely to fail when the data contain missing values. In this work, we propose a new tree model called Cascading Decision Trees to alleviate this problem. The key insight of Cascading Decision Trees is to separate the decision path and the explanation path. Our experiments show that on average, Cascading Decision Trees generate 63.38% shorter explanation paths, avoiding overfitting and thus achieve higher test accuracy. We also empirically demonstrate that Cascading Decision Trees have advantages in the robustness against missing values.

cs.LG↗

arXiv2022

A high-frequency mobility big-data reveals how COVID-19 spread across professions, locations and age groups

As infected and vaccinated population increases, some countries decided not to impose non-pharmaceutical intervention measures anymore and to coexist with COVID-19. However, we do not have a comprehensive understanding of its consequence , especially for China where most population has not been infected and most Omicron transmissions are silent. This paper serves as the first study to reveal the complete silent transmission dynamics of COVID-19 overlaying a big data of more than 0.7 million real individual mobility tracks without any intervention measures throughout a week in a Chinese city, with an extent of completeness and realism not attained in existing studies. Together with the empirically inferred transmission rate of COVID-19, we find surprisingly that with only 70 citizens to be infected initially, 0.33 million becomes infected silently at last. We also reveal a characteristic daily periodic pattern of the transmission dynamics, with peaks in mornings and afternoons. In addition, retailing, catering and hotel staff are more likely to get infected than other professions. Unlike all other age groups and professions, elderly and retirees are more likely to get infected at home than outside home.

physics.soc-ph↗

arXiv2022

Repairing Bugs in Python Assignments Using Large Language Models

Students often make mistakes on their introductory programming assignments as part of their learning process. Unfortunately, providing custom repairs for these mistakes can require a substantial amount of time and effort from class instructors. Automated program repair (APR) techniques can be used to synthesize such fixes. Prior work has explored the use of symbolic and neural techniques for APR in the education domain. Both types of approaches require either substantial engineering efforts or large amounts of data and training. We propose to use a large language model trained on code, such as Codex, to build an APR system -- MMAPR -- for introductory Python programming assignments. Our system can fix both syntactic and semantic mistakes by combining multi-modal prompts, iterative querying, test-case-based selection of few-shots, and program chunking. We evaluate MMAPR on 286 real student programs and compare to a baseline built by combining a state-of-the-art Python syntax repair engine, BIFI, and state-of-the-art Python semantic repair engine for student assignments, Refactory. We find that MMAPR can fix more programs and produce smaller patches on average.

cs.SE↗

arXiv2022

Automated Feedback Generation for Competition-Level Code

Competitive programming has become a popular way for programmers to test their skills. Large-scale online programming contests attract millions of experienced programmers to compete against each other. Competition-level programming problems are challenging in nature, and participants often fail to solve the problem on their first attempt. Some online platforms for competitive programming allow programmers to practice on competition-level problems as well, and the standard feedback for an incorrect practice submission is the first test case that the submission fails. Often, the failed test case does not provide programmers with enough information to resolve the errors in their code, and they abandon the problem after several more unsuccessful attempts. We present Clef, the first data-driven tool that can generate feedback on competition-level code automatically by repairing programmers' incorrect submissions. The key development is that Clef can learn how to generate repairs for incorrect submissions by examining the repairs that other programmers made to their own submissions over time. Since the differences between an incorrect program and a correct program for the same task may be significant, we introduce a new data structure, merge trees, to capture the changes between submissions. Merge trees are versatile: they can encode both large algorithm-level redesigns and small statement-level alterations. Clef applies the patterns it learns from a database of submissions to generate repairs for new submissions outside the database. We evaluated Clef on six real-world problems from Codeforces, the world's largest platform for competitive programming. Clef achieves 42.1% accuracy in repairing programmers' incorrect submissions. Even when given incorrect submissions from programmers who never found the solution to a problem on their own, Clef repairs the users' programs 34.1% of the time.

cs.SE↗