Searcharxiv⌕ Search

arXiv subjects

Jialong Li

Publications and source records attributed to Jialong Li.

At least 37 records · Page 2Linked to original sources

Bridging the Interpretation Gap in Accessibility Testing: Empathetic and Legal-Aware Bug Report Generation via Large Language Models

Modern automated accessibility testing tools for mobile applications have significantly improved the detection of interface violations, yet their impact on remediation remains limited. A key reason is that existing tools typically produce low-level, technical outputs that are difficult for non-specialist stakeholders, such as product managers and designers, to interpret in terms of real user harm and compliance risk. In this paper, we present \textsc{HEAR} (\underline{H}uman-c\underline{E}ntered \underline{A}ccessibility \underline{R}eporting), a framework that bridges this interpretation gap by transforming raw accessibility bug reports into empathetic, stakeholder-oriented narratives. Given the outputs of the existing accessibility testing tool, \textsc{HEAR} first reconstructs the UI context through semantic slicing and visual grounding, then dynamically injects disability-oriented personas matched to each violation type, and finally performs multi-layer reasoning to explain the physical barrier, functional blockage, and relevant legal or compliance concerns. We evaluate the framework on real-world accessibility issues collected from four popular Android applications and conduct a user study (N=12). The results show that \textsc{HEAR} generates factually grounded reports and substantially improves perceived empathy, urgency, persuasiveness, and awareness of legal risk compared with raw technical logs, while imposing little additional cognitive burden.

cs.SE↗

Normalizing Flows are Capable Models for Bi-manual Visuomotor Policy

The field of general-purpose robotics has recently embraced powerful probabilistic diffusion-based models to learn the complex embodiment behaviours. However, existing models often come with significant trade-offs, namely high computational costs for inference and a fundamental inability to quantify output uncertainty. We introduce Normalizing Flows Policy (NF-P), a conditional normalizing flow-based visuomotor policy for bi-manual manipulation. NF-P learns a conditional density over action sequences and enables single-pass generative sampling with tractable likelihood computation. Using this property, we propose two inference-time optimization strategies: Stochastic Batch Selection, which selects the highest-likelihood trajectory among sampled candidates, and Gradient Refinement, which directly ascends the log-likelihood to improve action quality. In both simulation and real robot experiments, NF-P achieves promising success rates compared to the baseline. In addition to improved task performance, NF-P demonstrates faster training and lower inference latency. These results establish normalizing flows as a competitive and computationally efficient visuomotor policy, particularly for real-time, uncertainty-aware robotic control.

cs.RO↗

Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts

On-the-fly Directed Controller Synthesis (OTF-DCS) mitigates state-space explosion by incrementally exploring the system and relies critically on an exploration policy to guide search efficiently. Recent reinforcement learning (RL) approaches learn such policies and achieve promising zero-shot generalization from small training instances to larger unseen ones. However, a fundamental limitation is anisotropic generalization, where an RL policy exhibits strong performance only in a specific region of the domain-parameter space while remaining fragile elsewhere due to training stochasticity and trajectory-dependent bias. To address this, we propose a Soft Mixture-of-Experts framework that combines multiple RL experts via a prior-confidence gating mechanism and treats these anisotropic behaviors as complementary specializations. The evaluation on the Air Traffic benchmark shows that Soft-MoE substantially expands the solvable parameter space and improves robustness compared to any single expert.

cs.AI↗

See What I See: An Attention-Guiding eHMI Approach for Autonomous Vehicles

As autonomous vehicles are gradually being deployed in the real world, external Human-Machine Interfaces (eHMIs) are expected to serve as a critical solution for enhancing vehicle-pedestrian communication. However, existing eHMI designs typically focus solely on the ego vehicle's status, which can inadvertently capture pedestrians' attention or encourage misguided reliance on the AV's signals, leading them to neglect scanning for other surrounding hazards. To address this, we propose the Attention-Guiding eHMI (AGeHMI), a projection-based visualization that employs directional cues and risk-based color coding to actively guide pedestrians' attention toward potential environmental dangers. Evaluation through a virtual reality user study (N = 20) suggests that AGeHMI effectively influences participants' visual attention distribution and significantly reduces potential collision risks with surrounding vehicles, while simultaneously improving subjective confidence and reducing cognitive workload.

cs.HC↗

Quest2ROS2: A ROS 2 Framework for Bi-manual VR Teleoperation

Quest2ROS2 is an open-source ROS2 framework for bi-manual teleoperation designed to scale robot data collection. Extending Quest2ROS, it overcomes workspace limitations via relative motion-based control, calculating robot movement from VR controller pose changes to enable intuitive, pose-independent operation. The framework integrates essential usability and safety features, including real-time RViz visualization, streamlined gripper control, and a pause-and-reset function for smooth transitions. We detail a modular architecture that supports "Side-by-Side" and "Mirror" control modes to optimize operator experience across diverse platforms. Code is available at: https://github.com/Taokt/Quest2ROS2.

cs.RO↗

FAROS: Robust Federated Learning with Adaptive Scaling against Backdoor Attacks

Federated Learning (FL) enables multiple clients to collaboratively train a shared model without exposing local data. However, backdoor attacks pose a significant threat to FL. These attacks aim to implant a stealthy trigger into the global model, causing it to mislead on inputs that possess a specific trigger while functioning normally on benign data. Although pre-aggregation detection is a main defense direction, existing state-of-the-art defenses often rely on fixed defense parameters. This reliance makes them vulnerable to single-point-of-failure risks, rendering them less effective against sophisticated attackers. To address these limitations, we propose FAROS, an enhanced FL framework that incorporates Adaptive Differential Scaling (ADS) and Robust Core-set Computing (RCC). The ADS mechanism adjusts the defense's sensitivity dynamically, based on the dispersion of uploaded gradients by clients in each round. This allows it to counter attackers who strategically shift between stealthiness and effectiveness. Furthermore, the RCC effectively mitigates the risk of single-point failure by computing the centroid of a core set comprising clients with the highest confidence. We conducted extensive experiments across various datasets, models, and attack scenarios. The results demonstrate that our method outperforms current defenses in both attack success rate and main task accuracy.

cs.LG↗

Graph Contextual Reinforcement Learning for Efficient Directed Controller Synthesis

Controller synthesis is a formal method approach for automatically generating Labeled Transition System (LTS) controllers that satisfy specified properties. The efficiency of the synthesis process, however, is critically dependent on exploration policies. These policies often rely on fixed rules or strategies learned through reinforcement learning (RL) that consider only a limited set of current features. To address this limitation, this paper introduces GCRL, an approach that enhances RL-based methods by integrating Graph Neural Networks (GNNs). GCRL encodes the history of LTS exploration into a graph structure, allowing it to capture a broader, non-current-based context. In a comparative experiment against state-of-the-art methods, GCRL exhibited superior learning efficiency and generalization across four out of five benchmark domains, except one particular domain characterized by high symmetry and strictly local interactions.

cs.AI↗

Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning

The widespread adoption of the "Games as a Service" model necessitates frequent content updates, placing immense pressure on quality assurance. In response, automated game testing has been viewed as a promising solution to cope with this demanding release cadence. However, existing automated testing approaches typically create a dichotomy: code-centric methods focus on structural coverage without understanding gameplay context, while player-centric agents validate high-level intent but often fail to cover specific underlying code changes. To bridge this gap, we propose SMART (Structural Mapping for Augmented Reinforcement Testing), a novel framework that synergizes structural verification and functional validation for game update testing. SMART leverages large language models (LLMs) to interpret abstract syntax tree (AST) differences and extract functional intent, constructing a context-aware hybrid reward mechanism. This mechanism guides reinforcement learning agents to sequentially fulfill gameplay goals while adaptively exploring modified code branches. We evaluate SMART on two environments, Overcooked and Minecraft. The results demonstrate that SMART significantly outperforms state-of-the-art baselines; it achieves over 94% branch coverage of modified code, nearly double that of traditional reinforcement learning methods, while maintaining a 98% task completion rate, effectively balancing structural comprehensiveness with functional correctness.

cs.AI↗

FedLAD: A Modular and Adaptive Testbed for Federated Log Anomaly Detection

Log-based anomaly detection (LAD) is critical for ensuring the reliability of large-scale distributed systems. However, most existing LAD approaches assume centralized training, which is often impractical due to privacy constraints and the decentralized nature of system logs. While federated learning (FL) offers a promising alternative, there is a lack of dedicated testbeds tailored to the needs of LAD in federated settings. To address this, we present FedLAD, a unified platform for training and evaluating LAD models under FL constraints. FedLAD supports plug-and-play integration of diverse LAD models, benchmark datasets, and aggregation strategies, while offering runtime support for validation logging (self-monitoring), parameter tuning (self-configuration), and adaptive strategy control (self-adaptation). By enabling reproducible and scalable experimentation, FedLAD bridges the gap between FL frameworks and LAD requirements, providing a solid foundation for future research. Project code is publicly available at: https://github.com/AA-cityu/FedLAD.

cs.SE↗

Automatic Syntax Error Repair for Discrete Controller Synthesis using Large Language Model

Discrete Controller Synthesis (DCS) is a powerful formal method for automatically generating specifications of discrete event systems. However, its practical adoption is often hindered by the highly specialized nature of formal models written in languages such as FSP and FLTL. In practice, syntax errors in modeling frequently become an important bottleneck for developers-not only disrupting the workflow and reducing productivity, but also diverting attention from higher-level semantic design. To this end, this paper presents an automated approach that leverages Large Language Models (LLMs) to repair syntax errors in DCS models using a well-designed, knowledge-informed prompting strategy. Specifically, the prompting is derived from a systematic empirical study of common error patterns, identified through expert interviews and student workshops. It equips the LLM with DCS-specific domain knowledge, including formal grammar rules and illustrative examples, to guide accurate corrections. To evaluate our method, we constructed a new benchmark by systematically injecting realistic syntax errors into validated DCS models. The quantitative evaluation demonstrates the high effectiveness of the proposed approach in terms of repair accuracy and its practical utility regarding time, achieving a speedup of 3.46 times compared to human developers. The experimental replication suite, including the benchmark and prompts, is available at https://github.com/Uuusay1432/DCSModelRepair.git

cs.SE↗

Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmap

Self-adaptive systems (SASs) are designed to handle changes and uncertainties through a feedback loop with four core functionalities: monitoring, analyzing, planning, and execution. Recently, generative artificial intelligence (GenAI), especially the area of large language models, has shown impressive performance in data comprehension and logical reasoning. These capabilities are highly aligned with the functionalities required in SASs, suggesting a strong potential to employ GenAI to enhance SASs. However, the specific benefits and challenges of employing GenAI in SASs remain unclear. Yet, providing a comprehensive understanding of these benefits and challenges is complex due to several reasons: limited publications in the SAS field, the technological and application diversity within SASs, and the rapid evolution of GenAI technologies. To that end, this paper aims to provide researchers and practitioners a comprehensive snapshot that outlines the potential benefits and challenges of employing GenAI's within SAS. Specifically, we gather, filter, and analyze literature from four distinct research fields and organize them into two main categories to potential benefits: (i) enhancements to the autonomy of SASs centered around the specific functions of the MAPE-K feedback loop, and (ii) improvements in the interaction between humans and SASs within human-on-the-loop settings. From our study, we outline a research roadmap that highlights the challenges of integrating GenAI into SASs. The roadmap starts with outlining key research challenges that need to be tackled to exploit the potential for applying GenAI in the field of SAS. The roadmap concludes with a practical reflection, elaborating on current shortcomings of GenAI and proposing possible mitigation strategies.

cs.SE↗

Amplifiers or Equalizers? A Longitudinal Study of LLM Evolution in Software Engineering Project-Based Learning

As LLMs reshape software development, integrating LLM-augmented practices into SE education has become imperative. While existing studies explore LLMs' educational use in introductory programming or isolated SE tasks, their impact in more open-ended Project-Based Learning (PBL) remains unexplored. This paper introduces a two-year longitudinal study comparing a 2024 (using early free LLMs, $n$=48) and 2025 (using the latest paid LLMs, $n$=46) cohort. Our findings suggest the latest powerful LLMs' dual role: they act as "equalizers," boosting average performance even for programming-weak students, providing opportunities for more authentic SE practices; yet also as "amplifiers," dramatically widening absolute performance gaps, creating new pedagogical challenges for addressing educational inequities.

cs.SE↗

PLATONT: Learning a Platonic Representation for Unified Network Tomography

Network tomography aims to infer hidden network states, such as link performance, traffic load, and topology, from external observations. Most existing methods solve these problems separately and depend on limited task-specific signals, which limits generalization and interpretability. We present PLATONT, a unified framework that models different network indicators (e.g., delay, loss, bandwidth) as projections of a shared latent network state. Guided by the Platonic Representation Hypothesis, PLATONT learns this latent state through multimodal alignment and contrastive learning. By training multiple tomography tasks within a shared latent space, it builds compact and structured representations that improve cross-task generalization. Experiments on synthetic and real-world datasets show that PLATONT consistently outperforms existing methods in link estimation, topology inference, and traffic prediction, achieving higher accuracy and stronger robustness under varying network conditions.

cs.LG↗

Knowledge Graph-enhanced Large Language Model for Incremental Game PlayTesting

The rapid iteration and frequent updates of modern video games pose significant challenges to the efficiency and specificity of testing. Although automated playtesting methods based on Large Language Models (LLMs) have shown promise, they often lack structured knowledge accumulation mechanisms, making it difficult to conduct precise and efficient testing tailored for incremental game updates. To address this challenge, this paper proposes a KLPEG framework. The framework constructs and maintains a Knowledge Graph (KG) to systematically model game elements, task dependencies, and causal relationships, enabling knowledge accumulation and reuse across versions. Building on this foundation, the framework utilizes LLMs to parse natural language update logs, identify the scope of impact through multi-hop reasoning on the KG, enabling the generation of update-tailored test cases. Experiments in two representative game environments, Overcooked and Minecraft, demonstrate that KLPEG can more accurately locate functionalities affected by updates and complete tests in fewer steps, significantly improving both playtesting effectiveness and efficiency.

cs.AI↗

RailS: Load Balancing for All-to-All Communication in Distributed Mixture-of-Experts Training

Training Mixture-of-Experts (MoE) models introduces sparse and highly imbalanced all-to-all communication that dominates iteration time. Conventional load-balancing methods fail to exploit the deterministic topology of Rail architectures, leaving multi-NIC bandwidth underutilized. We present RailS, a distributed load-balancing framework that minimizes all-to-all completion time in MoE training. RailS leverages the Rail topology's symmetry to prove that uniform sending ensures uniform receiving, transforming global coordination into local scheduling. Each node independently executes a Longest Processing Time First (LPT) spraying scheduler to proactively balance traffic using local information. RailS activates N parallel rails for fine-grained, topology-aware multipath transmission. Across synthetic and real-world MoE workloads, RailS improves bus bandwidth by 20%--78% and reduces completion time by 17%--78%. For Mixtral workloads, it shortens iteration time by 18%--40% and achieves near-optimal load balance, fully exploiting architectural parallelism in distributed training.

cs.DC↗

Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach

The increasing demand for software development has driven interest in automating software engineering (SE) tasks using Large Language Models (LLMs). Recent efforts extend LLMs into multi-agent systems (MAS) that emulate collaborative development workflows, but these systems often fail due to three core deficiencies: under-specification, coordination misalignment, and inappropriate verification, arising from the absence of foundational SE structuring principles. This paper introduces Software Engineering Multi-Agent Protocol (SEMAP), a protocol-layer methodology that instantiates three core SE design principles for multi-agent LLMs: (1) explicit behavioral contract modeling, (2) structured messaging, and (3) lifecycle-guided execution with verification, and is implemented atop Google's Agent-to-Agent (A2A) infrastructure. Empirical evaluation using the Multi-Agent System Failure Taxonomy (MAST) framework demonstrates that SEMAP effectively reduces failures across different SE tasks. In code development, it achieves up to a 69.6% reduction in total failures for function-level development and 56.7% for deployment-level development. For vulnerability detection, SEMAP reduces failure counts by up to 47.4% on Python tasks and 28.2% on C/C++ tasks.

cs.SE↗

Humanoid Policy ~ Human Policy

Training manipulation policies for humanoid robots with diverse data enhances their robustness and generalization across tasks and platforms. However, learning solely from robot demonstrations is labor-intensive, requiring expensive tele-operated data collection which is difficult to scale. This paper investigates a more scalable data source, egocentric human demonstrations, to serve as cross-embodiment training data for robot learning. We mitigate the embodiment gap between humanoids and humans from both the data and modeling perspectives. We collect an egocentric task-oriented dataset (PH2D) that is directly aligned with humanoid manipulation demonstrations. We then train a human-humanoid behavior policy, which we term Human Action Transformer (HAT). The state-action space of HAT is unified for both humans and humanoid robots and can be differentiably retargeted to robot actions. Co-trained with smaller-scale robot data, HAT directly models humanoid robots and humans as different embodiments without additional supervision. We show that human data improves both generalization and robustness of HAT with significantly better data collection efficiency. Code and data: https://human-as-robot.github.io/

cs.RO↗

Temporal-Aware GPU Resource Allocation for Distributed LLM Inference via Reinforcement Learning

The rapid growth of large language model (LLM) services imposes increasing demands on distributed GPU inference infrastructure. Most existing scheduling systems follow a reactive paradigm, relying solely on the current system state to make decisions, without considering how task demand and resource availability evolve over time. This lack of temporal awareness in reactive approaches leads to inefficient GPU utilization, high task migration overhead, and poor system responsiveness under dynamic workloads. In this work, we identify the fundamental limitations of these instantaneous-state-only scheduling approaches and propose Temporal Optimal Resource scheduling via Two-layer Architecture (TORTA). TORTA introduces a spatiotemporal scheduling framework that captures both long-term workload patterns and short-term execution constraints. It adopts a two-layer design: a macro-level scheduler leverages reinforcement learning and optimal transport to coordinate inter-region task distribution, while a micro-level allocator refines task-to-server assignments within each region to reduce latency and switching costs. Experimental results across multiple network topologies show that TORTA reduces average inference response time by up to 15\%, improves load balance by approximately 4-5\%, and cuts total operational cost by 10-20\% compared to state-of-the-art baseline methods.

cs.DC↗