arXiv subjects

Jianwei Yin

Publications and source records attributed to Jianwei Yin.

At least 73 records · Page 4Linked to original sources

arXiv2025

Video-QTR: Query-Driven Temporal Reasoning Framework for Lightweight Video Understanding

The rapid development of multimodal large-language models (MLLMs) has significantly expanded the scope of visual language reasoning, enabling unified systems to interpret and describe complex visual content. However, applying these models to long-video understanding remains computationally intensive. Dense frame encoding generates excessive visual tokens, leading to high memory consumption, redundant computation, and limited scalability in real-world applications. This inefficiency highlights a key limitation of the traditional process-then-reason paradigm, which analyzes visual streams exhaustively before semantic reasoning. To address this challenge, we introduce Video-QTR (Query-Driven Temporal Reasoning), a lightweight framework that redefines video comprehension as a query-guided reasoning process. Instead of encoding every frame, Video-QTR dynamically allocates perceptual resources based on the semantic intent of the query, creating an adaptive feedback loop between reasoning and perception. Extensive experiments across five benchmarks: MSVD-QA, Activity Net-QA, Movie Chat, and Video MME demonstrate that Video-QTR achieves state-of-the-art performance while reducing input frame consumption by up to 73%. These results confirm that query-driven temporal reasoning provides an efficient and scalable solution for video understanding.

cs.CV↗

arXiv2025

TenonOS: A Self-Generating LibOS-on-LibOS Framework for Time-Critical Embedded Operating Systems

The growing complexity of embedded systems creates tension between rich functionality and strict resource and real-time constraints. Traditional monolithic operating system and hypervisor designs suffer from resource bloat and unpredictable scheduling, making them unsuitable for time-critical workloads where low latency and low jitter are essential. We propose TenonOS, a demand-driven, self-generating, lightweight operating system framework for time-critical embedded systems that rethinks both hypervisor and operating system architectures. TenonOS introduces a LibOS-on-LibOS model that decomposes hypervisor and operating system functionality into fine-grained, reusable micro-libraries. A generative orchestration engine dynamically composes these libraries to synthesize a customized runtime tailored to each application's criticality, timing requirements, and resource profile. TenonOS consists of two core components: Mortise, a minimalist micro-hypervisor, and Tenon, a real-time library operating system. Mortise provides lightweight isolation and removes the usual double-scheduler overhead in virtualized setups, while Tenon provides precise and deterministic task management. By generating only the necessary software stack per workload, TenonOS removes redundant layers, minimizes the trusted computing base, and maximizes responsiveness. Experiments show a 40.28 percent reduction in scheduling latency, an ultra-compact 361 KiB memory footprint, and strong adaptability.

cs.OS↗

arXiv2025

Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding

As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-augmented generation (RAG) methods typically treat code as plain natural language, relying primarily on shallow semantic matching while overlooking structural semantics and code-specific dependencies. This limits their ability to capture control flow and underlying intent, ultimately constraining the quality of generated code. Therefore, we propose CoCo, a novel framework that enables code Completion by Comprehension of multi-granularity context from large-scale code repositories. CoCo employs static code analysis to extract structured context at the function, file, and project levels, capturing execution logic and semantic dependencies. It then adopts an graph-based multi-granularity context selection mechanism to filter out redundant information and remove noise. Consequently, the information is converted into natural language in a consistent manner, thereby functioning as explicit contextual prompts to guide subsequent code completion. Additionally, a structure-aware code re-ranker mechanism ensures alignment at both semantic and structural levels. Extensive experiments on CrossCodeEval and RepoEval benchmarks demonstrate that CoCo consistently surpasses state-of-the-art baselines, achieving up to 20.2% gains in EM. Moreover, the framework is model-agnostic and can be seamlessly integrated into existing methods, leading to significant performance.

cs.SE↗

arXiv2025

TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentation

3D medical image segmentation is important for clinical diagnosis and treatment but faces challenges from high-dimensional data and complex spatial dependencies. Traditional single-modality networks, such as CNNs and Transformers, are often limited by computational inefficiency and constrained contextual modeling in 3D settings. To alleviate these limitations, we propose TK-Mamba, a multimodal framework that fuses the linear-time Mamba with Kolmogorov-Arnold Networks (KAN) to form an efficient hybrid backbone. Our approach is characterized by two primary technical contributions. Firstly, we introduce the novel 3D-Group-Rational KAN (3D-GR-KAN), which marks the first application of KAN in 3D medical imaging, providing a superior and computationally efficient nonlinear feature transformation crucial for complex volumetric structures. Secondly, we devise a dual-branch text-driven strategy using Pubmedclip's embeddings. This strategy significantly enhances segmentation robustness and accuracy by simultaneously capturing inter-organ semantic relationships to mitigate label inconsistencies and aligning image features with anatomical texts. By combining this advanced backbone and vision-language knowledge, TK-Mamba offers a unified and scalable solution for both multi-organ and tumor segmentation. Experiments on multiple datasets demonstrate that our framework achieves state-of-the-art performance in both organ and tumor segmentation tasks, surpassing existing methods in both accuracy and efficiency. Our code is publicly available at https://github.com/yhy-whu/TK-Mamba

cs.CV↗

arXiv2025

Integrating Artificial Intelligence into Operating Systems: A Survey on Techniques, Applications, and Future Directions

Heterogeneous hardware and dynamic workloads worsen long-standing OS bottlenecks in scalability, adaptability, and manageability. At the same time, advances in machine learning (ML), large language models (LLMs), and agent-based methods enable automation and self-optimization, but current efforts lack a unifying view. This survey reviews techniques, architectures, applications, challenges, and future directions at the AI-OS intersection. We chart the shift from heuristic- and rule-based designs to AI-enhanced systems, outlining the strengths of ML, LLMs, and agents across the OS stack. We summarize progress in AI for OS (core components and the wider ecosystem) and in OS for AI (component- and architecture-level support for short- and long-context inference, distributed training, and edge inference). For practice, we consolidate evaluation dimensions, methodological pipelines, and patterns that balance real-time constraints with predictive accuracy. We identify key challenges, such as complexity, overhead, model drift, limited explainability, and privacy and safety risks, and recommend modular, AI-ready kernel interfaces; unified toolchains and benchmarks; hybrid rules-plus-AI decisions with guardrails; and verifiable in-kernel inference. Finally, we propose a three-stage roadmap including AI-powered, AI-refactored, and AI-driven OSs, to bridge prototypes and production and to enable scalable, reliable AI deployment.

cs.OS↗

arXiv2025

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection

The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models (LLMs) and LLM-based agents have demonstrated remarkable capabilities in various software engineering (SE) tasks, enabling them to effectively address software security challenges such as vulnerability detection. However, systematic evaluation of the capabilities of LLMs and LLM-based agents in security patch detection remains limited. To bridge this gap, we conduct a comprehensive evaluation of the performance of LLMs and LLM-based agents for security patch detection. Specifically, we investigate three methods: Plain LLM (a single LLM with a system prompt), Data-Aug LLM (data augmentation based on the Plain LLM), and the ReAct Agent (leveraging the thought-action-observation mechanism). We also evaluate the performance of both commercial and open-source LLMs under these methods and compare these results with those of existing baselines. Furthermore, we analyze the detection performance of these methods across various vulnerability types, and examine the impact of different prompting strategies and context window sizes on the results. Our findings reveal that the Data-Aug LLM achieves the best overall performance, whereas the ReAct Agent demonstrates the lowest false positive rate (FPR). Although baseline methods exhibit strong accuracy, their false positive rates are significantly higher. In contrast, our evaluated methods achieve comparable accuracy while substantially reducing the FPR. These findings provide valuable insights into the practical applications of LLMs and LLM-based agents in security patch detection, highlighting their advantage in maintaining robust performance while minimizing false positive rates.

cs.CR↗

arXiv2025

Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation

Recent advancements in optimization-based text-to-3D generation heavily rely on distilling knowledge from pre-trained text-to-image diffusion models using techniques like Score Distillation Sampling (SDS), which often introduce artifacts such as over-saturation and over-smoothing into the generated 3D assets. In this paper, we address this essential problem by formulating the generation process as learning an optimal, direct transport trajectory between the distribution of the current rendering and the desired target distribution, thereby enabling high-quality generation with smaller Classifier-free Guidance (CFG) values. At first, we theoretically establish SDS as a simplified instance of the Schrödinger Bridge framework. We prove that SDS employs the reverse process of an Schrödinger Bridge, which, under specific conditions (e.g., a Gaussian noise as one end), collapses to SDS's score function of the pre-trained diffusion model. Based upon this, we introduce Trajectory-Centric Distillation (TraCe), a novel text-to-3D generation framework, which reformulates the mathematically trackable framework of Schrödinger Bridge to explicitly construct a diffusion bridge from the current rendering to its text-conditioned, denoised target, and trains a LoRA-adapted model on this trajectory's score dynamics for robust 3D optimization. Comprehensive experiments demonstrate that TraCe consistently achieves superior quality and fidelity to state-of-the-art techniques.

cs.CV↗

arXiv2025

Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives

Generative Artificial Intelligence (GenAI) is taking the world by storm. It promises transformative opportunities for advancing and disrupting existing practices, including healthcare. From large language models (LLMs) for clinical note synthesis and conversational assistance to multimodal systems that integrate medical imaging, electronic health records, and genomic data for decision support, GenAI is transforming the practice of medicine and the delivery of healthcare, such as diagnosis and personalized treatments, with great potential in reducing the cognitive burden on clinicians, thereby improving overall healthcare delivery. However, GenAI deployment in healthcare requires an in-depth understanding of healthcare tasks and what can and cannot be achieved. In this paper, we propose a data-centric paradigm in the design and deployment of GenAI systems for healthcare. Specifically, we reposition the data life cycle by making the medical data ecosystem as the foundational substrate for generative healthcare systems. This ecosystem is designed to sustainably support the integration, representation, and retrieval of diverse medical data and knowledge. With effective and efficient data processing pipelines, such as semantic vector search and contextual querying, it enables GenAI-powered operations for upstream model components and downstream clinical applications. Ultimately, it not only supplies foundation models with high-quality, multimodal data for large-scale pretraining and domain-specific fine-tuning, but also serves as a knowledge retrieval backend to support task-specific inference via the agentic layer. The ecosystem enables the deployment of GenAI for high-quality and effective healthcare delivery.

cs.AI↗

arXiv2025

Revisiting Vulnerability Patch Localization: An Empirical Study and LLM-Based Solution

Open-source software vulnerability patch detection is a critical component for maintaining software security and ensuring software supply chain integrity. Traditional manual detection methods face significant scalability challenges when processing large volumes of commit histories, while being prone to human errors and omissions. Existing automated approaches, including heuristic-based methods and pre-trained model solutions, suffer from limited accuracy, poor generalization capabilities, and inherent methodological constraints that hinder their practical deployment. To address these fundamental challenges, this paper conducts a comprehensive empirical study of existing vulnerability patch detection methods, revealing four key insights that guide the design of effective solutions: the critical impact of search space reduction, the superiority of pre-trained semantic understanding over architectural complexity, the temporal limitations of web crawling approaches, and the advantages of knowledge-driven methods. Based on these insights, we propose a novel two-stage framework that combines version-driven candidate filtering with large language model-based multi-round dialogue voting to achieve accurate and efficient vulnerability patch identification. Extensive experiments on a dataset containing 750 real vulnerabilities demonstrate that our method outperforms current approaches.

cs.SE↗

arXiv2025

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing

With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM to protect its IP, they have limitations when facing the more practical and complex demand, i.e., offering the individual user-level tracing in the black-box setting. This work presents CLMTracing, a black-box code LM watermarking framework employing the rule-based watermarks and utility-preserving injection method for user-level model tracing. CLMTracing further incorporates a parameter selection algorithm sensitive to the robust watermark and adversarial training to enhance the robustness against watermark removal attacks. Comprehensive evaluations demonstrate CLMTracing is effective across multiple state-of-the-art (SOTA) code LMs, showing significant harmless improvements compared to existing SOTA baselines and strong robustness against various removal attacks.

cs.PL↗

arXiv2025

GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion

LLMs excel in localized code completion but struggle with repository-level tasks due to limited context windows and complex semantic and structural dependencies across codebases. While Retrieval-Augmented Generation (RAG) mitigates context scarcity by retrieving relevant code snippets, current approaches face significant limitations. They overly rely on textual similarity for retrieval, neglecting structural relationships such as call chains and inheritance hierarchies, and lose critical structural information by naively concatenating retrieved snippets into text sequences for LLM input. To address these shortcomings, GRACE constructs a multi-level, multi-semantic code graph that unifies file structures, abstract syntax trees, function call graphs, class hierarchies, and data flow graphs to capture both static and dynamic code semantics. For retrieval, GRACE employs a Hybrid Graph Retriever that integrates graph neural network-based structural similarity with textual retrieval, refined by a graph attention network-based re-ranker to prioritize topologically relevant subgraphs. To enhance context, GRACE introduces a structural fusion mechanism that merges retrieved subgraphs with the local code context and preserves essential dependencies like function calls and inheritance. Extensive experiments on public repository-level benchmarks demonstrate that GRACE significantly outperforms state-of-the-art methods across all metrics. Using DeepSeek-V3 as the backbone LLM, GRACE surpasses the strongest graph-based RAG baselines by 8.19% EM and 7.51% ES points on every dataset. The code is available at https://anonymous.4open.science/r/grace_icse-C3D5.

cs.SE↗

arXiv2025

ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in vision-language understanding. Recently, with the integration of test-time scaling techniques, these models have also shown strong potential in visual reasoning. However, most existing reasoning approaches remain text-level in nature: MLLMs are prompted to explore various combinations of textual tokens via their underlying language model, while the visual input remains fixed throughout the reasoning process. This paradigm limits the model's ability to fully exploit rich visual information, particularly when dealing with images containing numerous fine-grained elements. In such cases, vision-level reasoning becomes crucial - where models dynamically zoom into specific regions of the image to gather detailed visual cues necessary for accurate decision-making. In this paper, we propose Zoom Eye, a training-free, model-agnostic tree search algorithm tailored for vision-level reasoning. Zoom Eye treats an image as a hierarchical tree structure, where each child node represents a zoomed-in sub-region of its parent, and the root corresponds to the full image. The algorithm enables MLLMs to simulate human-like zooming behavior by navigating from root to leaf nodes in search of task-relevant visual evidence. We experiment on a series of high-resolution benchmarks and the results demonstrate that Zoom Eye consistently improves the performance of multiple MLLMs by a large margin (e.g., InternVL2.5-8B increases by 15.71% and 17.69% on HR-Bench) and also enables small 3-8B MLLMs to outperform strong large models such as GPT-4o. Code: https://github.com/om-ai-lab/ZoomEye

cs.CV↗

arXiv2025

BPI: A Novel Efficient and Reliable Search Structure for Hybrid Storage Blockchain

Hybrid storage solutions have emerged as potent strategies to alleviate the data storage bottlenecks prevalent in blockchain systems. These solutions harness off-chain Storage Services Providers (SPs) in conjunction with Authenticated Data Structures (ADS) to ensure data integrity and accuracy. Despite these advancements, the reliance on centralized SPs raises concerns about query correctness. Although ADS can verify the existence of individual query results, they fall short of preventing SPs from omitting valid results. In this paper, we delineate the fundamental distinctions between data search in blockchains and traditional database systems. Drawing upon these insights, we introduce BPI, a lightweight framework that enables efficient keyword queries and maintenance with low overhead. We propose "Articulated Search", a query pattern specifically designed for blockchain environments that enhances search efficiency while significantly reducing costs during data user updates. Furthermore, BPI employs a suite of validation models to ensure the inclusion of all valid content in search results while maintaining low overhead. Extensive experimental evaluations demonstrate that the BPI framework achieves outstanding scalability and performance in keyword searches within blockchain, surpassing EthMB+ and state of the art search databases commonly used in mainstream hybrid storage blockchains (HSB).

cs.DB↗

arXiv2025

VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning

Recent advancements in code generation have shown remarkable success across software domains, yet hardware description languages (HDLs) such as Verilog remain underexplored due to their concurrency semantics, syntactic rigidity, and simulation complexity. In this work, we address these challenges by introducing a reinforcement learning (RL) framework tailored for Verilog code generation. We first construct Veribench-53K, a high-quality dataset curated from over 700K Verilog problems, enriched with structured prompts, complexity labels, and diverse testbenches. To tackle the problem of sparse and noisy reward signals, we propose a Trace-back based Rescore mechanism that leverages reasoning paths and iterative refinement to enhance feedback reliability and support reward model training. Furthermore, to mitigate catastrophic forgetting and overfitting during RL fine-tuning, we introduce a sample-balanced weighting strategy that adaptively balances learning dynamics based on reward-probability distributions. These innovations are integrated into an iterative RL pipeline that co-evolves the policy and reward models. In contrast to recent work such as CraftRTL, which relies on large-scale closed-source model distillation, and DeepSeek-style approaches that struggle with sparse feedback, our method demonstrates superior performance using a smaller but high-quality dataset combined with RL optimization. Experiments on Verilog generation tasks demonstrate state-of-the-art performance, with substantial gains in test pass rate, functional correctness, and compilation robustness. Our findings highlight the potential of RL-driven approaches for structured code generation in hardware-centric domains. VERIRL is publicly available at https://github.com/omniAI-Lab/VeriRL.

cs.LG↗

arXiv2025

Preguss: It Analyzes, It Specifies, It Verifies

Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recently demonstrated their potential for enhancing the degree of automation in formal verification by, e.g., generating formal specifications as essential to deductive verification, yet exhibit poor scalability due to context-length limitations and, more importantly, the difficulty of inferring complex, interprocedural specifications. This paper outlines Preguss - a modular, fine-grained framework for automating the generation and refinement of formal specifications. Preguss synergizes between static analysis and deductive verification by orchestrating two components: (i) potential runtime error (RTE)-guided construction and prioritization of verification units, and (ii) LLM-aided synthesis of interprocedural specifications at the unit level. We envisage that Preguss paves a compelling path towards the automated verification of large-scale programs.

cs.SE↗

arXiv2025

Tool-Planner: Task Planning with Clusters across Multiple Tools

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing examples of tool usage and their corresponding functions, allowing LLMs to formulate plans and demonstrate the process of invoking and executing each tool. LLMs can address tasks that they cannot complete independently, thereby enhancing their potential across different tasks. However, this approach faces two key challenges. First, redundant error correction leads to unstable planning and long execution time. Additionally, designing a correct plan among multiple tools is also a challenge in tool learning. To address these issues, we propose Tool-Planner, a task-processing framework based on toolkits. Tool-Planner groups tools based on the API functions with the same function into a toolkit and allows LLMs to implement planning across the various toolkits. When a tool error occurs, the language model can reselect and adjust tools based on the toolkit. Experiments show that our approach demonstrates a high pass and win rate across different datasets and optimizes the planning scheme for tool learning in models such as GPT-4 and Claude 3, showcasing the potential of our method. Our code is public at https://github.com/OceannTwT/Tool-Planner

cs.AI↗

arXiv2025

Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding

Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These challenges often arise due to the complexity and ambiguity present in longer texts. To enhance the performance of LLMs in such scenarios, we introduce the Long Question Coreference Adaptation (LQCA) method. This innovative framework focuses on coreference resolution tailored to long contexts, allowing the model to identify and manage references effectively. The LQCA method encompasses four key steps: resolving coreferences within sub-documents, computing the distances between mentions, defining a representative mention for coreference, and answering questions through mention replacement. By processing information systematically, the framework provides easier-to-handle partitions for LLMs, promoting better understanding. Experimental evaluations on a range of LLMs and datasets have yielded positive results, with a notable improvements on OpenAI-o1-mini and GPT-4o models, highlighting the effectiveness of leveraging coreference resolution to bridge context gaps in question answering. Our code is public at https://github.com/OceannTwT/LQCA.

cs.CL↗

arXiv2025

Data-Locality-Aware Task Assignment and Scheduling for Distributed Job Executions

This paper addresses the data-locality-aware task assignment and scheduling problem for distributed job executions. Our goal is to minimize job completion times without prior knowledge of future job arrivals. We propose an Optimal Balanced Task Assignment algorithm (OBTA), which achieves minimal job completion times while significantly reducing computational overhead through efficient narrowing of the solution search space. To balance performance and efficiency, we extend the approximate Water-Filling (WF) algorithm, providing a rigorous proof that its approximation factor equals the number of task groups in a job. We also introduce a novel heuristic, Replica-Deletion (RD), which outperforms WF by leveraging global optimization techniques. To further enhance scheduling efficiency, we incorporate job ordering strategies based on a shortest-estimated-time-first policy, reducing average job completion times across workloads. Extensive trace-driven evaluations validate the effectiveness and scalability of the proposed algorithms.

cs.DC↗