arXiv subjects

Shuai Wang

Publications and source records attributed to Shuai Wang.

At least 415 records · Page 23Linked to original sources

arXiv2025

Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models

Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like buffer overflows and use-after-free errors. Traditional fuzzing struggles with the complexity and API diversity of DL libraries such as TensorFlow and PyTorch, which feature over 1,000 APIs. Testing all these APIs is challenging due to complex inputs and varied usage patterns. While large language models (LLMs) show promise in code understanding and generation, existing LLM-based fuzzers lack deep knowledge of API edge cases and struggle with test input generation. To address this, we propose DFUZZ, an LLM-driven fuzzing approach for DL libraries. DFUZZ leverages two insights: (1) LLMs can reason about error-triggering edge cases from API code and apply this knowledge to untested APIs, and (2) LLMs can accurately synthesize test programs to automate API testing. By providing LLMs with a "white-box view" of APIs, DFUZZ enhances reasoning and generation for comprehensive fuzzing. Experimental results show that DFUZZ outperforms state-of-the-art fuzzers in API coverage for TensorFlow and PyTorch, uncovering 37 bugs, with 8 fixed and 19 under developer investigation.

cs.SE↗

arXiv2024

ProofCloud: A Proof Retrieval Engine for Verified Proofs in Higher Order Logic

This paper introduces ProofCloud, a proof retrieval engine for verified proofs in higher order logic. It provides a fast proof searching service for mathematicians and computer scientists for the reuse of proofs and proof packages. In addition, it includes the first complete proof-checking results and benchmarks of the OpenTheory repository.

cs.LO↗

arXiv2024

A Qualitative Analysis of Kernel Extension for Higher Order Proof Checking

For the sake of reliability, the kernels of Interactive Theorem Provers (ITPs) are generally kept relatively small. On top of the kernel, additional symbols and inference rules are defined. This paper presents an analysis of how kernel extension reduces the size of proofs and impacts proof checking.

cs.LO↗

arXiv2024

Clutter Resilient Occlusion Avoidance for Tightly-Coupled Motion-Assisted Detection

Occlusion is a key factor leading to detection failures. This paper proposes a motion-assisted detection (MAD) method that actively plans an executable path, for the robot to observe the target at a new viewpoint with potentially reduced occlusion. In contrast to existing MAD approaches that may fail in cluttered environments, the proposed framework is robust in such scenarios, therefore termed clutter resilient occlusion avoidance (CROA). The crux to CROA is to minimize the occlusion probability under polyhedron-based collision avoidance constraints via the convex-concave procedure and duality-based bilevel optimization. The system implementation supports lidar-based MAD with intertwined execution of learning-based detection and optimization-based planning. Experiments show that CROA outperforms various MAD schemes under a sparse convolutional neural network detector, in terms of point density, occlusion ratio, and detection error, in a multi-lane urban driving scenario.

cs.RO↗

arXiv2024

Linked Data on Geo-annotated Events and Use Cases for the Resilience of Ukraine

The mission of resilience of Ukrainian cities calls for international collaboration with the scientific community to increase the quality of information by identifying and integrating information from various news and social media sources. Linked Data technology can be used to unify, enrich, and integrate data from multiple sources. In our work, we focus on datasets about damaging events in Ukraine due to Russia's invasion between February 2022 and the end of April 2023. We convert two selected datasets to Linked Data and enrich them with additional geospatial information. Following that, we present an algorithm for the detection of identical events from different datasets. Our pipeline makes it easy to convert and enrich datasets to integrated Linked Data. The resulting dataset consists of 10K reported events covering damage to hospitals, schools, roads, residential buildings, etc. Finally, we demonstrate in use cases how our dataset can be applied to different scenarios for resilience purposes.

cs.CY↗

arXiv2024

How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation

Visual deep learning (VDL) systems have shown significant success in real-world applications like image recognition, object detection, and autonomous driving. To evaluate the reliability of VDL, a mainstream approach is software testing, which requires diverse mutations over image semantics. The rapid development of multi-modal large language models (MLLMs) has introduced revolutionary image mutation potentials through instruction-driven methods. Users can now freely describe desired mutations and let MLLMs generate the mutated images. Hence, parallel to large language models' (LLMs) recent success in traditional software fuzzing, one may also expect MLLMs to be promising for VDL testing in terms of offering unified, diverse, and complex image mutations. However, the quality and applicability of MLLM-based mutations in VDL testing remain largely unexplored. We present the first study, aiming to assess MLLMs' adequacy from 1) the semantic validity of MLLM mutated images, 2) the alignment of MLLM mutated images with their text instructions (prompts), and 3) the faithfulness of how different mutations preserve semantics that are ought to remain unchanged. With large-scale human studies and quantitative evaluations, we identify MLLM's promising potentials in expanding the covered semantics of image mutations. Notably, while SoTA MLLMs (e.g., GPT-4V) fail to support or perform worse in editing existing semantics in images (as in traditional mutations like rotation), they generate high-quality test inputs using "semantic-replacement" mutations (e.g., "dress a dog with clothes"), which bring extra semantics to images; these were infeasible for past approaches. Hence, we view MLLM-based mutations as a vital complement to traditional mutations, and advocate future VDL testing tasks to combine MLLM-based methods and traditional image mutations for comprehensive and reliable testing.

cs.SE↗

arXiv2024

SUBMASSIVE: Resolving Subclass Cycles in Very Large Knowledge Graphs

Large knowledge graphs capture information of a large number of entities and their relations. Among the many relations they capture, class subsumption assertions are usually present and expressed using the \texttt{rdfs:subClassOf} construct. From our examination, publicly available knowledge graphs contain many potentially erroneous cyclic subclass relations, a problem that can be exacerbated when different knowledge graphs are integrated as Linked Open Data. In this paper, we present an automatic approach for resolving such cycles at scale using automated reasoning by encoding the problem of cycle-resolving to a MAXSAT solver. The approach is tested on the LOD-a-lot dataset, and compared against a semi-automatic version of our algorithm. We show how the number of removed triples is a trade-off against the efficiency of the algorithm.

cs.LO↗

arXiv2024

VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis

This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly understand remote sensing images and perform diverse remote sensing tasks. Moreover, different from existing remote sensing instruction datasets that only include factual questions, HnstD contains additional deceptive questions stemming from the non-existence of objects. This feature prevents VHM from producing affirmative answers to nonsense queries, thereby ensuring its honesty. In our experiments, VHM significantly outperforms various vision language models on common tasks of scene classification, visual question answering, and visual grounding. Additionally, VHM achieves competent performance on several unexplored tasks, such as building vectorizing, multi-label classification and honest question answering. We will release the code, data and model weights at https://github.com/opendatalab/VHM .

cs.CV↗

arXiv2024

Surrealistic-like Image Generation with Vision-Language Models

Recent advances in generative AI make it convenient to create different types of content, including text, images, and code. In this paper, we explore the generation of images in the style of paintings in the surrealism movement using vision-language generative models, including DALL-E, Deep Dream Generator, and DreamStudio. Our investigation starts with the generation of images under various image generation settings and different models. The primary objective is to identify the most suitable model and settings for producing such images. Additionally, we aim to understand the impact of using edited base images on the generated resulting images. Through these experiments, we evaluate the performance of selected models and gain valuable insights into their capabilities in generating such images. Our analysis shows that Dall-E 2 performs the best when using the generated prompt by ChatGPT.

cs.CV↗

arXiv2024

AI PERSONA: Towards Life-long Personalization of LLMs

In this work, we introduce the task of life-long personalization of large language models. While recent mainstream efforts in the LLM community mainly focus on scaling data and compute for improved capabilities of LLMs, we argue that it is also very important to enable LLM systems, or language agents, to continuously adapt to the diverse and ever-changing profiles of every distinct user and provide up-to-date personalized assistance. We provide a clear task formulation and introduce a simple, general, effective, and scalable framework for life-long personalization of LLM systems and language agents. To facilitate future research on LLM personalization, we also introduce methods to synthesize realistic benchmarks and robust evaluation metrics. We will release all codes and data for building and benchmarking life-long personalized LLM systems.

cs.CL↗

arXiv2024

RecSys Arena: Pair-wise Recommender System Evaluation with Large Language Models

Evaluating the quality of recommender systems is critical for algorithm design and optimization. Most evaluation methods are computed based on offline metrics for quick algorithm evolution, since online experiments are usually risky and time-consuming. However, offline evaluation usually cannot fully reflect users' preference for the outcome of different recommendation algorithms, and the results may not be consistent with online A/B test. Moreover, many offline metrics such as AUC do not offer sufficient information for comparing the subtle differences between two competitive recommender systems in different aspects, which may lead to substantial performance differences in long-term online serving. Fortunately, due to the strong commonsense knowledge and role-play capability of large language models (LLMs), it is possible to obtain simulated user feedback on offline recommendation results. Motivated by the idea of LLM Chatbot Arena, in this paper we present the idea of RecSys Arena, where the recommendation results given by two different recommender systems in each session are evaluated by an LLM judger to obtain fine-grained evaluation feedback. More specifically, for each sample we use LLM to generate a user profile description based on user behavior history or off-the-shelf profile features, which is used to guide LLM to play the role of this user and evaluate the relative preference for two recommendation results generated by different models. Through extensive experiments on two recommendation datasets in different scenarios, we demonstrate that many different LLMs not only provide general evaluation results that are highly consistent with canonical offline metrics, but also provide rich insight in many subjective aspects. Moreover, it can better distinguish different algorithms with comparable performance in terms of AUC and nDCG.

cs.IR↗

arXiv2024

Multi-Level Speaker Representation for Target Speaker Extraction

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model's generalization capability. Additionally, we propose a contextual embedding feature based on cross-attention mechanisms that integrate frame-level embeddings from a pre-trained speaker encoder. By incorporating speaker features across multiple levels, we significantly enhance the performance of the TSE model. Our approach achieves a 2.74 dB improvement and a 4.94% increase in extraction accuracy on Libri2mix test set over the baseline.

eess.AS↗

arXiv2024

Split and Merge: Aligning Position Biases in LLM-based Evaluators

Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems. However, these LLM-based evaluators exhibit position bias, or inconsistency, when used to evaluate candidate answers in pairwise comparisons, favoring either the first or second answer regardless of content. To address this limitation, we propose PORTIA, an alignment-based system designed to mimic human comparison strategies to calibrate position bias in a lightweight yet effective manner. Specifically, PORTIA splits the answers into multiple segments, aligns similar content across candidate answers, and then merges them back into a single prompt for evaluation by LLMs. We conducted extensive experiments with six diverse LLMs to evaluate 11,520 answer pairs. Our results show that PORTIA markedly enhances the consistency rates for all the models and comparison forms tested, achieving an average relative improvement of 47.46%. Remarkably, PORTIA enables less advanced GPT models to achieve 88% agreement with the state-of-the-art GPT-4 model at just 10% of the cost. Furthermore, it rectifies around 80% of the position bias instances within the GPT-4 model, elevating its consistency rate up to 98%. Subsequent human evaluations indicate that the PORTIA-enhanced GPT-3.5 model can even surpass the standalone GPT-4 in terms of alignment with human evaluators. These findings highlight PORTIA's ability to correct position bias, improve LLM consistency, and boost performance while keeping cost-efficiency. This represents a valuable step toward a more reliable and scalable use of LLMs for automated evaluations across diverse applications.

cs.CL↗

arXiv2024

Fab-ME: A Vision State-Space and Attention-Enhanced Framework for Fabric Defect Detection

Effective defect detection is critical for ensuring the quality, functionality, and economic value of textile products. However, existing methods face challenges in achieving high accuracy, real-time performance, and efficient global information extraction. To address these issues, we propose Fab-ME, an advanced framework based on YOLOv8s, specifically designed for the accurate detection of 20 fabric defect types. Our contributions include the introduction of the cross-stage partial bottleneck with two convolutions (C2F) vision state-space (C2F-VMamba) module, which integrates visual state-space (VSS) blocks into the YOLOv8s feature fusion network neck, enhancing the capture of intricate details and global context while maintaining high processing speeds. Additionally, we incorporate an enhanced multi-scale channel attention (EMCA) module into the final layer of the feature extraction network, significantly improving sensitivity to small targets. Experimental results on the Tianchi fabric defect detection dataset demonstrate that Fab-ME achieves a 3.5% improvement in mAP@0.5 compared to the original YOLOv8s, validating its effectiveness for precise and efficient fabric defect detection.

cs.CV↗

arXiv2024

Preserving Privacy in Software Composition Analysis: A Study of Technical Solutions and Enhancements

Software composition analysis (SCA) denotes the process of identifying open-source software components in an input software application. SCA has been extensively developed and adopted by academia and industry. However, we notice that the modern SCA techniques in industry scenarios still need to be improved due to privacy concerns. Overall, SCA requires the users to upload their applications' source code to a remote SCA server, which then inspects the applications and reports the component usage to users. This process is privacy-sensitive since the applications may contain sensitive information, such as proprietary source code, algorithms, trade secrets, and user data. Privacy concerns have prevented the SCA technology from being used in real-world scenarios. Therefore, academia and the industry demand privacy-preserving SCA solutions. For the first time, we analyze the privacy requirements of SCA and provide a landscape depicting possible technical solutions with varying privacy gains and overheads. In particular, given that de facto SCA frameworks are primarily driven by code similarity-based techniques, we explore combining several privacy-preserving protocols to encapsulate the similarity-based SCA framework. Among all viable solutions, we find that multi-party computation (MPC) offers the strongest privacy guarantee and plausible accuracy; it, however, incurs high overhead (184 times). We optimize the MPC-based SCA framework by reducing the amount of crypto protocol transactions using program analysis techniques. The evaluation results show that our proposed optimizations can reduce the MPC-based SCA overhead to only 8.5% without sacrificing SCA's privacy guarantee or accuracy.

cs.SE↗

arXiv2024

Adaptive Interactive Segmentation for Multimodal Medical Imaging via Selection Engine

In medical image analysis, achieving fast, efficient, and accurate segmentation is essential for automated diagnosis and treatment. Although recent advancements in deep learning have significantly improved segmentation accuracy, current models often face challenges in adaptability and generalization, particularly when processing multi-modal medical imaging data. These limitations stem from the substantial variations between imaging modalities and the inherent complexity of medical data. To address these challenges, we propose the Strategy-driven Interactive Segmentation Model (SISeg), built on SAM2, which enhances segmentation performance across various medical imaging modalities by integrating a selection engine. To mitigate memory bottlenecks and optimize prompt frame selection during the inference of 2D image sequences, we developed an automated system, the Adaptive Frame Selection Engine (AFSE). This system dynamically selects the optimal prompt frames without requiring extensive prior medical knowledge and enhances the interpretability of the model's inference process through an interactive feedback mechanism. We conducted extensive experiments on 10 datasets covering 7 representative medical imaging modalities, demonstrating the SISeg model's robust adaptability and generalization in multi-modal tasks. The project page and code will be available at: [URL].

cs.CV↗

arXiv2024

SurgeMOD: Translating image-space tissue motions into vision-based surgical forces

We present a new approach for vision-based force estimation in Minimally Invasive Robotic Surgery based on frequency domain basis of motion of organs derived directly from video. Using internal movements generated by natural processes like breathing or the cardiac cycle, we infer the image-space basis of the motion on the frequency domain. As we are working with this representation, we discretize the problem to a limited amount of low-frequencies to build an image-space mechanical model of the environment. We use this pre-built model to define our force estimation problem as a dynamic constraint problem. We demonstrate that this method can estimate point contact forces reliably for silicone phantom and ex-vivo experiments, matching real readings from a force sensor. In addition, we perform qualitative experiments in which we synthesize coherent force textures from surgical videos over a certain region of interest selected by the user. Our method demonstrates good results for both quantitative and qualitative analysis, providing a good starting point for a purely vision-based method for surgical force estimation.

cs.CV↗

arXiv2024

2D Matryoshka Training for Information Retrieval

2D Matryoshka Training is an advanced embedding representation training approach designed to train an encoder model simultaneously across various layer-dimension setups. This method has demonstrated higher effectiveness in Semantic Text Similarity (STS) tasks over traditional training approaches when using sub-layers for embeddings. Despite its success, discrepancies exist between two published implementations, leading to varied comparative results with baseline models. In this reproducibility study, we implement and evaluate both versions of 2D Matryoshka Training on STS tasks and extend our analysis to retrieval tasks. Our findings indicate that while both versions achieve higher effectiveness than traditional Matryoshka training on sub-dimensions, and traditional full-sized model training approaches, they do not outperform models trained separately on specific sub-layer and sub-dimension setups. Moreover, these results generalize well to retrieval tasks, both in supervised (MSMARCO) and zero-shot (BEIR) settings. Further explorations of different loss computations reveals more suitable implementations for retrieval tasks, such as incorporating full-dimension loss and training on a broader range of target dimensions. Conversely, some intuitive approaches, such as fixing document encoders to full model outputs, do not yield improvements. Our reproduction code is available at https://github.com/ielab/2DMSE-Reproduce.

cs.IR↗