Search

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLMs for automated bug fixing remains challenging due to the complexity and diversity of real-world software systems. In this paper, we introduce MarsCode Agent, a novel framework that leverages LLMs to automatically identify and repair bugs in software code. MarsCode Agent combines the power of LLMs with advanced code analysis techniques to accurately localize faults and generate patches. Our approach follows a systematic process of planning, bug reproduction, fault localization, candidate patch generation, and validation to ensure high-quality bug fixes. We evaluated MarsCode Agent on SWE-bench, a comprehensive benchmark of real-world software projects, and our results show that MarsCode Agent achieves a high success rate in bug fixing compared to most of the existing automated approaches., Comment: Yizhou Liu and Pengfei Gao contributed equally and the order is determined by rolling the dice. Chao Peng is the corresponding author

With the growing reliance on automated code completion tools in software development, the need for robust evaluation benchmarks has become critical. However, existing benchmarks focus more on code generation tasks in function and class level and provide rich text description to prompt the model. By contrast, such descriptive prompt is commonly unavailable in real development and code completion can occur in wider range of situations such as in the middle of a function or a code block. These limitations makes the evaluation poorly align with the practical scenarios of code completion tools. In this paper, we propose RepoMasterEval, a novel benchmark for evaluating code completion models constructed from real-world Python and TypeScript repositories. Each benchmark datum is generated by masking a code snippet (ground truth) from one source code file with existing test suites. To improve test accuracy of model generated code, we employ mutation testing to measure the effectiveness of the test cases and we manually crafted new test cases for those test suites with low mutation score. Our empirical evaluation on 6 state-of-the-art models shows that test argumentation is critical in improving the accuracy of the benchmark and RepoMasterEval is able to report difference in model performance in real-world scenarios. The deployment of RepoMasterEval in a collaborated company for one month also revealed that the benchmark is useful to give accurate feedback during model training and the score is in high correlation with the model's performance in practice. Based on our findings, we call for the software engineering community to build more LLM benchmarks tailored for code generation tools taking the practical and complex development environment into consideration.

Recently, an audio-visual segmentation (AVS) task has been introduced, aiming to group pixels with sounding objects within a given video. This task necessitates a first-ever audio-driven pixel-level understanding of the scene, posing significant challenges. In this paper, we propose an innovative audio-visual transformer framework, termed COMBO, an acronym for COoperation of Multi-order Bilateral relatiOns. For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement. Regarding pixel entanglement, we employ a Siam-Encoder Module (SEM) that leverages prior knowledge to generate more precise visual features from the foundational model. For modality entanglement, we design a Bilateral-Fusion Module (BFM), enabling COMBO to align corresponding visual and auditory signals bi-directionally. As for temporal entanglement, we introduce an innovative adaptive inter-frame consistency loss according to the inherent rules of temporal. Comprehensive experiments and ablation studies on AVSBench-object (84.7 mIoU on S4, 59.2 mIou on MS3) and AVSBench-semantic (42.1 mIoU on AVSS) datasets demonstrate that COMBO surpasses previous state-of-the-art methods. Code and more results will be publicly available at https://yannqi.github.io/AVS-COMBO/., Comment: CVPR 2024 Highlight. 13 pages, 10 figures

Fault injection attacks represent a type of active, physical attack against cryptographic circuits. Various countermeasures have been proposed to thwart such attacks, the design and implementation of which are, however, intricate, error-prone, and laborious. The current formal fault-resistance verification approaches are limited in efficiency and scalability. In this paper, we formalize the fault-resistance verification problem which is shown to be NP-complete. We then devise a novel approach for encoding the fault-resistance verification problem as the Boolean satisfiability (SAT) problem so that off-the-shelf SAT solvers can be utilized. The approach is implemented in an open-source tool FIRMER which is evaluated extensively on realistic cryptographic circuit benchmarks. The experimental results show that FIRMER is able to verify fault-resistance of almost all (46/48) benchmarks in 3 minutes (the other two are verified in 35 minutes). In contrast, the prior approach fails on 23 fault-resistance verification tasks even after 24 hours (per task).

In this paper, we present the Multi-Forgery Detection Challenge held concurrently with the IEEE Computer Society Workshop on Biometrics at CVPR 2022. Our Multi-Forgery Detection Challenge aims to detect automatic image manipulations including but not limited to image editing, image synthesis, image generation, image photoshop, etc. Our challenge has attracted 674 teams from all over the world, with about 2000 valid result submission counts. We invited the Top 10 teams to present their solutions to the challenge, from which three teams are awarded prizes in the grand finale. In this paper, we present the solutions from the Top 3 teams, in order to boost the research work in the field of image forgery detection., Comment: Workshop and challenge summary paper, containing technical reports from different teams

Many important classification problems in the real-world consist of a large number of closely related categories in a hierarchical structure or taxonomy. Hierarchical multi-label text classification (HMTC) with higher accuracy over large sets of closely related categories organized in a hierarchy or taxonomy has become a challenging problem. In this paper, we present a hierarchical and fine-tuning approach based on the Ordered Neural LSTM neural network, abbreviated as HFT-ONLSTM, for more accurate level-by-level HMTC. First, we present a novel approach to learning the joint embeddings based on parent category labels and textual data for accurately capturing the joint features of both category labels and texts. Second, a fine tuning technique is adopted for training parameters such that the text classification results in the upper level should contribute to the classification in the lower one. At last, the comprehensive analysis is made based on extensive experiments in comparison with the state-of-the-art hierarchical and flat multi-label text classification approaches over two benchmark datasets, and the experimental results show that our HFT-ONLSTM approach outperforms these approaches, in particular reducing computational costs while achieving superior performance., Comment: 31 pages, 8 tables, 4 figures