Paper Summaries

    Category: AI

    • Summary of the paper: “Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis”

      paper citation: Vashist, Chirag, Shichong Peng, and Ke Li. “Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis.” arXiv preprint arXiv:2409.17439 (2024). Summary: In the world of image generation, creating high-quality images usually requires vast amounts of training data. However, there are situations where getting enough data is hard or expensive, such as in…

    • Summary of the paper “CodePilot: Enhancing Code Coverage Prediction”

      Paper citation: Dhulipala, Hridya, Aashish Yadavally, and Tien N. Nguyen. “Planning to Guide LLM for Code Coverage Prediction.” In Proceedings of the 2024 IEEE/ACM First International Conference on AI Foundation Models and Software Engineering, pp. 24–34. 2024. Summary CodePilot is a novel prompting approach. It uses program semantics to improve code coverage prediction with a…

    • Summary of the paper “Harnessing the Power of LLM to Support Binary Taint Analysis”

      arXiv, 2023 Paper citation: Liu, Puzhuo, Chengnian Sun, Yaowen Zheng, Xuan Feng, Chuan Qin, Yuncheng Wang, Zhi Li, and Limin Sun. “Harnessing the power of llm to support binary taint analysis.” arXiv preprint arXiv:2310.08275 (2023).  Brief Summary: Use LLM (almost exclusively) to do taint analysis. Main idea: Identifying sources, sinks, and propagation flow rules is…

    • Summary of the paper: “DescribeCtx: Context-Aware Description Synthesis for Sensitive Behaviors in Mobile Apps”

      Paper citation: Yang, Shao, Yuehan Wang, Yuan Yao, Haoyu Wang, Yanfang Ye, and Xusheng Xiao. “Describectx: context-aware description synthesis for sensitive behaviors in mobile apps.” In Proceedings of the 44th International Conference on Software Engineering, pp. 685–697. 2022. Summary: Generate app description given the code, GUI text, and requested permissions. Approach: 1. Extract features from…

    • Summary of the paper: “COSTELLO: Contrastive Testing for Embedding-Based Large Language Model as a Service Embeddings”

      Paper citation: Jiang, Weipeng, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, and Chao Shen. “COSTELLO: Contrastive Testing for Embedding-Based Large Language Model as a Service Embeddings.” Proceedings of the ACM on Software Engineering 1, no. FSE (July 12, 2024): 906–28. https://doi.org/10.1145/3643767. Summary: This paper presents Costello a contrastive learning approach for testing validating the embeddings of…

    • Glossary of LLM Terms and Abbreviations in Academic Papers

      This is a list of all terms related to large language models that I found while reading academic papers in that field. I will keep adding to this glossary each time I encounter a new term (ISA), please let me know if you find a missing term in this list. This list is in ascending…