Aman Sharma

Serena Cofano, Daniel Williams, Aman Sharma et al.

Runtime introspection of dependencies, i.e., the ability to observe which dependencies are currently used during program execution, is fundamental for Software Supply Chain security. Yet, Java has no support for it. We solve this problem with Classport, a blueprint and system that embeds dependency information into Java class files, enabling the retrieval of dependency information at runtime. We evaluate Classport on six real-world projects, demonstrating the feasibility in identifying dependencies at runtime.

Hossein Rajabzadeh, Aref Jafari, Aman Sharma et al.

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased computational demands, particularly during inference and fine-tuning. To address these challenges, we introduce EchoAtt, a novel framework aimed at optimizing transformer-based models by analyzing and leveraging the similarity of attention patterns across layers. Our analysis reveals that many inner layers in LLMs, especially larger ones, exhibit highly similar attention matrices. By exploiting this similarity, EchoAtt enables the sharing of attention matrices in less critical layers, significantly reducing computational requirements without compromising performance. We incorporate this approach within a knowledge distillation setup, where a pre-trained teacher model guides the training of a smaller student model. The student model selectively shares attention matrices in layers with high similarity while inheriting key parameters from the teacher. Our best results with TinyLLaMA-1.1B demonstrate that EchoAtt improves inference speed by 15\%, training speed by 25\%, and reduces the number of parameters by approximately 4\%, all while improving zero-shot performance. These findings highlight the potential of attention matrix sharing to enhance the efficiency of LLMs, making them more practical for real-time and resource-limited applications.

Aman Sharma, Ashutosh Bhatia

Bitcoin is the most popular cryptocurrency used worldwide. It provides pseudonymity to its users by establishing identity using public keys as transaction end-points. These transactions are recorded on an immutable public ledger called Blockchain which is an append-only data structure. The popularity of Bitcoin has increased unreasonably. The general trend shows a positive response from the common masses indicating an increase in trust and privacy concerns which makes an interesting use case from the analysis point of view. Moreover, since the blockchain is publicly available and up-to-date, any analysis would provide a live insight into the usage patterns which ultimately would be useful for making a number of inferences by law-enforcement agencies, economists, tech-enthusiasts, etc. In this paper, we study various applications and techniques of performing data analytics over Bitcoin blockchain from a graph theoretic perspective. We also propose a framework for performing such data analytics and explored a couple of use cases using the proposed framework.