• Robustness of foundational models for hate speech detection: analyzing pretraining dynamics and finetuning settings 

  Khan, Mohammad Aflah; Akhtar, Md. Shad (Advisor) (IIIT-Delhi, 2023-11-29)

  Despite the widespread adoption, there is a lack of research into how various critical aspects of LLMs affect their performance in hate speech detection. Through five research questions, our findings and recommendations ...
• A comparative analysis of large language models for code documentation generation 

  Dvivedi, Shubhang Shekhar; Pujari, Sai Leela Rahul; Vijay, Vyshnav; Lodh, Shoumik; Kumar, Dhruv (Advisor) (IIIT-Delhi, 2023-11-29)

  This paper presents a comprehensive comparative analysis of Large Language Models (LLMs) for code documentation generation. Code documentation is an essential part of the software writing process as it allows a new user ...
• Application supported ERP therapy for OCD patients 

  Sharma, Mohit; Jaiswal, Vaibhav; Singh, Pushpendra (Advisor) (IIIT-Delhi, 2023-11-29)

  This research project focuses on addressing the challenges associated with the treatment of Obsessive–Compulsive Disorder (OCD) through the development of a bilingual smartphone application. The prevalence of OCD is ...
• Honeypots in containerised environments 

  Arora, Mehul; Chakravarty, Sambuddho (Advisor) (IIIT-Delhi, 2023-11-29)

  Containers have gained popularity for their efficiency, allowing developers to package and deploy applications seamlessly, thus replacing VMs in the modern-day deployment scenario and becoming a strong base for cloud ...
• Countercraft: counter-speech retrieval with template-based ingenuity 

  Saini, Manav; Akhtar, Md Shad (Advisor) (2023-11-29)

  To address the issue of hate speech, the study proposes a novel method to retrieve counter speeches using templates. The templates are created by analyzing instances of hate speech in the CONAN dataset, which contains ...
• Distributed stream processing at edge 

  Choudhary, Aditya; Chak, Ayush Raje; Shah, Rajiv Ratn (Advisor) (IIIT-Delhi, 2023-11-23)

  A vast amount of data is produced by billions of modern devices each year. An effective Stream Processing Engine (SPE) is needed to arrange and handle this data. Among the well-known SPEs are Apache Hadoop, Apache Spark, ...
• KG quality metrics 

  Sharma, Pranav; Mutharaju, Raghava (Advisor); Mukherjee, Manuj (Advisor) (IIIT-Delhi, 2023-11-27)

  In the burgeoning field of knowledge representation, the construction and maintenance of highquality knowledge graphs (KG’s) play a pivotal role in ensuring the accuracy and reliability of information. This research endeavors ...
• DIKE: blockchain based e-voting 

  Aggarwal, Naman; Chakravarty, Sambuddho (Advisor); Samajder, Subhabrata (Advisor); Buduru, Arun Balaji (Advisor) (IIIT-Delhi, 2023-11-23)

  DIKE: is an online voting system which uses a private blockchain to securely cast and count the votes . The system addresses the issues in existing offline voting system revealing/compromising voter anonymity, partial vote ...
• Fairness in machine learning 

  Budhija, Kuber; Shah, Rajiv Ratn (Advisor) (IIIT-Delhi, 2023-11-01)

  In a world where machine learning and AI play an increasing role in decision-making across various sectors, concerns about fairness have emerged. This report delves into the journey of understanding fairness in machine ...
• Web development on different interesting systems 

  Hanoon, Ahmed; Shah, Rajiv Ratn (Advisor) (IIIT-Delhi, 2023-11-29)

  The project is aimed at enhancing a collection of web portals within the broader framework of the Facility Hub application. Comprising of eight distinct portals, each either ready for production or in the final stages of ...
• Parameterized algorithms to find cohesive subgraphs with small diameter 

  Sakhuja, Raghav; Majumdar, Diptapriyo (Advisor) (IIIT-Delhi, 2023-11-24)

  Given an undirected graph G = (V,E), an s-club is a vertex subset S ⊆ V (G) such that G[S] has diameter at most s. Formally, an s-Club problem asks if the input graph has an s-club with at least k vertices. There have been ...
• Benchmarking ML/DL libraries 

  Tyagi, Jatin; Rastogi, Nishaant; Jain, Pratyush; Kumar, Dhruv (Advisor) (IIIT-Delhi, 2023-11-29)

  The exponential growth of machine and deep learning applications across diverse domains has led to the proliferation of machine and deep learning libraries. As these libraries offer various algorithms, tools, and ...
• AI for software development: refactoring code-bases 

  Vohra, Aryan; Jalote, Pankaj (Advisor) (IIIT-Delhi, 2023-11-29)

  Code refactoring, in which an existing module is modified for satisfying some property while maintaining the functionality, is often needed as software evolves. Since refactoring is tedious and error prone, it is sometimes ...
• Implementation and evaluation of QUIC on serverless architectures 

  Ambooken, Alvin Joseph; Maity, Mukulika (Advisor) (IIIT-Delhi, 2023-11-29)

  Serverless computing has emerged as a tranformative field in the cloud computing world. It is being increasingly adopted in the industry due to the energy and cost savings associated with it. However, communications withing ...
• Real-time covert communication 

  Kumar, Anirudh S.; Kumar, Prateek; Chakravarty, Sambuddho (Advisor) (IIIT-Delhi, 2023-11-29)

  In recent years, the censorship measures taken by various countries have introduced large-scale and sophisticated apparatuses to prevent citizens from accessing the internet freely. Numerous efforts have been made in this ...
• Text-to-talking face: emotionally rich facial animation synthesis 

  Maini, Sarthak; Shukla, Jainendra (Advisor) (IIIT-Delhi, 2023-11-29)

  Given the facial image of an individual along with audio, Talking face generation aims to synthesize portrait videos of the individual that are conditioned by the given audio. Existing methods focus on generating talking ...
• Building a risk scoring system using ML for cardiovascular risk for Indian population 

  Gupta, Akshat; Gupta, Anubha (Advisor) (IIIT-Delhi, 2023-12-03)

  Cardiovascular diseases (CVD) include a variety of conditions affecting the heart and blood vessels, often arising from complex interplay of genetic predisposition, lifestyle factors, and environmental influences. Myocardial ...
• Innovative graph based transformer model for ECG data analysis 

  Raj, Aditya; Gupta, Anubha (Advisor) (IIIT-Delhi, 2023-11-29)

  In this research, we attempt to create a state-of-the-art model for the classification of the PTBXL dataset and improve upon already established metrics. Firstly, we use the previous best model, ST-CNN-GAP-5 and introduce ...
• Unsupervised pre-trained vitals signals embeddings for fine-tuned prognostication: a multi-resolution approach 

  Sheoran, Ashwin; Patil, Vedant; Sethi, Tavpritesh (Advisor) (IIIT-Delhi, 2023-11-29)

  The project introduces an innovative method for predicting shock in ICU patients by leveraging unsupervised pre-trained embeddings from vital signs. Utilizing the extensive eICU and MIMIC datasets, the research focuses on ...
• Activation functions in neural networks 

  Narayan, Anupam; Pandey, Ashish Kumar (Advisor) (IIIT-Delhi, 2023-12-12)

  Artificial neural networks (ANNs) are pivotal in deep learning, with activation functions introducing crucial non-linearity. An ideal activation function should generalize well across datasets, expedite convergence, and ...

View more