• Knowledge graph distillation 

  Narotam, N; Kaif, Mohammad; Akhter, Md. Shad (Advisor); Mutharaju, Raghava (Advisor) (IIIT-Delhi, 2024-11-27)

  We combine domain-specific knowledge graphs with general knowledge graphs to enrich a language model. The objective of this semester was to implement baselines, test var- ious previous literature surveyed, and try to ...
• Consistent vision: exploring multi-domain applications of consistency models 

  Bhagat, Amil; Jain, Milind; Subramanyam, A V (Advisor) (IIIT-Delhi, 2024-05)

  This project focuses on leveraging consistency models for downstream tasks involving the trans- lation and mapping between different modalities, such as converting visible images to their corresponding infrared representations. ...
• Non - rigid motion transfer between non - isometric 3D bodies 

  Pandey, Daksh; Sharma, Ojaswa (Advisor) (IIIT-Delhi, 2024-11-27)

  This paper explores the problem of motion transfer between 3D non-isometric shapes. The re- search addresses the challenge of transferring motion between shapes that do not share identical geometric properties, which is ...
• Ontology reasoning in EL++ 

  Chawla, Jessica Kaur; Mutharaju, Raghava (Advisor) (IIIT-Delhi, 2024-11-27)

  The project builds upon existing research that has investigated the reasoning capabilities of PLMs, primarily using RDFS rules. I aim to extend this work by incorporating the more expressive EL++ formalism, which potentially ...
• QUIC TCP benchmarking 

  Kumar, Ankit; Goel, Vinayak; Maity, Mukulika (Advisor) (IIIT-Delhi, 2024-12-04)

  QUIC is google’s latest protocol built on the application layer over the UDP transport, and is utilised by major services provided by google all over the world. This has led to comparisons between QUIC and TCP, the protocol ...
• Supporting the development of idea inspire for novel idea generation at the conceptual stage of designing 

  Sharma, Aman; Keshwani, Sonal (Advisor) (IIIT-Delhi, 2024-11-27)

  At the heart of product design lies the spark of creativity, where new ideas are born. Enter ”Idea Inspire,” a game-changing tool designed to help designers unleash their creativity. By tapping into both natural and ...
• Active learning for object detection 

  Goel, Atharv; Anand, Saket (Advisor) (IIIT-Delhi, 2024-12-11)

  Object detection is a fundamental task in computer vision, involving the localization and classi- fication of objects within images or video frames. However, training these models requires large amounts of labeled data, ...
• Optimizing local art sales in urban market~bamboo: artisan ecohaven furniture 

  Razafimiadana, Jacqueline Precilia; Chauhan, Aashish; Mukherjee, Payel C. (Advisor); Saronwala, Anupam (Advisor) (IIIT-Delhi, 2024-11-27)

  This “Artisan EcoHaven Furniture” seeks to fill this gap by developing strategies for enhancing the sale of local art in urban settings through the use of bamboo. It is locally available and culturally appropriate material. ...
• Platform to enable ESDM workflow management 

  Vatsayan, Hitesh; Kurda, Shivam; Grover, Anuj (Advisor) (IIIT-Delhi, 2024-11-25)

  This project introduces a platform to streamline workflow management in the Electronics System Design and Manufacturing (ESDM) sector. This is a B2B platform which connects Businesses in the ESDM sector with the most ...
• Mitigating gender bias in speech-to-speech translation 

  Aggarwal, Aditya; Gupta, Anubha (Advisor) (IIIT-Delhi, 2024-12-13)

  Despite advances in Machine Translation (MT), translating gender-marked languages remains chal- lenging. The challenge is further compounded by existing models that attempt to handle both co-reference resolution and ...
• Android malware detection 

  Gupta, Mayank; Somani, Krishna; Chakravarty, Sambuddho (Advisor) (IIIT-Delhi, 2024-05-10)

  As the usage of Android mobile devices has increased rapidly, so has the occurrence of Android malware. To mitigate the risk posed by Android malware, it is important to develop effective de- tection techniques. In this ...
• Edubot chatbot 

  Moitra, Arjun; Hooda, Vijay; Shankhwar, Kalpana (Advisor) (IIIT-Delhi, 2024-11-27)

  This B.Tech project addresses the challenges of traditional education systems, focusing on scalability, personalized learning, and administrative efficiency. Recognizing the limitations of conventional schooling in meeting ...
• Large language models for program verification 

  Bharti, Varun; Jalote, Pankaj (Advisor); Kumar, Dhruv (Advisor); Akhtar, Md. Shad (Advisor) (IIIT-Delhi, 2024-11-27)

  Program verification is a crucial process in software engineering, ensuring that programs func- tion correctly according to their specifications. Traditional methods of program verification, such as model checking and ...
• Food label 

  Chauhan, Aviral; Bagler, Ganesh (Advisor) (IIIT-Delhi, 2024-11-27)

  The project aims to create an innovative food product search and prediction system that enables users to explore a comprehensive database of 900,000 food items. Each product is enriched with metadata, including its name, ...
• Question answering for policy documents 

  Bohra, Ankur; Singh, Himanshu; Akhtar, Md Shad (Advisor) (IIIT-Delhi, 2024-11-28)

  Privacy policies are legally enforceable documents notifying consumers of how a company intends to interact with the consumer’s data, but modern policy documents prove to be too long and complex for the average user to ...
• Advertisement generator startup 

  Garg, Nitesh; Grover, Anuj (Advisor) (IIIT-Delhi, 2024-11-27)

  This report outlines the development of a startup aimed at addressing advertising challenges faced by small-to-medium scale enterprises (SMEs) through innovative, AI-driven solutions. Initially focused on enabling users ...
• K-12 teacher training through LLMs 

  Jain, Samyak; Pal, Shubham; Kumar, Dhruv (Advisor) (IIIT-Delhi, 2024-11-27)

  In the modern educational landscape, technological tools play a crucial role in improving learning experiences, addressing individual needs, and facilitating effective teaching practices. The problem at hand revolves around ...
• Autoencoders and kalman filters for generative AI 

  Singh, Ankit Kumar; Choudhary, Aayush; Kumar, Saurabh; Kumar, Vibhor (Advisor) (IIIT-Delhi, 2024-11-27)

  With the growing complexity of models like ChatGPT, LLaMA, and other Generative AI mod- els, which demand significant computational resources, applying them in resource-constrained environments becomes a major challenge. ...
• TTS in codemix domain 

  Bharti, Rahul; Akhtar, Md Shad (Advisor) (IIIT-Delhi, 2024-11-27)

  We aim to develop a Text-to-Speech (TTS) system for code-mixed corpora, addressing the unique challenges posed by multilingual and mixed-language text. To establish a robust foundation, we first reviewed TTS literature ...
• Comparative assessment of bias in human cognition and large language models 

  Gupta, Arnav; Garg, Parth; Yadav, Shagun; Jalote, Pankaj (Advisor); Kumar, Manohar (Advisor) (IIIT-Delhi, 2024-12-12)

  Abstract This study compares the biases in human cognition and those exhibited by large language mod- els (LLMs) compared using the same assessment instrument. The research evaluates biases across eight key parameters—gender, ...

View more