http://repository.iiitd.edu.in/xmlui/handle/123456789/45 2026-05-05T12:39:49Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1963 Knowledge graph distillation Narotam, N; Kaif, Mohammad; Akhter, Md. Shad (Advisor); Mutharaju, Raghava (Advisor) 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 formulate what works. We develop a test hypothesis and plan to evaluate our proposed solutions. We try to investigate various tasks across domains to test our solution and its generalizability Keywords: Knowledge 2024-11-27T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1962 Applications of NLP in recipe texts Neelu; Vaikundam, Gurupriya; Upadhyay, Rituj; Bagler, Ganesh (Advisor) This study addresses the challenge of large-scale, multi-label recipe classification us- ing a real-world dataset of over 600,000 recipes collected from heterogeneous sources. The raw data exhibited significant noise, duplication, and label imbalance, motivating a comprehensive, multi-stage cleaning and preprocessing framework. Key steps included in- gredient normalization, instructions standardization, multi-label parsing, deduplication, and semantic category mapping into hierarchical supercategories. For modeling, we im- plemented a modular pipeline combining TF-IDF feature extraction, classical classifiers, XGBoost, and fine-tuned BERT models to capture both statistical and contextual signals. By adopting a per-supercategory strategy, we minimized cross-domain interference and achieved strong performance, with the fine-tuned BERT classifier attaining a weighted F1-score of 0.7996 and high accuracy on dominant labels. This work demonstrates how rigorous data preparation and modular modeling can enable fine-grained, interpretable recipe classification at scale, providing a robust foundation for downstream culinary ap- plications such as personalized meal planning and intelligent search. 2025-07-27T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1961 Consistent vision: exploring multi-domain applications of consistency models Bhagat, Amil; Jain, Milind; Subramanyam, A V (Advisor) 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. By utilizing paired data for training, the model learns a robust mapping that preserves essential features across modalities. The ultimate goal is to build a model capable of generating accurate outputs in the target domain (e.g., infrared) from inputs in the source domain (e.g., visible), enabling practical applications in domains like imaging, vision enhancement, and modality transformation while showcasing the potential of consistency models for cross-domain learning tasks. 2024-05-01T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/1960 Non - rigid motion transfer between non - isometric 3D bodies Pandey, Daksh; Sharma, Ojaswa (Advisor) 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 often encountered in real-world scenarios. The project outlines a pipeline involving shape matching and motion transfer. The literature review reveals key ad- vancements and gaps in the field, while the proposed framework aims to contribute new method- ologies for handling complex transformations. The project is partially implemented, with shape matching algorithms defined, while the motion transfer pipeline is under development. 2024-11-27T00:00:00Z