http://repository.iiitd.edu.in/xmlui/handle/123456789/1722 Year-2024 Sat, 29 Aug 2026 17:41:09 GMT 2026-08-29T17:41:09Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2028 Title: Automatic partitioning of parallel programs on heterogeneous multicore processors Authors: Kansal, Rohak; Gupta, Samridh; Kumar, Vivek (Advisor) Abstract: With the advent of hybrid CPUs integrated with GPUs, achieving peak performance and energy efficiency necessitates the effective utilization of all available resources. This project explores workload partitioning strategies for heterogeneous multicore processors, leveraging tools like Intel PCM for CPU analysis and OpenCL for GPU-based computations. A key focus was on implementing custom convolution functions and analyzing metrics such as frequency scaling and power consumption. Significant challenges were encountered, including device compatibility issues and optimization of custom functions. Results indicate that OpenCL enables successful GPU and CPU operations, but limitations with simultaneous device detection and slower custom implementations compared to PyTorch underline the need for further refinement. Future directions include addressing these challenges, optimizing workload distribution, and expanding scalability to larger datasets. Wed, 27 Nov 2024 00:00:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/2028 2024-11-27T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2027 Title: Federated learning for radio environment mapping Authors: Kumar, Lakshay; Sarkar, Shamik (Advisor) Abstract: My work extends previous work on proactive spatial prediction of radio environments for spectrum sharing by integrating it into a distributed Federated Learning (FL) framework. In this enhanced version of the Federated ProSpire system, clients locally train their models and communicate after several rounds of local training. This decentralized approach allows for the secure and efficient sharing of learned models without requiring centralized data collection. We investigate the impact of hyperparameters such as local epochs, communication rounds, and data augmentation on model performance. Additionally, we explore the effects of data distribution under both IID (Independent and Identi cally Distributed) and non-IID conditions, with the latter simulating location-based variations and RSS strength differences across clients. Experiments show that the Federated ProSpire system maintains comparable accuracy in signal strength prediction, with a mean absolute error of around 5 dB, while enhancing scalability, privacy, and robustness against interference under some conditions. These findings demonstrate the suitability of our framework for emerging spectrum-sharing paradigms in next-generation wireless networks, offering a flexible and scalable solution for collaborative, privacy preserving radio environment prediction. Thu, 28 Nov 2024 00:00:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/2027 2024-11-28T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2026 Title: Novel recipe generation using LLMs Authors: Mehta, Saurabh; Gupta, Aditya; Bagler, Ganesh (Advisor) Abstract: Generating novel recipes within specific cuisine constraints is a challenging task that combines creativity with cultural authenticity. This study explores the capabilities of fine-tuned large lan guage models (LLMs), including GPT-2, Llama-3.1-8b, and Mistral-7B-Instruct-v0.3, to generate innovative recipes while adhering to predefined culinary styles. By leveraging the contextual and generative strengths of these models, we aim to create recipes that balance novelty with adherence to the cuisine’s defining characteristics. To evaluate the quality of the generated recipes, we employ intrinsic metrics such as BLEU, ME TEOR, BERTScore, and Perplexity. These metrics provide a multifaceted assessment of linguistic diversity, semantic alignment, and fluency. The results reveal how effectively each model captures the essence of the target cuisine while introducing creative variations. Our findings highlight the trade-offs between generating novel content and preserving authentic culinary traits, offering valuable insights into the potential of LLMs for constrained creative tasks. This research demonstrates the applicability of AI-driven approaches to culinary innovation and provides a foundation for future exploration in cuisine-constrained text generation. Sat, 30 Nov 2024 00:00:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/2026 2024-11-30T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2025 Title: navX : online guidance platform Authors: Singh, Niharika; Singh, Rajbir (Advisor) Abstract: This project presents navX, a comprehensive career guidance platform in the form of a website, designed to address the gaps in current systems by providing personalized and accessible career advice to students and parents, particularly those in underserved regions. Through extensive research, we identified key challenges faced by students, including limited awareness of career options, a lack of mentorship, and financial constraints. Based on these findings, we conceptual ized navX, a platform that combines a Q&A forum, personalized mentorship, structured career courses, and financial guidance. The competitor analysis revealed that most existing platforms focus on college students, and navX distinguishes itself by targeting students in Class 9-12 and offering holistic support. The first prototype was developed using Figma, and the product is currently being built using React.js, Next.js, Chakra UI for the front-end, and Firebase for the back-end. navX aims to bridge the gap between traditional career paths and emerging fields, providing students with the tools they need to make informed decisions about their futures. Wed, 27 Nov 2024 00:00:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/2025 2024-11-27T00:00:00Z