• Automatic partitioning of parallel programs on heterogeneous multicore processors 

  Kansal, Rohak; Gupta, Samridh; Kumar, Vivek (Advisor) (IIIT-Delhi, 2024-11-27)

  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 ...
• Federated learning for radio environment mapping 

  Kumar, Lakshay; Sarkar, Shamik (Advisor) (IIIT-Delhi, 2024-11-28)

  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 ...
• Novel recipe generation using LLMs 

  Mehta, Saurabh; Gupta, Aditya; Bagler, Ganesh (Advisor) (IIIT-Delhi, 2024-11-30)

  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), ...
• navX : online guidance platform 

  Singh, Niharika; Singh, Rajbir (Advisor) (IIIT-Delhi, 2024-11-27)

  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, ...
• Visual ocean wave analytics 

  Garg, Navyam; Sharma, Tizil; Anand, Saket (Advisor) (IIIT-Delhi, 2024-12-12)

  Accurate prediction and tracking of ocean wave dynamics especially near the beach side are important for enhancing the safety and experience of surfers. This study presents a deep learning based approach that uses computer ...
• Chatbot for recipe videos 

  Raman, Param Kumar; Kumar, Rahul; Raj, Ankit; Adarsh (IIIT-Delhi, 2024-11-27)

  This report explores advancements and methodologies in the development and fine-tuning of large language models (LLMs) and their integration into knowledge-intensive tasks. It em phasizes the role of retrieval-augmented ...
• Dynamic target tracking for quadrotors using liquid neural networks 

  Singal, Akanksha; Roy, Sayan Basu (Advisor) (IIIT-Delhi, 2024-12-02)

  Image Based Visual Servoing (IBVS) and autonomous navigation in robots often rely on phys ical markers for fast detection and estimation of pose and orientation. However, in real-world scenarios, the use of fiducial markers ...
• Leveraging langchain and generative AI for PDF information retrieval 

  Himani; Singh, Pushpendra (Advisor) (IIIT-Delhi, 2024-11-25)

  One of the biggest challenges when it comes to retrieving information from diversified and complex datasets, such as PDFs, is their unstructured nature and the possibility of re ceiving irrelevant or incorrect responses. ...
• Alteration in spin transport of a modified magnetic tunnel junction due to resonant tunneling 

  Abhisri, Arya; Ghosh, Ram Krishna (Advisor) (IIIT-Delhi, 2024-04-29)

  This study explores potential improvement in the efficiency of traditional Magnetic Tunnel Junctions (MTJ) through utilisation of an altered double MTJ with a non-magnetic metalllic spacer (tungsten) for resonant tunneling. ...
• SLIM-SENSE: a resource efficient WiFi sensing framework towards integrated sensing and communication 

  Walecha, Aryan; Maity, Mukulika (Advisor); Bhattacharya, Arani (Advisor); Singh, Vijay Kumar (Advisor) (IIIT-Delhi, 2024-11-27)

  WiFi signals have become pivotal in sensing applications by leveraging Channel State Informa tion (CSI). WiImg, a novel system, utilizes Generative Adversarial Networks (GAN) for image inpainting to perform WiFi sensing ...
• Deception analysis: controlled dialogue summarization 

  Arora, Arjit Singh; Akhtar, Md. Shad (Advisor) (IIIT-Delhi, 2024-11-27)

  In the field of deception analysis, controlled dialogue summarization plays a critical role in dis tilling key information from witness testimonies. This project aims to develop a summarization framework for interrogations ...
• Product launch at CiPD 

  Garg, Dhruv; Garg, Archit; Gupta, Raj; Grover, Anuj (Advisor) (IIIT-Delhi, 2024-11-26)

  In an era where personal safety remains a paramount concern, especially among vulnerable groups such as women, children, and the elderly, innovative solutions are essential to address the escalating risks of stalking, ...
• Code generation and repo understanding using LLMs, knowledge graphs and search-based algorithms 

  Gupta, Akshit; Shah, Rajiv Ratn (Advisor); Anand, Avinash (Advisor) (IIIT-Delhi, 2024-11-27)

  The increasing complexity of codebases demands advanced methods for automated code gener ation and repository understanding. This project explores the synergistic application of large language models (LLMs), knowledge ...
• Comparing large language models with small language models for healthcare applications 

  Tiwari, Abhijay; Kumar, Vibhor (Advisor) (IIIT-Delhi, 2024-12-01)

  Large Language Models (LLMs) have revolutionized natural language processing applications, but their computational and memory demands often overshadow their utility in resource-constrained scenarios, particularly in ...
• AMR sense 

  Tiju, Noel Abraham; Sethi, Tavpritesh (Advisor) (IIIT-Delhi, 2024-12-12)

  Antimicrobial resistance (AMR) is one of the most significant global health threats of the 21st century, driven by the overuse and misuse of antibiotics and the lack of effective surveillance systems. This study leverages ...
• Semi-synthetic scene transition generation for a video 

  Das, Abhirup; Gupta, Anubha (Advisor) (IIIT-Delhi, 2024-12-06)

  Scene transitions are integral to video editing, enabling seamless storytelling by connecting dis tinct video segments into a cohesive visual narrative. Despite advancements in video editing tools, automated generation of ...
• Exploring usage of covert channel in android malware bot communication 

  Chugh, Manan; Aggarwal, Manan; Chakravarty, Sambuddho (Advisor) (IIIT-Delhi, 2024-11-27)

  The rapid adoption of Android devices has been paralleled by a significant rise in Android malware, leveraging sophisticated techniques to evade detection and execute malicious activi ties. This research investigates the ...
• Multi-dataset emotion representation learning 

  Girdhar, Samridh; Singh, Pushpendra (Advisor) (IIIT-Delhi, 2024-11-29)

  This study aims to understand the feasibility of a stress detection model through a smartwatch using the physiological data collected for lab and real-life settings. Wearable devices such as smartwatches have the potential ...
• Data center network technologies for AI/ML workloads 

  Singh, Ramanjeet; Shah, Rinku (Advisor) (IIIT-Delhi, 2024-12-01)

  Distributed machine learning (ML) workloads, particularly the training of deep neural networks (DNNs) and large language models (LLMs), rely heavily on efficient network communication to achieve scalability. However, network ...
• AI/ML in healthcare: leveraging embeddings for patient diagnosis and treatment optimization 

  Malhotra, Chehak; Gopal, Mehak; Sethi, Tavpritesh (Advisor) (IIIT-Delhi, 2024-01)

  This study encapsulates our progress in the integration of advanced AI models within healthcare contexts. Utilizing state-of-the-art models for new tasks, we explore their efficacy in tasks like cancer classification and ...

View more