Year-2024

 

Recent Submissions

  • Optimising serialisation for cloud applications 
    Nayak, Siddharth; Shah, Rinku (Advisor) (IIIT-Delhi, 2024-05-21)
    Serialisation latency is a significant concern in modern cloud applications that leverage the microservice paradigm. A cloud service request typically traverses a sequence of microservices across nodes, increasing latency ...
  • Programmable proxy for microservice communication in multi-cloud environments 
    Pathak, Shambhavi; Shah, Rinku (Advisor) (IIIT-Delhi, 2024-05-21)
    As enterprises migrate from single-cloud to multi-cloud architecture, they encounter challenges due to geographical dispersion, varying WAN characteristics, and diverse cloud policies. These challenges demand a re-evaluation ...
  • Incongruence identification in eyewitness narratives 
    Nair, Akshara; Akhtar, Md. Shad (Advisor) (IIIT-Delhi, 2024-07)
    Eyewitness accounts are crucial to legal and investigative proceedings, serving as foundational sources for reconstructing events. Agencies typically collect multiple statements to achieve a thorough understanding of the ...
  • Federated learning with distribution models 
    Reddy, Gunjapalli Sravani; Chatterjee, Bapi (Advisor) (IIIT-Delhi, 2024-06-14)
    This thesis investigates the integration of Mixture Density Networks (MDNs) within Federated Learning (FL) frameworks to tackle challenges in data privacy, security, and model robustness, focusing on Automatic Speech ...
  • A digital honor code : detecting academic dishonesty with keystroke dynamics 
    Kundu, Debnath; Shah, Rajiv Ratn (Advisor); Kumar, Rajesh (Advisor) (IIIT-Delhi, 2024-05-20)
    As educational assessments migrate to digital platforms, ensuring academic integrity becomes crucial. Traditional plagiarism detection systems struggle to catch instances of intelligent cheating, especially when students ...
  • Participation strategies in federated learning with heterogeneous client communications 
    Agrawal, Shubham; Chatterjee, Bapi (Advisor) (IIIT-Delhi, 2024-06-01)
    In cross-device federated learning (FL) [1], a machine learning model is developed by leveraging communication between a central server and numerous edge device clients. In practical scenarios, the ability of these edge ...
  • Quaternion-enhanced neural networks : a new paradigm for audio processing efficiency 
    Chaudhary, Aryan; Abrol, Vinayak (Advisor) (IIIT-Delhi, 2024-05-01)
    This thesis explores the integration of quaternion algebra into neural network architectures to enhance their efficiency for diverse audio processing tasks. Quaternion-based transformations are employed to achieve structural ...
  • Taxonomy completion via sector hierarchy 
    Talukdar, Indraayudh; Akhtar, Md Shad (Advisor) (IIIT-Delhi, 2024-07-01)
    Taxonomy is a hierarchical structure that deals with knowledge. It can be perceivedas Knowledge graph with all the relations being only ’is-a’. Automatic creation of taxonomies can be achieved by creation scratch, by ...
  • Exploration of continual learning paradigm for large-scale speaker verification systems 
    Verma, Akash; Abrol, Vinayak (Advisor) (IIIT-Delhi, 2024-05-21)
    Speaker verification (SV) focuses on confirming or denying the claimed identity of a speaker. It is a one-to-one comparison between the test utterance and the claimant’s stored reference voice sample. This process is ...
  • Indian legal case judgment document mining : semantic segmentation and information extraction 
    Das, Antara; Goyal, Vikram (Advisor) (IIIT-Delhi, 2024-05-01)
    Developing NLP-based techniques to automate tasks in the Indian legal domain is highly demanding due to the enormously increasing volume of legal text documents, intricate legal terminologies, and the need for efficient ...
  • Patterns and problems : analyzing document layouts and improving mathematical reasoning of llms 
    Gupta, Mohit; Shah, Rajiv Ratn (Advisor) (IIIT-Delhi, 2024-05-08)
    Documents play a pivotal role in conveying information, serving as integral carriers of knowledge across various domains. Their importance lies in their ability to encapsulate ideas, facts, and insights, thereby facilitating ...
  • Federated distribution learning 
    Bansal, Mehak; Chatterjee, Bapi (Advisor) (IIIT-Delhi, 2024-01-19)
    Distribution Learning is a form of machine learning which involves the distribution of data across in a network having multiple devices. Each node is trained independently, and then combined the results to generate a model ...
  • VT-Nood : vision transformer based near ood detection in fine-grained datasets 
    Dey, Kaushik; Prasad, Ranjitha (Advisor) (IIIT-Delhi, 2024-08-01)
    Machine Learning models output high confidence scores when provided with input samples that belong to the input data distribution, referred to as in-distribution (ID)samples. However, when presented with an Out of Distribution ...