Sharma, Mohit; Shah, Rajiv Ratn (Advisor); Deshpande, Amit (Advisor)(IIIT-Delhi, 2026-08)
In the context of classification, the Bayes optimal classifier represents the best possible classification rule with respect to the 0-1 loss, for a given data distribution. In the setting of binary classification, it can ...
The various video applications running over wireless networks face a common set of challenges, such as inconsistent bandwidth, high network variability, and sudden latency spikes. Considering such constraints, this thesis ...
This thesis presents a unified framework for analysing the “expressivity” of Deep Neural Networks by combining factor analysis with topological data analysis (TDA). The central idea is to study the learning in Neural ...
Today, global Internet traffic is dominated by video streaming, prompting service providers to adopt emerging technologies that enhance users’ Quality of Experience (QoE) while sustaining operational efficiency. In this ...
While progress in graph representation learning has often been model-centric: focusing on the design of more powerful architectures, this thesis presents a data-centric lens: a framework viewing the graph not as a static ...
Machine learning and deep learning algorithms have demonstrated exceptional performance across various computer vision tasks, including face detection, attribute prediction, object detection, image segmentation, and ...
The rapid emergence of large-scale Pre-Trained Models (PTMs) trained on massive and diverse corpora has fundamentally reshaped the landscape of numerous AI domains, in- cluding natural language processing, computer vision ...
As artificial intelligence-enabled wearable devices become increasingly integrated into everyday life, they offer new opportunities to continuously monitor physiological signals and support emotional well-being outside ...
Alias analysis is a technique to determine whether a pair of pointers points to overlapping memory locations. Alias information (especially non-overlapping of pointers) is critical for enabling key transformations such as ...
Sharma, V. Divya; Gupta, Anubha (Advisor)(IIIT-Delhi, 2026-04)
High-quality synthetic speech has transformative potential for accessibility, education, entertainment, and personalized human–computer interaction. However, it also poses serious risks: synthetic voices can be exploited ...
Mental health issues are now the leading global cause of disability, with conditions such as anxiety and depression escalating, particularly following the COVID-19 pandemic. However, traditional mental health support methods ...
We address the development of explainable Question Answering (QA) systems for Indic languages, focusing on the unique challenges posed by resource scarcity and the complexities of multilingual processing. The research ...
The United Nations Sustainable Development Goal 3.7 promotes universal access to sexual and reproductive healthcare services, including family planning, information, and education. India has a dedicated National Programme ...
Ansari, Bushra; Biswas, Sanat (Advisor)(IIIT-Delhi, 2025-08-27)
The developments in Global Navigation Satellite Systems (GNSS) and Regional Navigation Satellite Systems(RNSS) have given rise to various application areas beyond the conventional Positioning, Navigation and Timing (PNT) ...
Despite our best efforts, tackling hate speech remains an elusive issue for researchers and practitioners alike. What can be considered hateful is subject to context, time, geography, and culture. This poses a challenge ...
Large Language Models (LLMs) have transformative capabilities but limited application in specialized educational and research contexts requiring multimodal reasoning, context-aware processing, and domain-specific understanding. ...
Communication, as a system of messages, symbols, and cultural exchanges, is ubiquitous across all species. Scholars have argued that communication represents one of the most transformative evolutionary transitions in life’s ...
The spread of misinformation on social media platforms endangers public discourse and societal trust. Addressing this issue requires robust mechanisms for identifying and verifying the accuracy of information circulated ...
The global recognition around the transformative potential of Information and Communication Technologies (ICTs) highlights their crucial role in shaping and enriching critical aspects of human development. Along-side this ...