It is a collection of Master's Dissertations submitted in fulfillment of the courses awarded by the Indian Statistical Institute in the subject areas of Statistics, Mathematics, Computer Science, Quantitative Economics, Cryptography, Library & Information Science, Statistical Quality Control and Operations Research.
Theses/Dissertations from 2026
Learning in Infants using Intrinsically Motivated Goal Conditioned Reinforcement Learning, T I Darsan
Bias Before Generation: Attention-based Preemptive Fairness Signals in Large Language Models, Aniket Das
Learning to See Lesions, Not Skin Tone: Counterfactual Multimodal Learning for Fair, Trustworthy, and Text-Free Dermatology AI, Shivam Jangid
Design and Evaluation of a Code-Switching-Aware Multilingual Conversational AI System using Advanced RAG Architectures, Ashutosh Juvale
Multi-Frequency Associative Memory for Continual Graph Learning through Nested Optimization, Shuvam Kundu
Extending UniBreak: Semantic Retrieval and Harmful-Intent Direction Suppression for Token-Level LLM Jailbreaking, Sanket Saha
A Study of Prompt Tuning on Small Language Models(SLMs): A Controlled Benchmark and a Lightweight Instance-Aware Method, Narkadamilli Sahith
Reproducing and Analyzing the “Lost in the Middle” and “The Power of Noise” Phenomenon in Retrieval-Augmented Generation, Kousik Samanta
American Sign Language Recognition and Analysis Using Deep Learning, Saurabh Kumar Soni
Theses/Dissertations from 2025
Degraded Document Binarisation, Miriyala Ajith
A Study on Planar 2-Center Problem, Shince K. Baby
Multi-party Key Establishment for Resource-Constrained Devices, Supriyo Banerjee
Secure Query on Encrypted Data by Using Fully Homomorphic Encryption, Mrinmoy Bera
Efficient SIMD based Implementation of Xoodyak, Soham Biswas
Efficient Blending of Large Language Models, Sandeep Chatterjee
Reducing Attention Complexity in Graph Transformers through Subgraph Partitioning, Ranjan Kumar Choubey
Glacial Lakes Segmentation Using Multispectral Remote Sensing Data and Deep Learning Models, Debankan Das
From Vigilance to Veracity: Hallucination Detection, Mitigation, and Safety Enhancement in Large Language Models, Sharanya Dasgupta
Ideal Query Expansion using Reinforcement Learning, Madhuchchhanda Das
Security Analysis of Encrypted Mempool, Prabal Das
Modeling and Verification of Sigma Delta Neural Networks, Sirshendu Das
Understanding Humorous Contradictions in Comics: A Multi-Agent Debate Approach, Suparna Das
Enhancing Expressive Power Of Graph Neural Networks Using Geometric Transformations, Suranjan Dey
Low Entropy Side-Channel Secure Hardware Implementations, Jhelum Dhar
Explaining Query Expansion Algorithms, Aditya Dutta