Find final year projects, theses, dissertations, seminar papers and research outputs across participating institutions.
I would like to begin by expressing my deepest gratitude to God for providing me with the strength, clarity, and perseverance needed to complete this research. My heartfelt thanks go to …
This record links to the original Transformer paper, which introduced a sequence modelling architecture based entirely on self-attention. It is useful for repository testing because it cont…
This record links to the Faster R-CNN paper, which introduces region proposal networks for efficient object detection. It is suitable for testing robotics, intelligent systems, and engineer…
This record links to the Mask R-CNN paper, which extends object detection with instance segmentation masks. It gives the repository a realistic external PDF for image analysis, computer vis…
This record links to the word2vec paper, which presents efficient methods for learning distributed word representations. It is useful for testing older but influential NLP documents, keywor…
This record links to the XGBoost paper, which describes a scalable tree boosting system used widely in data science. It provides a strong test case for statistics metadata, predictive model…
This record links to the variational autoencoder paper, which introduces a practical approach to variational inference with neural networks. It supports realistic testing of statistics, gen…
This record links to the DeepLab semantic segmentation paper, which combines deep convolutional networks with atrous convolution and structured prediction. It is useful for testing long tec…
This record links to the DINO self-supervised vision transformer paper, which studies emergent properties in learned visual representations. It is useful for testing modern machine learning…
This record links to the EfficientNet paper, which proposes compound scaling for convolutional neural network depth, width, and resolution. It supports realistic testing of undergraduate AI…
This record links to a foundational neural machine translation paper that introduced an attention-based alignment approach. It is useful for testing humanities-adjacent computational lingui…
This record links to the sequence-to-sequence learning paper, which uses neural networks to map input sequences to output sequences. It provides a realistic external PDF for testing NLP rep…
This record links to the RAG paper, which combines neural retrieval with sequence generation for knowledge-intensive NLP tasks. It provides a strong external PDF test case for repository se…
This record links to the Vision Transformer paper, which adapts transformer architectures to image classification through patch-based image representation. It is useful for validating compu…
This record links to the LoRA paper, which introduces low-rank adaptation for efficient fine-tuning of large language models. It is useful for testing AI thesis metadata, modern NLP keyword…
This record links to the chain-of-thought prompting paper, which studies how intermediate reasoning steps improve large language model performance. It is useful for testing education techno…
This record links to the denoising diffusion probabilistic models paper, which describes a generative modelling framework based on iterative noise reversal. It supports realistic testing fo…
This record links to the latent diffusion models paper, which combines compression and diffusion modelling for efficient high-resolution image synthesis. It is suitable for validating exter…
This record links to the U-Net paper, which proposes an encoder-decoder convolutional network for biomedical image segmentation. It provides a realistic health technology document for repos…
This record links to the YOLO object detection paper, which frames detection as a single regression problem over bounding boxes and class probabilities. It is useful for testing engineering…
This record links to the original GAN paper, which introduced adversarial training between a generator and a discriminator. The document is useful for validating machine learning topics, ex…
This record links to the Adam optimization paper, which presents an adaptive learning-rate method widely used in deep learning. It is a compact but realistic technical PDF for testing keywo…
This record links to the dropout paper, which explains how randomly omitting feature detectors during training can reduce overfitting. It is suitable for testing undergraduate AI project me…
This record links to the BERT paper, which describes bidirectional transformer pre-training for language understanding tasks. It gives the platform a realistic NLP document for search, inde…
This record links to the GPT-3 paper, which evaluates large autoregressive language models under few-shot, one-shot, and zero-shot settings. It is useful for stress-testing long author meta…
