Search Results for author: Muhammad Rafi

Found 6 papers, 2 papers with code

Attention Transformer Model for Translation of Similar Languages

1 code implementation WMT (EMNLP) 2020 Farhan Dhanani, Muhammad Rafi

With the introduction of Recurrent Attention, it allows the decoder to focus effectively on order of the source sequence at different decoding steps.

Machine Translation Translation

Accuracy and Fidelity Comparison of Luna and DALL-E 2 Diffusion-Based Image Generation Systems

no code implementations5 Jan 2023 Michael Cahyadi, Muhammad Rafi, William Shan, Jurike Moniaga, Henry Lucky

We qualitatively examine the accuracy and fidelity between two diffusion-based image generation systems, namely DALL-E 2 and Luna, which have massive differences in training datasets, algorithmic approaches, prompt resolvement, and output upscaling.

Image Generation

Artificial Interrogation for Attributing Language Models

1 code implementation20 Nov 2022 Farhan Dhanani, Muhammad Rafi

And then perform one-to-many pairing between them based on similarities in their generated responses, where more than one fine-tuned model can pair with a base model but not vice-versa.

Machine Translation Multi Class Text Classification +3

Guiding Attention using Partial-Order Relationships for Image Captioning

no code implementations15 Apr 2022 Murad Popattia, Muhammad Rafi, Rizwan Qureshi, Shah Nawaz

A pairwise ranking objective is used for training this embedding space which allows similar images, topics and captions in the shared semantic space to maintain a partial order in the visual-semantic hierarchy and hence, helps the model to produce more visually accurate captions.

Caption Generation Image Captioning

An Intelligent and Time-Efficient DDoS Identification Framework for Real-Time Enterprise Networks SAD-F: Spark Based Anomaly Detection Framework

no code implementations21 Jan 2020 Awais Ahmed, Sufian Hameed, Muhammad Rafi, Qublai Khan Ali Mirza

Further, we study and compare the performance factor of our proposed framework on three different testbeds including normal commodity hardware, low-end system, and high-end system.

Anomaly Detection feature selection

Cannot find the paper you are looking for? You can Submit a new open access paper.