Wael Mobeirek

Carlos Alves Pereira, Tanay Komarlu, Wael Mobeirek

The development of Natural Language Generation models has led to the creation of powerful Artificial Intelligence-assisted writing tools. These tools are capable of predicting users' needs and actively providing suggestions as they write. In this work, we conduct a comparative user-study between such tools from an information retrieval lens: pull and push. Specifically, we investigate the user demand of AI-assisted writing, the impact of the two paradigms on quality, ownership of the writing product, and efficiency and enjoyment of the writing process. We also seek to understand the impact of bias of AI-assisted writing. Our findings show that users welcome seamless assistance of AI in their writing. Furthermore, AI helped users to diversify the ideas in their writing while keeping it clear and concise more quickly. Users also enjoyed the collaboration with AI-assisted writing tools and did not feel a lack of ownership. Finally, although participants did not experience bias in our experiments, they still expressed explicit and clear concerns that should be addressed in future AI-assisted writing tools.

Wael Mobeirek, Shirley Mao

With the increasing number of patients diagnosed with Alzheimer's Disease, prognosis models have the potential to aid in early disease detection. However, current approaches raise dependability concerns as they do not account for uncertainty. In this work, we compare the performance of Monte Carlo Dropout, Variational Inference, Markov Chain Monte Carlo, and Ensemble Learning trained on 512 patients to predict 4-year cognitive score trajectories with confidence bounds. We show that MC Dropout and MCMC are able to produce well-calibrated, and accurate predictions under noisy training data.

Mohammed Alsakabi, Wael Mobeirek, John M. Dolan et al.

Existing periodic activation-based implicit neural representation (INR) networks, such as SIREN and FINER, suffer from hidden feature redundancy, where neurons within a layer capture overlapping frequency components due to the use of a fixed frequency multiplier. This redundancy limits the expressive capacity of multilayer perceptrons (MLPs). Drawing inspiration from classical signal processing methods such as the Discrete Sine Transform (DST), we propose FM-SIREN and FM-FINER, which assign Nyquist-informed, neuron-specific frequency multipliers to periodic activations. Unlike existing approaches, our design introduces frequency diversity without requiring hyperparameter tuning or additional network depth. This simple yet principled modification reduces the redundancy of features by nearly 50% and consistently improves signal reconstruction across diverse INR tasks, including fitting 1D audio, 2D image and 3D shape, and synthesis of neural radiance fields (NeRF), outperforming their baseline counterparts while maintaining efficiency.