Scientific Computing

Rahman's 1964 Liquid Argon Simulation Replication

Complete replication of Aneesur Rahman's foundational 1964 molecular dynamics simulation using modern LAMMPS and Python, …...

Scientific Computing

Replicating Rahman's 1964 Liquid Argon Simulation

Recreating the foundational 1964 molecular dynamics simulation with modern Python and LAMMPS, testing whether Rahman's …...

Time Series Forecasting

Deconstructing Neural Networks for Time Series Forecasting

Ablation study examining key architectural components of neural networks for spatiotemporal forecasting, finding that …...

Computational Chemistry

Can You Hear the Shape of a Molecule? (Part Three)

Supervised learning analysis reveals surprising patterns in eigenvalue space that clustering missed, testing k-NN and …

Computational Chemistry

Can You Hear the Shape of a Molecule? (Part Two)

Rigorous clustering analysis reveals why Coulomb matrix eigenvalues struggle with larger alkanes, using Dunn Index and …

Natural Language Processing

Sarcasm Detection with Transformers: A Cautionary Tale

Learn how dataset bias can lead to misleading results in NLP: a sarcasm detection model that actually learned to …

Natural Language Processing

Analytical Model of Word2Vec and GloVe Statistics

Presents an analytical model of statistics learned by Word2Vec and GloVe. This work derives the first known analytical …...

AI Safety

GPT-2 Susceptibility to Universal Adversarial Triggers

An investigation into whether universal adversarial triggers can control not just the topic but also the stance of …...

Natural Language Processing

QuAC: Question Answering in Context Dataset

An analysis of QuAC's approach to conversational question answering through student-teacher interactions, featuring …