4 papers
SurF: A Generative Model for Multivariate Irregular Time Series Forecasting
Mohammad R. Rezaei, Tejas Balaji, Rahul G. Krishnan
Irregularly sampled multivariate event streams remain a difficult modality for generative modeling: tokenization-based approaches break down when inter-event intervals vary by orde…
Flows and Diffusions on the Neural Manifold
Daniel Saragih, Deyu Cao, Tejas Balaji
Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling. In this work, we ex…
Flow to Learn: Flow Matching on Neural Network Parameters
Daniel Saragih, Deyu Cao, Tejas Balaji +1
Foundational language models show a remarkable ability to learn new concepts during inference via context data. However, similar work for images lag behind. To address this challen…
An Empirical Study of Aegis
Daniel Saragih, Paridhi Goel, Tejas Balaji +1
Bit flipping attacks are one class of attacks on neural networks with numerous defense mechanisms invented to mitigate its potency. Due to the importance of ensuring the robustness…