29 citations · 56 across the 16 of their papers we have counts for
3 papers · 1 filter
Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula
Sam Blouir, Jimmy T. H. Smith, Antonios Anastasopoulos +1
Efficient state space models (SSMs), such as linear recurrent neural networks and linear attention variants, offer computational advantages over Transformers but struggle with task…
Accounting for Work Zone Disruptions in Traffic Flow Forecasting
Yuanjie Lu, Amarda Shehu, David Lattanzi
Traffic speed forecasting is an important task in intelligent transportation system management. The objective of much of the current computational research is to minimize the diffe…
Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms
Toki Tahmid Inan, Mingrui Liu, Amarda Shehu
Despite an extensive body of literature on deep learning optimization, our current understanding of what makes an optimization algorithm effective is fragmented. In particular, we…