Follow
Jimmy T.H. Smith
Jimmy T.H. Smith
PhD student, Stanford
Verified email at stanford.edu
Title
Cited by
Cited by
Year
Simplified state space layers for sequence modeling
JTH Smith, A Warrington, SW Linderman
arXiv preprint arXiv:2208.04933, 2022
3942022
Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems
J Smith, S Linderman, D Sussillo
Advances in Neural Information Processing Systems 34, 16700-16713, 2021
252021
Convolutional state space models for long-range spatiotemporal modeling
J Smith, S De Mello, J Kautz, S Linderman, W Byeon
Advances in Neural Information Processing Systems 36, 2024
122024
All-action policy gradient methods: A numerical integration approach
B Petit, L Amdahl-Culleton, Y Liu, J Smith, PL Bacon
arXiv preprint arXiv:1910.09093, 2019
92019
State-Free Inference of State-Space Models: The Transfer Function Approach
RN Parnichkun, S Massaroli, A Moro, JTH Smith, R Hasani, M Lechner, ...
arXiv preprint arXiv:2405.06147, 2024
32024
Towards a theory of learning dynamics in deep state space models
J Smékal, JTH Smith, M Kleinman, D Biderman, SW Linderman
arXiv preprint arXiv:2407.07279, 2024
12024
Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula
S Blouir, J Smith, A Anastasopoulos, A Shehu
arXiv preprint arXiv:2411.01030, 2024
2024
Towards Scalable and Stable Parallelization of Nonlinear RNNs
X Gonzalez, A Warrington, JTH Smith, SW Linderman
arXiv preprint arXiv:2407.19115, 2024
2024
Convolutional structured state space model
J Smith, W Byeon, S De Mello
US Patent App. 18/452,714, 2024
2024
Bayesian Inference in Augmented Bow Tie Networks
JTH Smith, D Lawson, SW Linderman
The system can't perform the operation now. Try again later.
Articles 1–10