Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
- Ido Amos
- Jonathan Berant
- et al.
- 2024
- ICLR 2024
Publications
Date
Featured collections
Popular topics
6 results for Ankit Gupta
Long Range Language Modeling via Gated State Spaces
- Harsh Mehta
- Ankit Gupta
- et al.
- 2023
- ICLR 2023
On the Parameterization and Initialization of Diagonal State Space Models
- Albert Gu
- Ankit Gupta
- et al.
- 2022
- NeurIPS 2022
Diagonal State Spaces are as Effective as Structured State Spaces
- Ankit Gupta
- Albert Gu
- et al.
- 2022
- NeurIPS 2022
Exploring the limits of decoder-only models trained on public speech recognition corpora
- Ankit Gupta
- George Saon
- et al.
- 2024
- INTERSPEECH 2024
Diagonal State Space Augmented Transformers for Speech Recognition
- George Saon
- Ankit Gupta
- et al.
- 2023
- ICASSP 2023