no code implementations • 10 Oct 2023 • Aditya R. Vaidya, Javier Turek, Alexander G. Huth
In contrast with these findings, we present a scenario in which the performance of humans and LMs diverges.
2 code implementations • 17 May 2023 • Chandan Singh, Aliyah R. Hsu, Richard Antonello, Shailee Jain, Alexander G. Huth, Bin Yu, Jianfeng Gao
Here, we ask whether we can automatically obtain natural language explanations for black box text modules.
no code implementations • 27 May 2022 • Aditya R. Vaidya, Shailee Jain, Alexander G. Huth
Overall, these results show that self-supervised models effectively capture the hierarchy of information relevant to different stages of speech processing in human cortex.
no code implementations • 17 May 2021 • Akarsh Kumar, Aditya R. Vaidya, Alexander G. Huth
All hand-object interaction is controlled by forces that the two bodies exert on each other, but little work has been done in modeling these underlying forces when doing pose and contact estimation from RGB/RGB-D data.
no code implementations • ICLR 2021 • Shivangi Mahto, Vy A. Vo, Javier S. Turek, Alexander G. Huth
Earlier work has demonstrated that dependencies in natural language tend to decay with distance between words according to a power law.
1 code implementation • ICML 2020 • Javier S. Turek, Shailee Jain, Vy Vo, Mihai Capota, Alexander G. Huth, Theodore L. Willke
In this work, we explore the delayed-RNN, which is a single-layer RNN that has a delay between the input and output.