Search Results for author:
Found 7 papers, 4 papers with code
Humans and language models diverge when predicting repeating text
In contrast with these findings, we present a scenario in which the performance of humans and LMs diverges.
Scaling laws for language encoding models in fMRI
Representations from transformer-based unidirectional language models are known to be effective at predicting brain responses to natural language.
Explaining black box text modules in natural language with language models
Here, we ask whether we can automatically obtain natural language explanations for black box text modules.
Self-supervised models of audio effectively explain human cortical responses to speech
Overall, these results show that self-supervised models effectively capture the hierarchy of information relevant to different stages of speech processing in human cortex.
Physically Plausible Pose Refinement using Fully Differentiable Forces
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.
Multi-timescale Representation Learning in LSTM Language Models
Earlier work has demonstrated that dependencies in natural language tend to decay with distance between words according to a power law.
Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network
In this work, we explore the delayed-RNN, which is a single-layer RNN that has a delay between the input and output.
