29 citations · 134 across the 10 of their papers we have counts for
12 papers
Brain encoding models based on multimodal transformers can transfer across language and vision
Jerry Tang, Meng Du, Vy A. Vo +2
Encoding models have been used to assess how the human brain represents concepts in language and vision. While language and vision rely on similar concept representations, current…
Scaling laws for language encoding models in fMRI
Richard Antonello, Aditya Vaidya, Alexander G. Huth
Representations from transformer-based unidirectional language models are known to be effective at predicting brain responses to natural language. However, most studies comparing l…
Explaining black box text modules in natural language with language models
Chandan Singh, Aliyah R. Hsu, Richard Antonello +4
Large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their rapid proliferation and increasing opaqueness have cre…
Self-supervised models of audio effectively explain human cortical responses to speech
Aditya R. Vaidya, Shailee Jain, Alexander G. Huth
Self-supervised language models are very effective at predicting high-level cortical responses during language comprehension. However, the best current models of lower-level audito…
Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses
Richard Antonello, Javier Turek, Vy Vo +1
How related are the representations learned by neural language models, translation models, and language tagging tasks? We answer this question by adapting an encoder-decoder transf…
Physically Plausible Pose Refinement using Fully Differentiable Forces
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 c…
Multi-timescale Representation Learning in LSTM Language Models
Shivangi Mahto, Vy A. Vo, Javier S. Turek +1
Language models must capture statistical dependencies between words at timescales ranging from very short to very long. Earlier work has demonstrated that dependencies in natural l…
Selecting Informative Contexts Improves Language Model Finetuning
Richard Antonello, Nicole Beckage, Javier Turek +1
Language model fine-tuning is essential for modern natural language processing, but is computationally expensive and time-consuming. Further, the effectiveness of fine-tuning is li…
Approximating Stacked and Bidirectional Recurrent Architectures with the Delayed Recurrent Neural Network
Javier S. Turek, Shailee Jain, Vy Vo +3
Recent work has shown that topological enhancements to recurrent neural networks (RNNs) can increase their expressiveness and representational capacity. Two popular enhancements ar…
Deep Generative Modeling for Scene Synthesis via Hybrid Representations
Zaiwei Zhang, Zhenpei Yang, Chongyang Ma +4
We present a deep generative scene modeling technique for indoor environments. Our goal is to train a generative model using a feed-forward neural network that maps a prior distrib…
Efficient, sparse representation of manifold distance matrices for classical scaling
Javier S. Turek, Alexander Huth
Geodesic distance matrices can reveal shape properties that are largely invariant to non-rigid deformations, and thus are often used to analyze and represent 3-D shapes. However, t…
PrAGMATiC: a Probabilistic and Generative Model of Areas Tiling the Cortex
Alexander G. Huth, Thomas L. Griffiths, Frederic E. Theunissen +1
Much of the human cortex seems to be organized into topographic cortical maps. Yet few quantitative methods exist for characterizing these maps. To address this issue we developed…