paper-with-me

Papers

Probing Brain Context-Sensitivity with Masked-Attention Generation

2023-05-23 · Alexandre Pasquiou, Yair Lakretz, Bertrand Thirion, Christophe Pallier

Two fundamental questions in neurolinguistics concerns the brain regions that integrate information beyond the lexical level, and the size of their window of integration. To address these questions we introduce a new approach named masked-attention generation. It uses GPT-2 transformers to generate word embeddings that capture a fixed amount of contextual information. We then tested whether these embeddings could predict fMRI brain activity in humans listening to naturalistic text. The results showed that most of the cortex within the language network is sensitive to contextual information, and that the right hemisphere is more sensitive to longer contexts than the left. Masked-attention generation supports previous analyses of context-sensitivity in the brain, and complements them by quantifying the window size of context integration per voxel.

📄 PDF Abstract BibTeX arXiv:2305.13863

Code (0)

등록된 구현이 없습니다.

Tasks

SensitivityWord Embeddings

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Keypoint Aware Masked Image Modelling

2024-07-18 · Madhava Krishna, A V Subramanyam

SimMIM is a widely used method for pretraining vision transformers using masked image modeling. However, despite its success in fine-tuning performance, it has been shown to perform sub-optimally when used for linear pro…

Contrastive Learning

CORE: Context-Robust Remasking for Diffusion Language Models

2026-02-04 · Kevin Zhai, Sabbir Mollah, Zhenyi Wang, Mubarak Shah arxiv

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade e…

Attention, Please! Revisiting Attentive Probing for Masked Image Modeling

2025-06-11 · Bill Psomas, Dionysis Christopoulos, Eirini Baltzi, Ioannis Kakogeorgiou 외

As fine-tuning (FT) becomes increasingly impractical at scale, probing is emerging as the preferred evaluation protocol for self-supervised learning (SSL). Yet, the standard linear probing (LP) fails to adequately reflec…

BenchmarkingComputational EfficiencySelf-Supervised Learning

SiamJEPA: On the Role of Siamese Student Encoders in JEPA

2026-07-04 · Makoto Yamada hf

Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for self-supervised representation learning…

Representation Learning

Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations

2021-09-28 · EMNLP (MRL) 2021 11 · Ekaterina Taktasheva, Vladislav Mikhailov, Ekaterina Artemova

Recent research has adopted a new experimental field centered around the concept of text perturbations which has revealed that shuffled word order has little to no impact on the downstream performance of Transformer-base…

Sensitivity