No article text was recorded for this version.
interpretability of attention mechanisms
Version 1 of 1119 papers128 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Measuring and Improving Faithfulness of Attention in Neural Machine Translation
- Blog: Structured Self-AttentionWeights Encode Semantics in Sentiment Analysis
- Blog: Attention vs non-attention for a Shapley-based explanation method
- Blog: Similarity Analysis of Contextual Word Representation Models
- Blog: Pay “Attention” to your Context when Classifying Abusive Language
- Blog: Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification
- Blog: The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?
- Blog: An Interpretable and Attention-Based Method for Gaze Estimation Using Electroencephalography
- Blog: Effective Attention Sheds Light On Interpretability
- Blog: Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?
- Blog: TransformerLSR: Attentive joint model of longitudinal data, survival, and recurrent events with concurrent latent structure
- Blog: Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?
- Blog: Understanding and improving recurrent networks for human activity recognition by continuous attention
- Blog: AiR: Attention with Reasoning Capability
- Blog: Medical Image Classification Algorithm Based on Visual Attention Mechanism‐MCNN
- Blog: Relation Networks for Object Detection
- Blog: Understanding Neural Abstractive Summarization Models via Uncertainty
- Blog: A Neighbourhood Framework for Resource-Lean Content Flagging
- Blog: SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks
- Blog: Learning Temporal and Bodily Attention in Protective Movement Behavior Detection
- Blog: M3d-CAM - A PyTorch Library to Generate 3D Attention Maps for Medical Deep Learning
- Blog: Variational Self-attention Model for Sentence Representation
- Blog: Convolutional Neural Networks for Authorship Attribution of Short Texts
- Blog: How Does a Transformer Learn Compression? An Attention Study on Huffman and LZ4
- Blog: Attention-based Dynamic Subspace Learners
- Blog: Routing with Self-Attention for Multimodal Capsule Networks
- Blog: Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?
- Blog: Linking In-context Learning in Transformers to Human Episodic Memory
- Blog: Medical Time Series Classification with Hierarchical Attention-based Temporal Convolutional Networks: A Case Study of Myotonic Dystrophy Diagnosis
- Blog: Less Is More Important: An Attention Module Guided by Probability Density Function for Convolutional Neural Networks
- Blog: Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few
- Blog: DeepANIS: Predicting antibody paratope from concatenated CDR sequences by integrating bidirectional long-short-term memory and transformer neural networks
- Blog: Dynamic Focus-aware Positional Queries for Semantic Segmentation
- Blog: Deep Attentive End-to-End Continuous Breath Sensing from Speech
- Blog: MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis
- Blog: Tailoring Self-Attention for Graph via Rooted Subtrees
- Blog: Attention mechanisms in computer vision: A survey
- Blog: CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
- Blog: Attention Approximates Sparse Distributed Memory
- Blog: EGRET: Edge Aggregated Graph Attention Networks and Transfer Learning Improve Protein-Protein Interaction Site Prediction
- Blog: Linear Context Transform Block
- Blog: Position Engineering: Boosting Large Language Models through Positional Information Manipulation
- Blog: Attention Awareness Multiple Instance Neural Network
- Blog: Narrowing the semantic gaps in U-Net with learnable skip connections: The case of medical image segmentation
- Blog: Attending to Routers Aids Indoor Wireless Localization
- Blog: A Shared Attention Mechanism for Interpretation of Neural Automatic Post-Editing Systems
- Blog: Understanding More About Human and Machine Attention in Deep Neural Networks
- Blog: Selective Attention: Enhancing Transformer through Principled Context Control
- Blog: Seeing Eye to AI: Comparing Human Gaze and Model Attention in Video Memorability
- Blog: Attention Meets Post-hoc Interpretability: A Mathematical Perspective
- Blog: CU-MAM: Coherence-Driven Unified Macro-Structures for Argument Mining
- Blog: AptaBLE: A Deep Learning Platform for Aptamer Generation and Analysis
- Blog: Towards understanding structure–property relations in materials with interpretable deep learning
- Blog: Removing Bias with Residual Mixture of Multi-View Attention for Speech Emotion Recognition
- Blog: Edge Attention-based Multi-Relational Graph Convolutional Networks
- Blog: On the Dynamics of Training Attention Models
- Blog: Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
- Blog: Canonical Saliency Maps: Decoding Deep Face Models
- Blog: Neural Relation Inference for Multi-dimensional Temporal Point Processes via Message Passing Graph
- Blog: Predicting utilization of healthcare services from individual disease trajectories using RNNs with multi-headed attention
Showing 60 of 119 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_interpretability_of_attention_mechanisms_ab60c8a0,
title = {interpretability of attention mechanisms},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/interpretability-of-attention-mechanisms/rdr_ab60c8a02b0f42b9aded952b52ac677d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_interpretability_of_attention_mechanisms_ab60c8a0_v1,
title = {interpretability of attention mechanisms},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/interpretability-of-attention-mechanisms/rdr_ab60c8a02b0f42b9aded952b52ac677d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}