No article text was recorded for this version.
sigmoid-based attention
Version 1 of 137 papers60 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation
- Blog: D-PAttNet: Dynamic Patch-Attentive Deep Network for Action Unit Detection
- Blog: Combining Distant and Direct Supervision for Neural Relation Extraction
- Blog: Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding
- Blog: Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
- Blog: Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers
- Blog: A Cascaded Inception of Inception Network With Attention Modulated Feature Fusion for Human Pose Estimation
- Blog: Neural Discourse Structure for Text Categorization
- Blog: Deep multiple instance learning for foreground speech localization in ambient audio from wearable devices
- Blog: Adding Attentiveness to the Neurons in Recurrent Neural Networks
- Blog: Supervised Domain Enablement Attention for Personalized Domain Classification
- Blog: End-to-end Contextual Perception and Prediction with Interaction Transformer
- Blog: Temporal Pattern Attention for Multivariate Time Series Forecasting
- Blog: Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health
- Blog: Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens
- Blog: When Attention Sink Emerges in Language Models: An Empirical View
- Blog: Multi-modal Attention Network Learning for Semantic Source Code Retrieval
- Blog: Pay Attention to Categories: Syntax-Based Sentence Modeling with Metadata Projection Matrix
- Blog: Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection
- Blog: Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
- Blog: EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
- Blog: Hyperbolic Attention Networks
- Blog: Single-DARTS: Towards Stable Architecture Search
- Blog: ASMIL: Attention-Stabilized Multiple Instance Learning for Whole-Slide Imaging
- Blog: Compositional De-Attention Networks
- Blog: Improving Distant Supervision with Maxpooled Attention and Sentence-Level Supervision
- Blog: Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
- Blog: Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health
- Blog: Dynamic Injection of Entity Knowledge into Dense Retrievers
- Blog: Free-Lunch Saliency via Attention in Atari Agents
- Blog: ShortcutBreaker: Low-Rank Noisy Bottleneck with Global Perturbation Attention for Multi-Class Unsupervised Anomaly Detection
- Blog: NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamics
- Blog: Your Attention Matters: to Improve Model Robustness to Noise and Spurious Correlations
- Blog: Unraveling hidden interactions in complex systems with deep learning
- Blog: Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
- Blog: PRIOR: Prototype Representation Joint Learning from Medical Images and Reports
- Blog: Interpretable Recommendation via Attraction Modeling: Learning Multilevel Attractiveness over Multimodal Movie Contents
History & citation
Current · Permanent link
- This direction split from Non-sum-to-one Attention for Robust Transformers (84% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sigmoid_based_attention_cba9d213,
title = {sigmoid-based attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sigmoid-based-attention/rdr_cba9d2130e0847b8ad9e6947ab711853},
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_sigmoid_based_attention_cba9d213_v1,
title = {sigmoid-based attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sigmoid-based-attention/rdr_cba9d2130e0847b8ad9e6947ab711853/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}