No article text was recorded for this version.
diagonal-masked self-attention
Version 2 of 216 papers22 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
- Blog: Enhanced Transformer Architecture for Natural Language Processing
- Blog: ANNA”:" Enhanced Language Representation for Question Answering
- Blog: ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series
- Blog: Reasoning with Sarcasm by Reading In-Between
- Blog: Knowledge-aware Attention Network for Protein-Protein Interaction Extraction
- Blog: Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition
- Blog: Context-Aware Multimodal Pretraining
- Blog: DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization
- Blog: Knowledgeable Salient Span Mask for Enhancing Language Models as Knowledge Base
- Blog: Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning
- Blog: Gaussian Transformer: A Lightweight Approach for Natural Language Inference
- Blog: Layer-Condensed KV Cache for Efficient Inference of Large Language Models
- Blog: Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
- Blog: Rethinking Item Importance in Session-based Recommendation
- Blog: TLM: Token-Level Masking for Transformers
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_diagonal_masked_self_attention_8e1bf18d,
title = {diagonal-masked self-attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/diagonal-masked-self-attention/rdr_8e1bf18d4cef46009a3e18810c8ff734},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_diagonal_masked_self_attention_8e1bf18d_v2,
title = {diagonal-masked self-attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/diagonal-masked-self-attention/rdr_8e1bf18d4cef46009a3e18810c8ff734/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}