No article text was recorded for this version.
bidirectional attention conversion
Version 1 of 121 papers28 conceptsfrozen 2026-10-04
Papers in this version
- Blog: LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
- Blog: The Impossibility of Inverse Permutation Learning in Transformer Models
- Blog: KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
- Blog: DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers
- Blog: NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- Blog: Nemotron ColEmbed V2: Top-Performing Late Interaction embedding models for Visual Document Retrieval
- Blog: Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
- Blog: Rethinking Causal Mask Attention for Vision-Language Inference
- Blog: ModernVBERT: Towards Smaller Visual Document Retrievers
- Blog: Generative Representational Instruction Tuning
- Blog: When Text Embedding Meets Large Language Model: A Comprehensive Survey
- Blog: Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention
- Blog: Scaling Sparse and Dense Retrieval in Decoder-Only LLMs
- Blog: LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation
- Blog: Understanding the Reversal Curse Mitigation in Masked Diffusion Models through Attention and Training Dynamics
- Blog: MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks
- Blog: FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
- Blog: ETAS: Zero-Shot Transformer Architecture Search via Network Trainability and Expressivity
- Blog: An Analysis and Mitigation of the Reversal Curse
- Blog: Enhancing Lexicon-Based Text Embeddings with Large Language Models
- Blog: Autoregressive Image Generation without Vector Quantization
History & citation
Current · Permanent link
- This direction split from Overcoming the Causal Bottleneck in Generative Transformers (67% overlap)
- This direction split from Bidirectional Attention for Decoder Only Representation (76% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_bidirectional_attention_conversion_dc13c9fd,
title = {bidirectional attention conversion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/bidirectional-attention-conversion/rdr_dc13c9fdebb84fcebacff0cf248647a6},
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_bidirectional_attention_conversion_dc13c9fd_v1,
title = {bidirectional attention conversion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/bidirectional-attention-conversion/rdr_dc13c9fdebb84fcebacff0cf248647a6/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}