No article text was recorded for this version.
proportional attention weighting
Version 2 of 218 papers21 conceptsfrozen 2026-10-04
Papers in this version
- Blog: ADAPTOR: Adaptive Token Reduction for Video Diffusion Transformers
- Blog: Fast KV Compaction via Attention Matching
- Blog: BccT: an efficient transformer model for blood cell classification
- Blog: Efficient Vision Transformers via Token Merging with Head-wise Attention Correction
- Blog: AiluRus: A Scalable ViT Framework for Dense Prediction
- Blog: Agglomerative Token Clustering
- Blog: Token Merging: Your ViT But Faster
- Blog: Video, How Do Your Tokens Merge?
- Blog: Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
- Blog: GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
- Blog: Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs
- Blog: TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token Merging
- Blog: Attention Modulation for Zero-Shot Cross-Domain Dialogue State Tracking
- Blog: Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers
- Blog: Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
- Blog: Accelerating Transformers with Spectrum-Preserving Token Merging
- Blog: Attention Normalization Impacts Cardinality Generalization in Slot Attention
- Blog: See What You Are Told: Visual Attention Sink in Large Multimodal Models
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_proportional_attention_weighting_a40ea3dd,
title = {proportional attention weighting},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/proportional-attention-weighting/rdr_a40ea3dd265f4f628a703e11983e2153},
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_proportional_attention_weighting_a40ea3dd_v2,
title = {proportional attention weighting},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/proportional-attention-weighting/rdr_a40ea3dd265f4f628a703e11983e2153/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}