A Faster Pytorch Implementation of Multi-Head Self-Attention
Official PyTorch Implementation of 'Entropy-Guided Attention for Private LLMs' (PPAI Workshop. AAAI 2025)
[IROS 2024] Language-driven Grasp Detection with Mask-guided Attention
CLI toolkit that ingests qk-sniffer dumps, measures per-head positional predictability and attention plasticity, and exports CSV stats plus ready-to-share plots.
This work proposes STAC, a novel framework for weakly supervised defect localization that leverages saliency-guided transformer attention and pixel-level contrastive learning to achieve precise defect maps using only image-level labels.
Investigating how formal constraints reorganize the internal routing geometry of Transformer attention graphs across model families.
Train your attention like a transformer trains its weights. Selective, sustained & N-back exercises grounded in the Q/K/V attention framework.
HopfieldLab — Interactive Modern Hopfield Network & Associative Memory Laboratory with 3D energy landscapes, attention-Hopfield bridge, phase transitions, and memory interference visualization
Add a description, image, and links to the transformer-attention topic page so that developers can more easily learn about it.
To associate your repository with the transformer-attention topic, visit your repo's landing page and select "manage topics."