Swin Transformer reaches 87.3% ImageNet accuracy and sets new records on COCO detection and ADE20K segmentation by replacing global self-attention with shifted-window local attention inside a hierarchical pyramid.
arXiv preprint arXiv:2102.10882 (2021)
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
The work demonstrates masked-token prediction with transformers for model-independent anomaly detection in LHC data, achieving strong results on top-rich BSM signatures like four-top production using VQ-VAE tokenization.
A hierarchical mesh transformer using topology-guided pretraining on simplicial complexes achieves state-of-the-art results on Alzheimer's classification, amyloid prediction, and focal cortical dysplasia detection from brain meshes.
Massive activations are constant large values in LLMs that function as indispensable bias terms and concentrate attention probabilities on specific tokens.
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
Device Passport improves cross-layout transfer for biosignal models by learning expert mixture models from each channel's functional activity and metadata, outperforming baselines in transfer regimes.
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
LCLMs are scaled 0.6B-encoder 4B-decoder compressors pre-trained on over 350B tokens that improve the Pareto frontier for general-task performance, compression speed, and peak memory in long-context language model inference.
WaveLiT combines wavelet tokenization, linear attention, and multiscale pyramids to produce parameter-efficient neural PDE solvers that match much larger models on TheWell benchmarks.
LOOPE learns a patch ordering for positional embeddings in ViTs and introduces the Three Cell Experiment benchmark that shows 30-35% gaps in positional retention versus the usual 4-6%.
USEMA is a hybrid UNet architecture merging CNNs with scalable Mamba-like attention (SEMA) that achieves better efficiency than transformers and superior segmentation accuracy than pure CNN or Mamba models across medical imaging modalities.
GSAM applies random cropping to enable variable input sizes for efficient SAM fine-tuning, claiming lower compute with comparable or higher accuracy on varied datasets.
citing papers explorer
-
Massive Activations in Large Language Models
Massive activations are constant large values in LLMs that function as indispensable bias terms and concentrate attention probabilities on specific tokens.
-
End-to-End Context Compression at Scale
LCLMs are scaled 0.6B-encoder 4B-decoder compressors pre-trained on over 350B tokens that improve the Pareto frontier for general-task performance, compression speed, and peak memory in long-context language model inference.