conftrace_

linear complexity

62 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) efficient computing (781) transformer architecture (1560) state space model (390) vision transformer (1106) self-attention mechanism (352) image classification (1944) linear attention (52) semantic segmentation (3186) approximation algorithm (630)

Papers

Scaling Laws for Linear Complexity Language Models EMNLP 2024
Scalable and Effective Conductance-Based Graph Clustering AAAI 2023
Singularformer: Learning to Decompose Self-Attention to Linearize the Complexity of Transformer IJCAI 2023
MB-TaylorFormer: Multi-Branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing ICCV 2023
ViBid: Linear Vision Transformer with Bidirectional Normalization UAI 2023
RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration ICCV 2023
KDLGT: A Linear Graph Transformer Framework via Kernel Decomposition Approach IJCAI 2023
Linear-Time Modeling of Linguistic Structure: An Order-Theoretic Perspective EMNLP 2023
HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition INTERSPEECH 2023
Linear Complexity Randomized Self-attention Mechanism ICML 2022
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences NAACL 2022
Flowformer: Linearizing Transformers with Conservation Flows ICML 2022
PatchFormer: An Efficient Point Transformer With Patch Attention CVPR 2022
EcoFormer: Energy-Saving Attention with Linear Complexity NIPS 2022
Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost NIPS 2022
Linearizing Transformer with Key-Value Memory EMNLP 2022
Giga-scale Kernel Matrix-Vector Multiplication on GPU NIPS 2022
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling ICML 2021
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding ICCV 2021
Relative Positional Encoding for Transformers with Linear Complexity ICML 2021
H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences ACL 2021
XCiT: Cross-Covariance Image Transformers NIPS 2021
Long-Short Transformer: Efficient Transformers for Language and Vision NIPS 2021
SOFT: Softmax-free Transformer with Linear Complexity NIPS 2021
H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences IJCNLP 2021