conftrace_

computational efficiency

362 papers

Explore in graph

Co-occurring keywords

model compression (3302) efficient computing (781) large language model (13587) neural network optimization (1293) convolutional neural network (4226) neural network (6616) attention mechanism (4001) vision transformer (1106) transformer architecture (1560) model architecture (324)

Papers

Transkimmer: Transformer Learns to Layer-wise Skim ACL 2022
DeeCap: Dynamic Early Exiting for Efficient Image Captioning CVPR 2022
Active Learning Polynomial Threshold Functions NIPS 2022
Transform Once: Efficient Operator Learning in Frequency Domain NIPS 2022
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness NIPS 2022
Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold ACL 2022
Token Dropping for Efficient BERT Pretraining ACL 2022
Beyond Fixation: Dynamic Window Visual Transformer CVPR 2022
Randomized Sketches for Clustering: Fast and Optimal Kernel $k$-Means NIPS 2022
Small Footprint Neural Networks for Acoustic Direction of Arrival Estimation INTERSPEECH 2022
Warmstart Approach for Accelerating Deep Image Prior Reconstruction in Dynamic Tomography MIDL 2022
Towards Computationally Feasible Deep Active Learning NAACL 2022
Learning Routines for Effective Off-Policy Reinforcement Learning ICML 2021
Adaptive Focus for Efficient Video Recognition ICCV 2021
AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition ICCV 2021
Decoupled Dynamic Filter Networks CVPR 2021
Virtual Fully-Connected Layer: Training a Large-Scale Face Recognition Dataset With Limited Computational Resources CVPR 2021
Amata: An Annealing Mechanism for Adversarial Training Acceleration AAAI 2021
A Decomposition Model for Stereo Matching CVPR 2021
Efficient Deep Image Denoising via Class Specific Convolution AAAI 2021
Learning Optical Flow From a Few Matches CVPR 2021
Locality Sensitive Teaching NIPS 2021
Accelerating BERT Inference for Sequence Labeling via Early-Exit ACL 2021
Faster Neural Network Training with Approximate Tensor Operations NIPS 2021
Motion-Aware Dynamic Architecture for Efficient Frame Interpolation ICCV 2021