Efficient Computing

Mask-Guided Spectral-Wise Transformer for Efficient Hyperspectral Image Reconstruction CVPR 2022 Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token EMNLP 2022 Matryoshka Representation Learning NeurIPS 2022 Memory safe computations with XLA compiler NeurIPS 2022 MIA-Former: Efficient and Robust Vision Transformers via Multi-Grained Input-Adaptation AAAI 2022 MLink: Linking Black-Box Models for Collaborative Multi-Model Inference AAAI 2022 Mobile-Former: Bridging MobileNet and Transformer CVPR 2022 Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems EMNLP 2022 Modeling Context With Linear Attention for Scalable Document-Level Translation EMNLP 2022 Modify Self-Attention via Skeleton Decomposition for Effective Point Cloud Transformer AAAI 2022 Motion-From-Blur: 3D Shape and Motion Estimation of Motion-Blurred Objects in Videos CVPR 2022 Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error CVPR 2022 MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens CVPR 2022 NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies NeurIPS 2022 Neural Data-Dependent Transform for Learned Image Compression CVPR 2022 Non-Autoregressive Machine Translation: It’s Not as Fast as it Seems NAACL 2022 Non-Autoregressive Models for Fast Sequence Generation EMNLP 2022 Non-deep Networks NeurIPS 2022 Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation CVPR 2022 OCSampler: Compressing Videos to One Clip With Single-Step Sampling CVPR 2022 On-Device Training Under 256KB Memory NeurIPS 2022 Online Convolutional Re-Parameterization CVPR 2022 On the Locality of Attention in Direct Speech Translation ACL 2022 OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion NeurIPS 2022 Optical Flow Estimation for Spiking Camera CVPR 2022