model architecture

The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023 TIPS: Topologically Important Path Sampling for Anytime Neural Networks ICML 2023 Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity NeurIPS 2023 Tracr: Compiled Transformers as a Laboratory for Interpretability NeurIPS 2023 Trained on 100 million words and still in shape: BERT meets British National Corpus EACL 2023 Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models NeurIPS 2023 YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors CVPR 2023 A ConvNet for the 2020s CVPR 2022 A Decoder-free Transformer-like Architecture for High-efficiency Single Image Deraining IJCAI 2022 Adversarial Robustness in Multi-Task Learning: Promises and Illusions AAAI 2022 Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition Interspeech 2022 A New Perspective on the Effects of Spectrum in Graph Neural Networks ICML 2022 AutoBERT-Zero: Evolving BERT Backbone from Scratch AAAI 2022 Automated Super-Network Generation for Scalable Neural Architecture Search AutoML 2022 B-Cos Networks: Alignment Is All We Need for Interpretability CVPR 2022 Better Few-Shot Relation Extraction with Label Prompt Dropout EMNLP 2022 Beyond Fixation: Dynamic Window Visual Transformer CVPR 2022 BINAS: Bilinear Interpretable Neural Architecture Search ACML 2022 Compositional Attention: Disentangling Search and Retrieval ICLR 2022 EENAS: An Efficient Evolutionary Algorithm for Neural Architecture Search ACML 2022 EfficientFormer: Vision Transformers at MobileNet Speed NeurIPS 2022 Efficient Training of Low-Curvature Neural Networks NeurIPS 2022 GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks NeurIPS 2022 GNN2GNN: Graph neural networks to generate neural networks UAI 2022 Learning Strides in Convolutional Neural Networks ICLR 2022