Techniques

“No Free Lunch” in Neural Architectures? A Joint Analysis of Expressivity, Convergence, and Generalization AutoML 2023 Noise-Robust Semi-Supervised Learning for Distantly Supervised Relation Extraction EMNLP 2023 Normalization-Equivariant Neural Networks with Application to Image Denoising NeurIPS 2023 Normalization Layers Are All That Sharpness-Aware Minimization Needs NeurIPS 2023 NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models ACL 2023 “Nothing Abnormal”: Disambiguating Medical Reports via Contrastive Knowledge Infusion AAAI 2023 N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition Interspeech 2023 ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection ICLR 2023 OmniMAE: Single Model Masked Pretraining on Images and Videos CVPR 2023 OMPQ: Orthogonal Mixed Precision Quantization AAAI 2023 On Bridging the Gap between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization ICML 2023 On Conditional and Compositional Language Model Differentiable Prompting IJCAI 2023 On Efficient Transformer-Based Image Pre-training for Low-Level Vision IJCAI 2023 One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models NeurIPS 2023 On Enhancing Fine-Tuning for Pre-trained Language Models EMNLP 2023 One-Shot Model for Mixed-Precision Quantization CVPR 2023 One Wide Feedforward Is All You Need EMNLP 2023 On Investigating the Conservative Property of Score-Based Generative Models ICML 2023 On Pre-training Language Model for Antibody ICLR 2023 On “Scientific Debt” in NLP: A Case for More Rigour in Language Model Pre-Training Research ACL 2023 On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis MIDL 2023 On Separate Normalization in Self-supervised Transformers NeurIPS 2023 On skip connections and normalisation layers in deep optimisation NeurIPS 2023 On Sparse Modern Hopfield Model NeurIPS 2023 On the Benefits of Learning to Route in Mixture-of-Experts Models EMNLP 2023