| Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling | Sep 14, 2021 | Inductive Bias | CodeCode Available | 1 |
| The Grammar-Learning Trajectories of Neural Language Models | Sep 13, 2021 | Inductive Bias | CodeCode Available | 0 |
| Good-Enough Example Extrapolation | Sep 12, 2021 | Data AugmentationInductive Bias | —Unverified | 0 |
| Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification? | Sep 12, 2021 | Inductive BiasNode Classification | —Unverified | 0 |
| The Impact of Positional Encodings on Multilingual Compression | Sep 11, 2021 | Inductive Bias | —Unverified | 0 |
| MATE: Multi-view Attention for Table Transformer Efficiency | Sep 9, 2021 | Inductive BiasQuestion Answering | —Unverified | 0 |
| Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids | Sep 8, 2021 | Inductive BiasInductive Learning | —Unverified | 0 |
| nnFormer: Interleaved Transformer for Volumetric Segmentation | Sep 7, 2021 | Image SegmentationInductive Bias | CodeCode Available | 1 |
| Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis | Sep 7, 2021 | Few-Shot LearningInductive Bias | —Unverified | 0 |
| Learning Hierarchical Structures with Differentiable Nondeterministic Stacks | Sep 5, 2021 | Inductive BiasLanguage Modeling | CodeCode Available | 1 |
| Rethinking Deep Image Prior for Denoising | Aug 29, 2021 | DenoisingInductive Bias | CodeCode Available | 1 |
| Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation | Aug 27, 2021 | Inductive BiasPlaying the Game of 2048 | CodeCode Available | 2 |
| PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers | Aug 19, 2021 | DecoderInductive Bias | CodeCode Available | 1 |
| Learning Type Annotation: Is Big Data Enough? | Aug 18, 2021 | Inductive Bias | CodeCode Available | 0 |
| ConvNets vs. Transformers: Whose Visual Representations are More Transferable? | Aug 11, 2021 | ClassificationDepth Estimation | —Unverified | 0 |
| A Generalizable Model-and-Data Driven Approach for Open-Set RFF Authentication | Aug 10, 2021 | Inductive Bias | CodeCode Available | 1 |
| Analysis of ODE2VAE with Examples | Aug 10, 2021 | Inductive Bias | —Unverified | 0 |
| RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality? | Aug 9, 2021 | Inductive Biasobject-detection | CodeCode Available | 1 |
| Global Self-Attention as a Replacement for Graph Convolution | Aug 7, 2021 | Edge ClassificationGraph Classification | CodeCode Available | 1 |
| S^2-MLPv2: Improved Spatial-Shift MLP Architecture for Vision | Aug 2, 2021 | Inductive Bias | CodeCode Available | 0 |
| Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data | Aug 1, 2021 | Code GenerationInductive Bias | CodeCode Available | 1 |
| Towards Data-Driven Synthesis of Autonomous Vehicle Safety Concepts | Jul 30, 2021 | Autonomous VehiclesInductive Bias | —Unverified | 0 |
| ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation | Jul 29, 2021 | Domain AdaptationHallucination | CodeCode Available | 1 |
| Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study | Jul 28, 2021 | ChunkingInductive Bias | CodeCode Available | 0 |
| H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences | Jul 25, 2021 | Inductive BiasLanguage Modelling | CodeCode Available | 1 |
