| Object-Region Video Transformers | 0 | 0.34 | 2022 |
| DETReg: Unsupervised Pretraining with Region Priors for Object Detection | 0 | 0.34 | 2022 |
| On the inductive bias of neural networks for learning read-once DNFs. | 0 | 0.34 | 2022 |
| Learning to Retrieve Passages without Supervision | 0 | 0.34 | 2022 |
| Efficient Learning of CNNs using Patch Based Features. | 0 | 0.34 | 2022 |
| Active learning with label comparisons. | 0 | 0.34 | 2022 |
| On the Implicit Bias of Gradient Descent for Temporal Extrapolation | 0 | 0.34 | 2022 |
| Compositional Video Synthesis With Action Graphs | 0 | 0.34 | 2021 |
| Explaining in Style: Training a GAN to explain a classifier in StyleSpace | 0 | 0.34 | 2021 |
| On The Implicit Bias Of Initialization Shape: Beyond Infinitesimal Mirror Descent | 0 | 0.34 | 2021 |
| An optimization and generalization analysis for max-pooling networks. | 0 | 0.34 | 2021 |
| Towards Understanding Learning in Neural Networks with Linear Teachers | 0 | 0.34 | 2021 |
| Optimal Strategies Against Generative Attacks | 0 | 0.34 | 2020 |
| A Simple and Effective Model for Answering Multi-span Questions. | 0 | 0.34 | 2020 |
| Regularizing Towards Permutation Invariance In Recurrent Models | 0 | 0.34 | 2020 |
| Pre-training Mention Representations in Coreference Models. | 0 | 0.34 | 2020 |
| Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing. | 1 | 0.35 | 2019 |
| Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem | 1 | 0.34 | 2019 |
| Learning Latent Scene-Graph Representations for Referring Relationships. | 0 | 0.34 | 2019 |
| Classifying Collisions with Spatio-Temporal Action Graph Networks. | 2 | 0.38 | 2018 |
| Predict and Constrain: Modeling Cardinality in Deep Structured Prediction. | 1 | 0.35 | 2018 |
| Learning to Optimize Combinatorial Functions. | 1 | 0.36 | 2018 |
| Over-parameterization Improves Generalization in the XOR Detection Problem. | 0 | 0.34 | 2018 |
| Explaining Queries over Web Tables to Non-Experts. | 0 | 0.34 | 2018 |
| Learning with Rules. | 0 | 0.34 | 2018 |
| Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction. | 10 | 0.50 | 2018 |
| Weakly Supervised Semantic Parsing with Abstract Examples. | 5 | 0.42 | 2018 |
| Learning Infinite Layer Networks Without the Kernel Trick. | 0 | 0.34 | 2017 |
| Robust Conditional Probabilities. | 0 | 0.34 | 2017 |
| SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data. | 31 | 0.86 | 2017 |
| Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs. | 54 | 1.71 | 2017 |
| Effective Semisupervised Learning on Manifolds. | 0 | 0.34 | 2017 |
| Learning and Inference with Expectations. | 0 | 0.34 | 2017 |
| Discriminative Learning of Infection Models. | 1 | 0.35 | 2016 |
| Improper Deep Kernels. | 3 | 0.39 | 2016 |
| Optimal Tagging with Markov Chain Optimization. | 3 | 0.38 | 2016 |
| Learning to generalize to new compositions in image understanding. | 6 | 0.45 | 2016 |
| Learning Infinite-Layer Networks: Beyond the Kernel Trick. | 0 | 0.34 | 2016 |
| Collective Entity Resolution With Multi-Focal Attention | 14 | 0.56 | 2016 |
| Template Kernels for Dependency Parsing. | 3 | 0.42 | 2015 |
| How Hard is Inference for Structured Prediction? | 5 | 0.40 | 2015 |
| Efficient Lifting of MAP LP Relaxations Using k-Locality. | 9 | 0.51 | 2014 |
| Lifted Message Passing As Reparametrization Of Graphical Models | 6 | 0.44 | 2014 |
| Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment. | 8 | 0.47 | 2014 |
| Discrete Chebyshev Classifiers. | 5 | 0.51 | 2014 |
| Inferning with High Girth Graphical Models. | 3 | 0.47 | 2014 |
| Tightness Results For Local Consistency Relaxations In Continuous Mrfs | 2 | 0.37 | 2014 |
| Spectral Regularization for Max-Margin Sequence Tagging. | 6 | 0.44 | 2014 |
| Steps To Excellence: Simple Inference With Refined Scoring Of Dependency Trees | 0 | 0.34 | 2014 |
| Learning Structured Models with the AUC Loss and Its Generalizations. | 11 | 0.53 | 2014 |
