Introduced Multi-News dataset and hierarchical abstractive model Hi-MAP, achieving ROUGE-1 35.78 and outperforming baselines.

Alexander R. Fabbri, Irene Li, Tianwei She et al.

Proposes Scene Representation Networks (SRNs), a continuous, differentiable scene model trained end-to-end from 2D images, capturing geometry and appearance without supervision.

Vincent Sitzmann, Michael Zollhöfer, Gordon Wetzstein

3D-BoNet directly predicts 3D bounding boxes and instance masks on point clouds, achieving 10x efficiency gains and surpassing ScanNet and S3DIS benchmarks.

Bo Yang, Jianan Wang, Ronald Clark et al.

Proposes an episodic memory model using sparse experience replay and local adaptation to mitigate catastrophic forgetting, reducing space complexity by 50-90%.

Cyprien de Masson d'Autume, Sebastian Ruder, Lingpeng Kong et al.

Using adversarial robustness as a prior, the paper achieves near-invertible, interpretable feature representations with improved visualization and manipulation, surpassing standard models.

Logan Engstrom, Andrew Ilyas, Shibani Santurkar et al.

Proposes Latent Retrieval with BERT and ICT pretraining, achieving 19-point EM gains over BM25 in open-domain QA.

Kenton Lee, Ming-Wei Chang, Kristina Toutanova

ActiveHARNet integrates Bayesian neural networks and active learning, significantly reducing labeled data points.

Gautham Krishna Gudur, Prahalathan Sundaramoorthy, Venkatesh Umaashankar

DLRM integrates embedding tables, MLP, and feature interactions, employing model and data parallelism to scale recommendation systems efficiently.

Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi et al.

Proposes Nyström-based exact DPP sampling with sublinear preprocessing and poly(k) sampling time.

Michał Dereziński, Daniele Calandriello, Michal Valko

Introduces MathQA dataset with operation-based formalism and neural models for interpretable math problem solving, achieving 54.2% accuracy.

Aida Amini, Saadia Gabriel, Peter Lin et al.

Graph Normalizing Flows: a novel reversible GNN model with reduced memory footprint for large-scale graphs.

Jenny Liu, Aviral Kumar, Jimmy Ba et al.

Combines Bayesian Eigenobjects with language models for viewpoint-invariant object understanding, enabling few-shot learning and attribute prediction.

Vanya Cohen, Benjamin Burchfiel, Thao Nguyen et al.

Proves equivalence between graph isomorphism testing and GNN function approximation, introduces Ring-GNN to distinguish non-isomorphic graphs.

Zhengdao Chen, Soledad Villar, Lei Chen et al.

Proposes node- and graph-level pretraining with self-supervised tasks, achieving up to 9.4% ROC-AUC improvement on molecular datasets.

Weihua Hu, Bowen Liu, Joseph Gomes et al.

LeTS-Drive enhances driving skills in crowded environments by learning from tree search.

Panpan Cai, Yuanfu Luo, Aseem Saxena et al.

Study the inductive bias of neural tangent kernels, analyzing smoothness and stability in convolutional networks.

Alberto Bietti, Julien Mairal

Proposes Patch-wise Adversarial Regularization (PAR) to improve CNN robustness by penalizing local predictive power, enhancing out-of-domain generalization.

Haohan Wang, Songwei Ge, Eric P. Xing et al.

Proposes a compound scaling method balancing depth, width, and resolution, achieving 84.3% top-1 accuracy on ImageNet with 8.4x fewer parameters.

Mingxing Tan, Quoc V. Le

Cross-lingual knowledge graph alignment using graph matching neural network, significantly improving accuracy.

Kun Xu, Liwei Wang, Mo Yu et al.

GraphNVP employs invertible normalizing flows for molecular graph generation, decomposing structure and attributes, achieving high validity and uniqueness with exact likelihood maximization.

Kaushalya Madhawa, Katushiko Ishiguro, Kosuke Nakago et al.