RSN solves Newton systems in random subspaces and usually outpaces GD, AGD, and full Newton across six datasets.

Robert M. Gower, Dmitry Kovalev, Felix Lieder et al.

Proposes an efficient Weingarten map estimator with proven asymptotic convergence rate, applied to curvature estimation and point cloud simplification.

Yueqi Cao, Didong Li, Huafei Sun et al.

Sherlock employs a multi-input deep neural network trained on 686,765 columns to detect 78 semantic types, achieving an F1 score of 0.89.

Madelon Hulsebos, Kevin Hu, Michiel Bakker et al.

This study reveals that many attention heads in multi-head attention are redundant; introduces gradient-based greedy pruning to improve efficiency.

Paul Michel, Omer Levy, Graham Neubig

Variational Autoencoder-based 6-DOF grasp generation achieves 88% success, enabling seamless simulation-to-real transfer.

Arsalan Mousavian, Clemens Eppner, Dieter Fox

Proves three-layer ResNet can efficiently learn certain functions beyond kernels in a distribution-free setting, with lower sample and computational complexity.

Zeyuan Allen-Zhu, Yuanzhi Li

Introduced CPNGNNs, the first to analyze GNN approximation ratios for combinatorial problems, improving theoretical bounds for dominating set and vertex cover.

Ryoma Sato, Makoto Yamada, Hisashi Kashima

winPIBT extends PIBT with configurable multi-step planning, improving path efficiency and deadlock avoidance in multi-agent systems.

Keisuke Okumura, Yasumasa Tamura, Xavier Défago

Proposes a batch black-box optimization method with deterministic regret bounds based on frequentist kernel techniques, improving efficiency and robustness.

Yueming Lyu, Yuan Yuan, Ivor W. Tsang

A subexpression-sharing GNN reaches 49.95% proof closure on HOList.

Aditya Paliwal, Sarah Loos, Markus Rabe et al.

MR-GNN enhances structured entity interaction prediction using multi-resolution and dual graph-state LSTM.

Nuo Xu, Pinghui Wang, Long Chen et al.

Graph neural networks perform low-pass filtering, lacking nonlinear manifold learning.

Hoang NT, Takanori Maehara

LRP and Hard Concrete pruning show that retaining 10 of 48 encoder heads cuts WMT En–Ru BLEU by only 0.15.

Elena Voita, David Talbot, Fedor Moiseev et al.

Block Gaussian Kaczmarz algorithm achieves exponential convergence; effective in noise reduction and variance control.

Deanna Needell, Elizaveta Rebrova

Introduces CoqGym dataset and ASTactic model, enabling flexible proof strategy generation via abstract syntax trees for automated theorem proving.

Kaiyu Yang, Jia Deng

Cluster-GCN leverages graph clustering to enable efficient deep GCN training on large graphs, reducing memory and computation significantly.

Wei-Lin Chiang, Xuanqing Liu, Si Si et al.

HellaSwag dataset leverages adversarial filtering to challenge state-of-the-art models, exposing their limitations in commonsense reasoning with only ~48% accuracy versus 95% humans.

Rowan Zellers, Ari Holtzman, Yonatan Bisk et al.

Proposes a DPP-based framework for generating diverse, feasible counterfactual explanations, outperforming prior methods on four datasets.

Ramaravind Kommiya Mothilal, Amit Sharma, Chenhao Tan

Multi-hop reading comprehension via reasoning over heterogeneous graphs, achieving state-of-the-art on WIKIHOP dataset.

Ming Tu, Guangtao Wang, Jing Huang et al.

Using Graph Neural Networks to encode database schema structure, improving Text-to-SQL parsing accuracy to 39.4%.

Ben Bogin, Matt Gardner, Jonathan Berant