Introduced global and local attention mechanisms, improving English-German translation by 5.0 BLEU points.

Minh-Thang Luong, Hieu Pham, Christopher D. Manning

Introduces two-way pAUC for direct TPR/FPR control, improving ROC performance evaluation.

Hanfang Yang, Kun Lu, Xiang Lyu et al.

Hamiltonian variational approach accelerates quantum state preparation, achieving high accuracy in Hubbard models with fewer parameters.

D. Wecker, M. B. Hastings, M. Troyer

Dynamic Matrix Factorization with Priors improves sparse recommendation, reaching 0.9276 AUC on AmazonMovies.

Robin Devooght, Nicolas Kourtellis, Amin Mantrach

Introduces LogDet-based non-convex rank approximation for subspace clustering, outperforming nuclear norm methods with improved accuracy and robustness.

Zhao Kang, Chong Peng, Jie Cheng et al.

Virtual Adversarial Training (VAT) outperforms most methods on the MNIST dataset.

Takeru Miyato, Shin-ichi Maeda, Masanori Koyama et al.

Proposed a quadratic droop control method for microgrid voltage stabilization and reactive power optimization.

John W. Simpson-Porco, Florian Dorfler, Francesco Bullo

Proposes an unsupervised multimodal approach combining video and narration, achieving 85% accuracy in key task step detection on a new dataset.

Jean-Baptiste Alayrac, Piotr Bojanowski, Nishant Agrawal et al.

Proposes a deep neural framework combining unsupervised sentence embeddings and video-text models for aligning books and movies, achieving over 70% accuracy.

Yukun Zhu, Ryan Kiros, Richard Zemel et al.

Deep visualization tools reveal computations in intermediate layers of convolutional neural networks.

Jason Yosinski, Jeff Clune, Anh Nguyen et al.

Proposes a Wasserstein distance-based loss for multi-label learning, utilizing entropic regularization for efficient approximation, enhancing semantic smoothness.

Charlie Frogner, Chiyuan Zhang, Hossein Mobahi et al.

Proposes spectral networks with graph estimation for non-Euclidean data, matching or surpassing Dropout networks with fewer parameters.

Mikael Henaff, Joan Bruna, Yann LeCun

Proposes a graph-based visual relationship model using large-scale Amazon data for clothing and accessory recommendations.

Julian McAuley, Christopher Targett, Qinfeng Shi et al.

Proposes a unified randomized iterative framework for linear systems, encompassing known algorithms like Kaczmarz and coordinate descent, with exponential convergence guarantees.

Robert M. Gower, Peter Richtárik

Permutation search is effective, but PP-Index/MI-file are not always faster than direct search.

Bilegsaikhan Naidan, Leonid Boytsov, Eric Nyberg

Pointer Networks leverage attention as pointers, enabling variable-length input-output mapping, successfully applied to convex hull, Delaunay triangulation, and TSP.

Oriol Vinyals, Meire Fortunato, Navdeep Jaitly

Proposed a connection importance learning-based pruning method; reduced AlexNet parameters by 9× and VGG-16 by 13× without accuracy loss.

Song Han, Jeff Pool, John Tran et al.

Path-SGD optimizes deep neural networks using path normalization, improving performance on datasets like MNIST.

Behnam Neyshabur, Ruslan Salakhutdinov, Nathan Srebro

Compositional training for TransE and bilinear models cuts path-query error by up to 76.2% and improves KBC.

Kelvin Guu, John Miller, Percy Liang

Proposes a hybrid deep learning and rule-based approach for text-to-3D scene generation, achieving significant improvements in scene fidelity and diversity, with a new dataset and evaluation metrics.

Angel Chang, Will Monroe, Manolis Savva et al.