Introduces SimLex-999, a gold standard for semantic similarity, covering multiple POS and abstract/concrete concepts, outperforming WordSim-353 and MEN.

Felix Hill, Roi Reichart, Anna Korhonen

Framework for statistical guarantees of EM and gradient EM, combining population and finite-sample analysis.

Sivaraman Balakrishnan, Martin J. Wainwright, Bin Yu

The paper proposes Bandit algorithms for tree search, improving the over-optimism issue of the UCT algorithm.

Pierre-Arnuad Coquelin, Remi Munos

EAGLE employs a novel thermal feedback model calibrated to match the z≈0 galaxy stellar mass function with 0.2dex accuracy, enabling realistic galaxy formation simulations.

Joop Schaye, Robert A. Crain, Richard G. Bower et al.

Introduces 'Intelligent Trial and Error' algorithm enabling robots to adapt within 2 minutes post-damage, mimicking animal repair behaviors.

Antoine Cully, Jeff Clune, Danesh Tarapore et al.

Motility-induced phase separation (MIPS) arises from the coupling between particle speed and local density, revealing a non-equilibrium phase behavior in active matter.

Michael E. Cates, Julien Tailleur

Introduces Predictive Entropy Search (PES) for efficient black-box function optimization.

José Miguel Hernández-Lobato, Matthew W. Hoffman, Zoubin Ghahramani

clingo 4 integrates ASP with scripting control, enabling complex, dynamic reasoning processes.

Martin Gebser, Roland Kaminski, Benjamin Kaufmann et al.

MS COCO dataset with 91 categories, 2.5 million instances, enhances scene understanding and precise localization.

Tsung-Yi Lin, Michael Maire, Serge Belongie et al.

Proposes a hybrid data-model parallel training method for CNNs, achieving over 6x speedup on 8 GPUs with minimal accuracy loss.

Alex Krizhevsky

Exploiting linear filter structures with low-rank SVD and clustering speeds up CNN evaluation 2-3×, with <1% accuracy loss.

Remi Denton, Wojciech Zaremba, Joan Bruna et al.

Proposed a distributed OPF algorithm using ADMM and SOCP relaxation, achieving 0.6s convergence on a 2,065-bus network.

Qiuyu Peng, Steven H. Low

Proposes multi-sentence, multi-level video description framework using semantic representations and visual recognition, improving coherence and detail control.

Anna Senina, Marcus Rohrbach, Wei Qiu et al.

Using pretrained OverFeat features with linear SVM achieves state-of-the-art results across multiple vision tasks without fine-tuning.

Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan et al.

Introduces multi-scale invertible orientation scores for vessel enhancement, significantly improving crossing and bifurcation detection in retinal images.

Julius Hannink, Remco Duits, Erik Bekkers

Proposes zero-bias autoencoders with decoupled activation functions, enabling high-dimensional data representation without extra regularization, improving recognition accuracy.

Kishore Konda, Roland Memisevic, David Krueger

Nested Dropout enforces ordered representations, ensuring unit identifiability, equivalent to PCA, enabling fast large-scale retrieval and adaptive compression.

Oren Rippel, Michael A. Gelbart, Ryan P. Adams

This survey introduces a taxonomy for multi-objective sequential decision-making, classifying algorithms based on scenarios, scalarization functions, and policy types.

Diederik Marijn Roijers, Peter Vamplew, Shimon Whiteson et al.

NEXUS+ on Millennium/MS-II shows clusters and filaments dominate mass, with >100 h^-1Mpc straight filaments.

Marius Cautun, Rien van de Weygaert, Bernard J. T. Jones et al.

Applying MCTS and MCCFR to approximate Nash equilibria in Poker, combined with RNR for robust responses, achieves faster learning and higher exploitability.

Marc Ponsen, Steven de Jong, Marc Lanctot