A DQN-based MODRL framework supports single/multi-policy and linear/nonlinear selection, recovering Pareto solutions on two benchmark tasks.

Thanh Thi Nguyen, Ngoc Duy Nguyen, Peter Vamplew et al.

Using fastText model to analyze annotation artifacts in NLI datasets, finding 67% of SNLI and 53% of MultiNLI data can be classified by hypothesis alone.

Suchin Gururangan, Swabha Swayamdipta, Omer Levy et al.

Introduces relative position representations into self-attention, improving machine translation BLEU scores by 1.3 and 0.3, replacing absolute encodings.

Peter Shaw, Jakob Uszkoreit, Ashish Vaswani

EGES integrates side information and reaches 0.9746 Taobao AUC, a 10.8% gain over BGE.

Jizhe Wang, Pipei Huang, Huan Zhao et al.

Proposes NO TEARS, a continuous optimization framework for DAG structure learning using matrix exponential-based smooth constraints, outperforming traditional combinatorial methods.

Xun Zheng, Bryon Aragam, Pradeep Ravikumar et al.

Quantum Circuit Learning combines classical and quantum computing to approximate nonlinear functions.

Kosuke Mitarai, Makoto Negoro, Masahiro Kitagawa et al.

Efficient numerical methods for optimal transport enable scalable high-dimensional distribution matching, benefiting image processing and machine learning.

Gabriel Peyré, Marco Cuturi

LCR-Net++ integrates multi-scale pose proposals, classification, and regression for multi-person 2D/3D pose estimation, outperforming state-of-the-art methods.

Gregory Rogez, Philippe Weinzaepfel, Cordelia Schmid

Proposed Fast Geometric Ensembling (FGE) improves accuracy by 0.56% on CIFAR-10.

Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin et al.

TD3 algorithm employs twin critics with minimum value selection, delayed policy updates, and target smoothing, reducing overestimation bias in continuous control tasks, outperforming DDPG.

Scott Fujimoto, Herke van Hoof, David Meger

Proposes Workflow-Guided Exploration (WGE) with DOMNET for web tasks, achieving 100x sample efficiency and high success rates with minimal demonstrations.

Evan Zheran Liu, Kelvin Guu, Panupong Pasupat et al.

Using input-output Jacobian norm as a sensitivity metric, the study finds strong correlation with neural network generalization across architectures and datasets.

Roman Novak, Yasaman Bahri, Daniel A. Abolafia et al.

PDDLStream integrates symbolic planners with black-box samplers via adaptive optimistic planning, significantly improving efficiency in high-dimensional robotic tasks.

Caelan Reed Garrett, Tomás Lozano-Pérez, Leslie Pack Kaelbling

Introduces tensor field neural networks with SO(3) equivariance for 3D point clouds, using spherical harmonic filters, achieving rotation, translation, and permutation invariance.

Nathaniel Thomas, Tess Smidt, Steven Kearnes et al.

Glimpse Clouds method uses visual attention for activity recognition without pose data, improving accuracy on NTU RGB+D dataset.

Fabien Baradel, Christian Wolf, Julien Mille et al.

Proposed new preference elicitation strategies based on ranking and clustering to enhance multi-objective decision support.

Luisa M Zintgraf, Diederik M Roijers, Sjoerd Linders et al.

Introduces Oblivious-Greedy for non-submodular maximization under element removal, achieving constant-factor approximation for support selection and variance reduction.

Ilija Bogunovic, Junyao Zhao, Volkan Cevher

Shield combines JPEG compression, vaccination, ensembling, and randomization to block 94% black-box and 98% gray-box attacks, enabling fast, practical defense.

Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen et al.

Proposes VAEP framework using probabilistic models to quantify player actions' impact in soccer.

Tom Decroos, Lotte Bransen, Jan Van Haaren et al.

FactorVAE improves disentanglement over β-VAE by encouraging factorial representation distribution.

Hyunjik Kim, Andriy Mnih