AutoAttack combines Auto-PGD, FAB, Square Attack for parameter-free, automated robustness evaluation, revealing vulnerabilities missed by prior methods.

Francesco Croce, Matthias Hein

Proposed IF-Nets use multi-scale deep feature tensors for continuous, multi-topology 3D shape reconstruction, outperforming prior methods in detail preservation and articulated human modeling.

Julian Chibane, Thiemo Alldieck, Gerard Pons-Moll

Proposed CASTER method enhances meta-reinforcement learning efficiency, reducing sample requirements.

Haozhe Wang, Jiale Zhou, Xuming He

Using MAP-Elites and CPPNs, EGAD generates 2000+ diverse objects for robotic grasp evaluation.

Douglas Morrison, Peter Corke, Jürgen Leitner

Learn2Perturb enhances adversarial robustness through end-to-end feature perturbation learning, achieving 4-7% improvement on CIFAR-10.

Ahmadreza Jeddi, Mohammad Javad Shafiee, Michelle Karg et al.

Proposes a decoder-free predictive coding approach for locally-linear control, improving high-dimensional observation control by maximizing latent mutual information.

Rui Shu, Tung Nguyen, Yinlam Chow et al.

Proposed a modular benchmarking framework for GNNs with diverse datasets and Laplace positional encoding, advancing model evaluation.

Vijay Prakash Dwivedi, Chaitanya K. Joshi, Anh Tuan Luu et al.

SAT combines state-aware feedback for real-time VOS, reaching 72.3% J&F and 39 FPS on DAVIS2017-Val.

Xi Chen, Zuoxin Li, Ye Yuan et al.

Cops-Ref dataset introduces complex logical reasoning for referring expression comprehension; current models perform poorly, highlighting room for improvement.

Zhenfang Chen, Peng Wang, Lin Ma et al.

Navigation2 employs behavior trees on ROS2, achieving 37.4 miles of collision-free autonomous campus navigation in dynamic environments.

Steve Macenski, Francisco Martín, Ruffin White et al.

Training only BatchNorm γ/β yields 82% on CIFAR-10 and 32% top-5 on ImageNet in deep ResNets.

Jonathan Frankle, David J. Schwab, Ari S. Morcos

AraBERT, a Transformer-based Arabic language model, achieves state-of-the-art results on multiple NLP tasks, surpassing multilingual BERT significantly.

Wissam Antoun, Fady Baly, Hazem Hajj

Proposes GP-MRO algorithm combining Gaussian processes and online learning to optimize robust mixed strategies, enhancing autonomous vehicle trajectory planning.

Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour et al.

Proposes a knowledge distillation framework with outlier rejection and multi-task learning to improve regression accuracy under noisy labels.

Makoto Takamoto, Yusuke Morishita, Hitoshi Imaoka

Proposes a fast, robust VOS method combining a Gauss-Newton optimized target model with a U-Net segmentation network, achieving 41 FPS and state-of-the-art accuracy.

Andreas Robinson, Felix Järemo Lawin, Martin Danelljan et al.

Learning ensemble-based cost models with resource-aware optimization improves accuracy by 2-3 orders of magnitude, achieving high correlation and plan improvements.

Tarique Siddiqui, Alekh Jindal, Shi Qiao et al.

This paper systematically reviews BERT's internal mechanisms, analyzing its encoding of syntax, semantics, and world knowledge, and discusses model improvements and compression.

Anna Rogers, Olga Kovaleva, Anna Rumshisky

Defense-PointNet employs a discriminator to enhance PointNet's robustness against FGSM adversarial point clouds, outperforming baseline defenses with 96.35% accuracy.

Yu Zhang, Gongbo Liang, Tawfiq Salem et al.

Proposed generalized ODIN achieves high OoD detection without out-of-distribution data tuning, via confidence decomposition and input preprocessing.

Yen-Chang Hsu, Yilin Shen, Hongxia Jin et al.

Sparse Sinkhorn Attention employs differentiable sorting for efficient attention, significantly reducing memory usage.

Yi Tay, Dara Bahri, Liu Yang et al.