Ensemble grammar induction for anomaly detection improves robustness by combining multiple parameter results, achieving near state-of-the-art performance with linear complexity.

Yifeng Gao, Jessica Lin, Constantin Brif

This paper introduces a self-supervised framework embedding a differentiable point-based motion estimator to learn robust radar keypoints, reducing odometry errors by 45% and increasing speed tenfold.

Dan Barnes, Ingmar Posner

Enhanced Virtual KITTI 2 with Unity HDRP, stereo camera, and weather variations; validated with deep learning models showing high transferability.

Yohann Cabon, Naila Murray, Martin Humenberger

Combines VAE and deep SVDD with ICAD for real-time out-of-distribution detection in CPS.

Feiyang Cai, Xenofon Koutsoukos

Proposes MM-SADA, combining multi-modal self-supervision and adversarial training, improving cross-domain fine-grained action recognition by 4.8%.

Jonathan Munro, Dima Damen

OURS adapts NetVLAD to polar radar, achieving F1=0.69 under random rotation versus 0.23 for VGG-16/NetVLAD.

Ştefan Săftescu, Matthew Gadd, Daniele De Martini et al.

This study formulates power-law scaling laws for neural language models, linking model size, data, and compute to performance, guiding efficient training strategies.

Jared Kaplan, Sam McCandlish, Tom Henighan et al.

Proposes mBART, a multilingual Seq2Seq denoising pretraining, boosting low-resource MT BLEU by up to 12 points, with broad transfer capabilities.

Yinhan Liu, Jiatao Gu, Naman Goyal et al.

FixMatch combines consistency regularization and pseudo-labeling, achieving 94.93% accuracy on CIFAR-10 with 250 labels.

Kihyuk Sohn, David Berthelot, Chun-Liang Li et al.

Hierarchical predictor-corrector framework with differentiable PDE solver enables long-term control of nonlinear PDE systems like Navier-Stokes.

Philipp Holl, Vladlen Koltun, Nils Thuerey

PLR-OSNet combines global and part-level features with a single ID loss, achieving 88.9% mAP and 95.6% Rank-1 on Market1501 with only 3.4M parameters.

Ben Xie, Xiaofu Wu, Suofei Zhang et al.

Proposes a discrete state-space active inference model using variational Bayesian inference, unifying perception, action, and learning.

Lancelot Da Costa, Thomas Parr, Noor Sajid et al.

DiffNet++ integrates social influence and interest diffusion on heterogeneous graphs, significantly improving social recommendation accuracy by modeling higher-order relations.

Le Wu, Junwei Li, Peijie Sun et al.

Reformer combines reversible residual layers and locality-sensitive hashing (LSH) attention, reducing complexity from O(L^2) to O(L log L) for long sequences.

Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya

RSL-Net uses radar and satellite imagery to achieve vehicle localization without prior maps, with mean angular error ~3°, translation ~3m.

Tim Y. Tang, Daniele De Martini, Dan Barnes et al.

This paper establishes near-optimal approximation bounds for deep ReLU networks approximating smooth functions, with errors of O(N^{-2s/d}L^{-2s/d}) when width and depth are optimized.

Jianfeng Lu, Zuowei Shen, Haizhao Yang et al.

DeeperForensics-1.0 is a large-scale face forgery dataset with 60,000 videos, 10x larger than existing datasets, built using a novel DF-VAE framework to enhance realism and diversity.

Liming Jiang, Ren Li, Wayne Wu et al.

SPACE combines spatial attention and scene mixture, enabling scalable unsupervised multi-object scene representation with explicit object and background factors.

Zhixuan Lin, Yi-Fu Wu, Skand Vishwanath Peri et al.

Proposes hybrid reinforcement learning (Hybrid RL) based on MPO to efficiently handle discrete and continuous actions simultaneously, improving robotic control.

Michael Neunert, Abbas Abdolmaleki, Markus Wulfmeier et al.

Proposes a Temporal-Spatial Neural Filter combining directional cues for end-to-end multi-channel speech separation, outperforming SOTA with fewer parameters.

Rongzhi Gu, Yuexian Zou