SURGE integrates interest graphs with GNNs to model long sequences, boosting recommendation accuracy by 12-15%.

Jianxin Chang, Chen Gao, Yu Zheng et al.

Proposed a post-training quantization algorithm for vision transformers, achieving 81.29% top-1 accuracy on ImageNet with DeiT-B model.

Zhenhua Liu, Yunhe Wang, Kai Han et al.

Unified EVLP taxonomy, analyzing algorithms, datasets, and challenges; emphasizing model generalization and real-world deployment.

Jonathan Francis, Nariaki Kitamura, Felix Labelle et al.

Proposes Adapt-and-Distill, combining vocabulary expansion and knowledge distillation to develop small, efficient domain-specific models outperforming BERT BASE.

Yunzhi Yao, Shaohan Huang, Wenhui Wang et al.

Video Swin Transformer uses local spatiotemporal attention, achieving 84.9% top-1 accuracy on Kinetics-400 with 28.2M parameters, outperforming global attention models.

Ze Liu, Jia Ning, Yue Cao et al.

Combines null-space and direct elimination methods with sparse-dense transformation to efficiently solve large-scale constrained least squares problems, ensuring small residuals.

Jennifer Scott, Miroslav Tuma

Proposes CW networks with cell complexes, surpassing WL test, for enhanced graph expressivity, especially in molecular graphs.

Cristian Bodnar, Fabrizio Frasca, Nina Otter et al.

Proposed C2F-ARM algorithm uses coarse-to-fine Q-attention for efficient visual robotic manipulation, requiring only 3 demonstrations for training.

Stephen James, Kentaro Wada, Tristan Laidlow et al.

Adaptive embedding in kernel and neural bandits achieves sample complexity depending only on effective dimension.

Yinglun Zhu, Dongruo Zhou, Ruoxi Jiang et al.

KaggleDBQA leverages real-world databases and documentation, boosting Text-to-SQL accuracy by over 13.2% in practical settings.

Chia-Hsuan Lee, Oleksandr Polozov, Matthew Richardson

This survey reviews 3D object detection methods for autonomous driving, emphasizing multi-modal fusion, datasets, and recent advances, with PV-RCNN achieving 82.86% mAP on KITTI.

Rui Qian, Xin Lai, Xirong Li

NeuS introduces a bias-free volume rendering approach combined with neural signed distance functions (SDF) for high-fidelity multi-view surface reconstruction, outperforming IDR and NeRF.

Peng Wang, Lingjie Liu, Yuan Liu et al.

PALMS uses small curated datasets to steer large language models toward societal values, reducing bias and toxicity effectively.

Irene Solaiman, Christy Dennison

LoRA introduces low-rank matrices to freeze pre-trained weights, reducing trainable parameters by 10,000x, with performance comparable or better than full fine-tuning.

Edward J. Hu, Yelong Shen, Phillip Wallis et al.

Proposes a realistic threat model for adversarial attacks on ML-based NIDS, analyzing attacker capabilities and constraints.

Giovanni Apruzzese, Mauro Andreolini, Luca Ferretti et al.

The paper introduces the Optimum-statistical Collaboration framework and VHCT algorithm for efficient black-box optimization.

Wenjie Li, Chi-Hua Wang, Guang Cheng et al.

This survey comprehensively reviews techniques for making deep learning models smaller, faster, and more efficient, including pruning, quantization, architecture search, and hardware support.

Gaurav Menghani

Proposes algorithms Exp3-IP and Exp3-GR for online learning with uncertain feedback graphs, achieving sublinear regret bounds under mild conditions.

Pouya M Ghari, Yanning Shen

Sequence-level training for NAT using reinforcement algorithms and BoN loss, achieving 3-4 BLEU points improvement on WMT tasks.

Chenze Shao, Yang Feng, Jinchao Zhang et al.

This paper reviews the evolution of pre-trained models (PTMs), focusing on architectures like BERT and GPT, highlighting their transformative impact on AI.

Xu Han, Zhengyan Zhang, Ning Ding et al.