Loading...
A comprehensive collection of influential research papers that have shaped my understanding of AI, machine learning, computer vision, and data science. These papers represent cutting-edge research and foundational work in their respective fields.
Authors: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
Published in: Computation and Language (NeurIPS)
The paper that introduced the Transformer architecture, revolutionizing natural language processing and becoming the foundation for modern large language models like GPT and BERT.
Authors: Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova
Published in: NAACL-HLT
Introduced BERT, a bidirectional encoder representation from transformers that significantly improved performance on various NLP tasks through pre-training on large text corpora.
Authors: Shuqi Li, Yuebo Sun, Yuxin Lin, Xin Gao, Shuo Shang, Rui Yan
Published in: Advances in Neural Information Processing Systems
Proposed a novel framework that integrates causal discovery with deep learning to predict stock movements based on news data, demonstrating improved performance over traditional methods.
Authors: Pan, Xiaokun & Li, Zhenzhe & Fan, Tianxing & Zhai, Hongjia & Bao, Hujun & Zhang, Guofeng
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduced a scalable visual SLAM system capable of handling multiple sessions in large-scale environments by employing subgraph optimization techniques, enhancing both accuracy and efficiency.
Authors: Carlos Campos, Richard Elvira, Juan J. Gómez Rodríguez, José M. M. Montiel, Juan D. Tardós
Published in: IEEE Transactions on Robotics
Presented ORB-SLAM3, an advanced SLAM system that supports visual, visual-inertial, and multi-map capabilities, achieving state-of-the-art performance in various benchmarks.
Authors: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
Published in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Introduced residual networks (ResNet) that enabled training of very deep neural networks by addressing the vanishing gradient problem through skip connections.
Authors: Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
Published in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Presented YOLO, a real-time object detection system that frames object detection as a single regression problem, achieving impressive speed and accuracy trade-offs.
Authors: Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio
Published in: Advances in Neural Information Processing Systems
Introduced GANs, a framework for training generative models through adversarial training, revolutionizing the field of generative AI and synthetic data creation.
This collection is regularly updated with new research papers that influence my work and thinking.