Loading...
Curated index of papers used as reference points for architectures, algorithms, and evaluation methods in AI, vision, and data systems.
Authors: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
Published in: Computation and Language (NeurIPS)
Introduces the Transformer architecture, using self-attention in place of recurrence to improve parallelism and sequence modeling.
Authors: Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova
Published in: NAACL-HLT
Introduces BERT, a bidirectional Transformer encoder pre-trained on large corpora and fine-tuned for downstream NLP tasks.
Authors: Shuqi Li, Yuebo Sun, Yuxin Lin, Xin Gao, Shuo Shang, Rui Yan
Published in: Advances in Neural Information Processing Systems
Combines deep learning with causal discovery to model how news signals drive stock movements in an end-to-end framework.
Authors: Pan, Xiaokun & Li, Zhenzhe & Fan, Tianxing & Zhai, Hongjia & Bao, Hujun & Zhang, Guofeng
Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence
Proposes a multi-session visual SLAM pipeline that uses subgraph optimization to maintain accuracy and scalability in large environments.
Authors: Carlos Campos, Richard Elvira, Juan J. Gómez Rodríguez, José M. M. Montiel, Juan D. Tardós
Published in: IEEE Transactions on Robotics
Extends ORB-SLAM to a unified system handling visual, visual–inertial, and multi-map SLAM with improved robustness across scenarios.
Authors: Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
Published in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Proposes residual networks with skip connections, enabling stable training of very deep convolutional architectures.
Authors: Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi
Published in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Frames object detection as a single-stage regression problem, yielding real-time detection with competitive accuracy.
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
Introduces GANs, training a generator and discriminator in an adversarial game to learn high-fidelity data distributions.
Papers are included when they define architectures, objective functions, or evaluation setups that I reuse as baselines or design templates.
I treat these works as working references: they are revisited when designing experiments, reading ablations, or debugging why a model or system underperforms.