INF367A Recap Repo

How to use

1. Clone the repo.
2. Run ./picker.sh on linux and mac, picker.bat on windows. This displays a random paper.
3. To play the Card Game, navigate to card_game and run the following command: python3 -m http.server. The game can be played at localhost.

How to contribute

1. Fork the repo.
2. Copy the template and create your paper overview and put it in the papers/ folder. If you add images, put them in the figures folder.
3. Once you have made your changes, press contribute in your fork, and create a pull request to the main repo.

Papers Covered

DISCLAIMER: Some of the papers are summarized with an LLM. They are marked with a disclaimer. Feel free to replace it with your own summary, or modify it if it contains any mistakes.

• An improved random forest based on the classification accuracy and correlation measurement of decision trees: paper, summary, pdf
• Automating Privilege Escalation with Deep Reinforcement Learning: paper, summary, pdf
• Automatic Data Augmentation via Invariance Constrained Learning: paper, summary, pdf
• A Satellite Band Selection Framework: paper, summary, pdf
• Binary Classification: Is Boosting stronger than Bagging?: paper, summary, pdf
• DiffCR - A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images: paper, summary, pdf
• Differentiable Model Selection for Ensemble Learning: paper, summary, pdf
• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains: paper, summary, pdf
• From Data Imputation to Data Cleaning – Automated Cleaning of Tabular Data Improves Downstream Predictive Performance: paper, summary, pdf
• GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data: paper, summary, pdf
• High-Resolution Image Synthesis with Latent Diffusion Models: paper, summary, pdf
• Improving Domain Generalization with Interpolation Robustness: paper, summary, pdf
• Learning to Maximize Mutual Information for Dynamic Feature Selection: paper, summary, pdf
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces: paper, summary, pdf
• Multi-Robot Path Planning Combining Heuristics and Multi-Agent Reinforcement Learning: paper, summary, pdf
• Object-Based Augmentation Improves Quality of Remote Sensing Semantic Segmentation: paper, summary, pdf
• OpenFE: Automated Feature Generation with Expert-level Performance: paper, summary, pdf
• PseudoSeg: Designing Pseudo Labels for Semantic Segmentation: paper, summary, pdf
• R2U++: a multiscale recurrent residual U-Net with dense skip connections for medical image segmentation: paper, summary, pdf
• Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery: paper, summary, pdf
• SAM 2: Segment Anything in Images and Videos: paper, summary, pdf
• SatMAE: Pre-Training Transformers for Temporal and Multi-Spectral Satellite Imagery: paper, summary, pdf
• SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation: paper, summary, pdf
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks: paper, summary, pdf
• Segment-then-Classify: Few-shot instance segmentation for environmental remote sensing: paper, summary, pdf
• SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers: paper, summary, pdf
• Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network: paper, summary, pdf
• Surrogate uncertainty estimation for your time series forecasting black box: learn when to trust: paper, summary, pdf
• TabM: Advanced Tabular Deep Learning with Parameter-Efficient Ensembling: paper, summary, pdf
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation: paper, summary, pdf