A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Yaoming Li, Guangxiang Zhao, Qilong Shi, et al.
First primer synthesizing over 150 studies on post-training reasoning data, organizing the field around four key questions.
Veronica Salmaso, Stefano Moro
This paper reviews the evolution of structure-based drug discovery from static molecular docking to enhanced molecular dynamics simulations for studying ligand-protein recognition.
Kai Olav Ellefsen, Jean-Baptiste Mouret, Jeff Clune
This paper shows that evolving modular neural networks with connection costs reduces catastrophic forgetting, enabling faster learning of new skills while retaining old ones.
Jessica Fridrich, Jan Kodovský
This paper introduces a novel strategy for building steganalysis detectors by assembling a rich model of noise residuals and using ensemble classifiers, achieving high detection accuracy against spatial-domain steganography.
Vincent Le Guilloux, Peter Schmidtke, Pierre Tufféry
Fpocket is an open-source platform for protein pocket detection using Voronoi tessellation and alpha spheres, achieving high accuracy and speed.
Leonardo L. G. Ferreira, Ricardo Nascimento dos Santos, Glaucius Oliva, et al.
This review examines molecular docking strategies in drug discovery, highlighting the integration of structure- and ligand-based methods and the importance of understanding each algorithm's strengths and limitations.
Frank F. Rosenblatt
This paper introduces the perceptron, a probabilistic model for information storage and organization in the brain, laying the foundation for neural network theory.
Lin Long, Rui Wang, Rui Xiao, et al.
This paper organizes LLM-driven synthetic data generation studies into a unified workflow, highlighting gaps and future research directions.
Unknown
ERNIE-Layout enhances document understanding by reorganizing tokens using layout knowledge and applying spatial-aware disentangled attention in a multi-modal transformer.
Unknown
Phi-4 is a 14B language model that achieves strong reasoning performance, especially in STEM, by prioritizing data quality through synthetic data, curated organic seeds, and innovative post-training techniques.
Guanglei Ding, Yitong Liu, Rui Zhang, et al.
A joint deep learning model using GANs to inpaint missing-wedge sinograms and reduce artifacts in electron tomography, outperforming traditional methods even at 45° missing wedge.
Matthew R. Masters, Amr H. Mahmoud, Markus A. Lill
This paper reveals that deep learning co-folding models for protein-ligand structure prediction often violate fundamental physical principles, indicating overfitting rather than learning true physics.