A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Md Toufikuzzaman, Md Abul Hassan Samee, M Sohel Rahman
CRISPR-DIPOFF is an interpretable deep learning approach for CRISPR Cas-9 off-target prediction that improves precision-recall balance and reveals two sub-regions in the seed region of sgRNA.
Jos'ephine Raugel, Marc Szafraniec, Huy V. Vo, et al.
This paper systematically varies model size, training amount, and image type in DINOv3 vision transformers to disentangle how these factors independently and interactively drive brain-like representations, revealing a developmental chronology aligned
Plamen Angelov, Dimitar Filev
This paper introduces the Evolving Takagi-Sugeno (ETS) model, a recursive learning algorithm that dynamically updates fuzzy rule structure and parameters for online system identification.
Richard S. Sutton
This paper presents positive results for all control tasks previously reported as failures by Boyan and Moore, using sparse-coarse-coded function approximators (CMACs) and online learning.
Mohammad Sadegh Norouzzadeh, Anh‐Tu Nguyen, Margaret Kosmala, et al.
This paper demonstrates that deep convolutional neural networks can automatically identify, count, and describe behaviors of 48 animal species in camera-trap images, achieving human-level accuracy and saving years of manual labeling effort.
Tzu‐Mao Li, Michaël Gharbi, Andrew Adams, et al.
This paper extends the Halide image processing language with reverse-mode automatic differentiation and automatic scheduling, enabling high-performance gradient computation for arbitrary programs.
M. Greenwell Brandon
This paper introduces pdp, an R package for constructing partial dependence plots to explain black-box machine learning models.
Aldo Pareja, Giacomo Domeniconi, Jie Chen, et al.
EvolveGCN adapts GCN parameters over time using an RNN to handle dynamic graphs without relying on node embeddings.
Justus Thies, Michael Zollhöfer, Matthias Nießner
Introduces Deferred Neural Rendering with Neural Textures, combining traditional graphics pipelines with learnable components to synthesize photo-realistic images from imperfect 3D content.
Benjamin Belay
This paper demonstrates that generated text can carry detectable evidence of causally relevant internal states, even when the answer is unchanged, in controlled feed-forward and transformer architectures.
Yin Dai, Yifan Gao, Fayu Liu
TransMed combines CNN and transformer architectures for multi-modal medical image classification, achieving significant accuracy improvements on parotid gland and knee injury datasets.
Yipeng Hu, Marc Modat, Eli Gibson, et al.
This paper introduces a weakly-supervised CNN approach for multimodal image registration that learns voxel-level transformations from anatomical labels, enabling real-time, fully-automated inference without labels.