Latest Research
The Importance of Time in Causal Algorithmic Recourse
The application of Algorithmic Recourse in decision-making is a promising field that offers practical solutions to reverse unfavorable decisions.
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data.
Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges
There is growing interest in discovering interpretable, closed-form equations for subgrid-scale (SGS) closures/parameterizations of complex processes in Earth system.
Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian
divelab/AIRS
•
•
We consider the prediction of the Hamiltonian matrix, which finds use in quantum chemistry and condensed matter physics.
Scaling Spherical CNNs
google-research/spherical-cnn
•
•
Spherical CNNs generalize CNNs to functions on the sphere, by using spherical convolutions as the main linear operation.
Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean
We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire modeling in the Mediterranean.
Learned spatial data partitioning
onizukalab/spatial-data-partitioning-using-drl
•
•
Due to the significant increase in the size of spatial data, it is essential to use distributed parallel processing systems to efficiently analyze spatial data.
Multi-level Multiple Instance Learning with Transformer for Whole Slide Image Classification
The combination of both should provide new insights for deep learning based image diagnosis.
Layer-level activation mechanism
In this work, we propose a novel activation mechanism aimed at establishing layer-level activation (LayerAct) functions.
ReliableSwap: Boosting General Face Swapping Via Reliable Supervision
To avoid the potential artifacts and drive the distribution of the network output close to the natural one, we reversely take synthetic images as input while the real face as reliable supervision during the training stage of face swapping.
