Country
9f42f06a54ce3b709ad78d34c73e4363-Paper-Conference.pdf
Therefore, neuro-symbolic RL aims at creating policies that are interpretable in the first place. Unfortunately, interpretability is not explainability. To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE).
Continual Learning with Global Alignment
Specifically, we learn the data representation as a task-specific composition of pre-trained token representations shared across all tasks. Then the correlations between different tasks' data representations are grounded
Large Language Model for Hundreds of Vision-Language Tasks
To this end, we propose a new information transmission mechanism termed "super
Understanding Visual Feature Reliance through the Lens of Complexity Thomas Fel Google DeepMind Brown University Louis Béthune
Recent studies suggest that deep learning models' inductive bias towards favoring
Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models
We present a novel approach for explaining Gaussian processes (GPs) that can utilize the full analytical covariance structure present in GPs.
ExploringthePreciseDynamicsofSingle-LayerGAN Models: LeveragingMulti-FeatureDiscriminatorsfor High-DimensionalSubspaceLearning
Subspace learning is acritical endeavor in contemporary machine learning, particularly given the vast dimensions of modern datasets.
DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
Current perceptual similarity metrics operate at the level of pixels and patches.