Europe
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
Easily integrated, FamO2O statistically enhances existing algorithms' performance.
A Spectral Theory of Neural Prediction and Alignment
We investigated DNNs as encoding models of visual areas V1, V2, V4, and IT. We examined 32 visual deep neural networks.
Queueing Matching Bandits with Preference Feedback
In these systems, there are two sides: queues (agents) on one side and servers (arms) on the other.
Adversarial Examples Might be A voidable: The Role of Data Concentration in Adversarial Robustness
However, these results can be too general to be applicable to natural data distributions. Indeed, humans are quite robust for tasks involving vision.
Reinforcement Learning with Lookahead Information
In reinforcement learning (RL), agents sequentially interact with a changing environment, aiming to collect as much reward as possible.
Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark
We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.