91 citations · 107 across the 6 of their papers we have counts for
3 papers · 1 filter
Concept Bottleneck Models Without Predefined Concepts
Simon Schrodi, Julian Schur, Max Argus +1
There has been considerable recent interest in interpretable concept-based models such as Concept Bottleneck Models (CBMs), which first predict human-interpretable concepts and the…
Latent Diffusion Counterfactual Explanations
Karim Farid, Simon Schrodi, Max Argus +1
Counterfactual explanations have emerged as a promising method for elucidating the behavior of opaque black-box models. Recently, several works leveraged pixel-space diffusion mode…
Loss is its own Reward: Self-Supervision for Reinforcement Learning
Evan Shelhamer, Parsa Mahmoudieh, Max Argus +1
Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and…