54 citations · 68 across the 4 of their papers we have counts for
4 papers
Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search
Wenqing Zheng, S P Sharan, Zhiwen Fan +3
Learning efficient and interpretable policies has been a challenging task in reinforcement learning (RL), particularly in the visual RL setting with complex scenes. While neural ne…
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Kevin Wang, Alexandre Variengien, Arthur Conmy +2
Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components. However, most previous work either focuses on…
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Mor Geva, Avi Caciularu, Kevin Ro Wang +1
Transformer-based language models (LMs) are at the core of modern NLP, but their internal prediction construction process is opaque and largely not understood. In this work, we mak…
Video-Specific Autoencoders for Exploring, Editing and Transmitting Videos
Kevin Wang, Deva Ramanan, Aayush Bansal
We study video-specific autoencoders that allow a human user to explore, edit, and efficiently transmit videos. Prior work has independently looked at these problems (and sub-probl…