7 papers
Pitfalls in Evaluating Interpretability Agents
Tal Haklay, Nikhil Prakash, Sana Pandey +5
Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverag…
Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
Christy Li, Josep Lopez Camuñas, Jake Thomas Touchet +4
When a vision model performs image recognition, which visual attributes drive its predictions? Detecting unintended reliance on specific visual features is critical for ensuring mo…
LoRA vs Full Fine-tuning: An Illusion of Equivalence
Reece Shuttleworth, Jacob Andreas, Antonio Torralba +1
Fine-tuning is a crucial paradigm for adapting pre-trained large language models to downstream tasks. Recently, methods like Low-Rank Adaptation (LoRA) have been shown to effective…
Opt-In Art: Learning Art Styles Only from Few Examples
Hui Ren, Joanna Materzynska, Rohit Gandikota +2
We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investigate this, we train a text-to-ima…
A Multimodal Automated Interpretability Agent
Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang +4
This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpr…
NewMove: Customizing text-to-video models with novel motions
Joanna Materzynska, Josef Sivic, Eli Shechtman +3
We introduce an approach for augmenting text-to-video generation models with customized motions, extending their capabilities beyond the motions depicted in the original training d…