Bell Labs Internship on Cross-Model Feature Transfer (PhD)

Job Description:

An increasing body of work has demonstrated that behavior in neural networks can often be explained and controlled through linear operations on their hidden activations. Model steering, for instance, is a technique where a specific target concept is elicited in the predictions of a generative model by adding a concept vector to its activations
Recent work suggests that these concept vectors can be transferred between models. In this PhD internship, you will investigate the feasibility of cross-model feature transfer for improving the performance and reliability of machine learning models.

* You will review scientific literature
* You will design and implement a cross-model feature transfer method(s)
* Evaluate the effectiveness of the proposed technique(s) on representative problems
* Consolidate your research in a scientific publication and/or a patent application
Location: Antwerp (Belgium) 

Candidate Requirements:

* Student enrolled in Ph.D. Computer Science/Engineering in Machine Learning
* Strong programming skills in Python 
* Language skills: English 
* Experience with representation engineering, mechanistic interpretability, or explainable AI is a big plus.
* A strong publication record is a big plus.