Abhishek Bhattacharjee

Abhishek Bhattacharjee, Jack Pilkington, Nita Farahany

Brain foundation models represent a new frontier in AI: instead of processing text or images, these models interpret real-time neural signals from EEG, fMRI, and other neurotechnologies. When integrated with brain-computer interfaces (BCIs), they may enable transformative applications-from thought controlled devices to neuroprosthetics-by interpreting and acting on brain activity in milliseconds. However, these same systems pose unprecedented risks, including the exploitation of subconscious neural signals and the erosion of cognitive liberty. Users cannot easily observe or control how their brain signals are interpreted, creating power asymmetries that are vulnerable to manipulation. This paper proposes embedding fiduciary duties-loyalty, care, and confidentiality-directly into BCI-integrated brain foundation models through technical design. Drawing on legal traditions and recent advancements in AI alignment techniques, we outline implementable architectural and governance mechanisms to ensure these systems act in users' best interests. Placing brain foundation models on a fiduciary footing is essential to realizing their potential without compromising self-determination.

Ketaki Joshi, Raghavendra Pradyumna Pothukuchi, Andre Wibisono et al.

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their ability to learn multiple tasks continually. We discover that catastrophic forgetting in LSTM networks can be overcome in two novel and readily-implementable ways -- separating the LSTM memory either for each task or for each target label. Our approach eschews the need for explicit regularization, hypernetworks, and other complex methods. We quantify the benefits of our approach on recently-proposed LSTM networks for computer memory access prefetching, an important sequential learning problem in ML-based computer system optimization. Compared to state-of-the-art weight regularization methods to mitigate catastrophic forgetting, our approach is simple, effective, and enables faster learning. We also show that our proposal enables the use of small, non-regularized LSTM networks for complex natural language processing in the offline learning scenario, which was previously considered difficult.