Avi Trost — accepted AI-conference papers

2026

Weight Updates as Activation Shifts: A Principled Framework for Steering

Dyah Adila, John Cooper, Alexander Yun, Avi Trost, Frederic Sala

ICML 2026poster

Activation steering promises to be an extremely parameter-efficient form of adaptation, but its effectiveness depends on critical design choices---such as intervention location and parameterization---that currently rely on empirical heuristics rather than a principled foundation. We establish a firs…

Cited by 0 Source ↗Scholar ↗

2024

Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation

Nihal Nayak, Yiyang Nan, Avi Trost, Stephen Bach

ACL 2024findings

We introduce Bonito, an open-source model for conditional task generation that converts unannotated text into task-specific training datasets for instruction tuning. We aim to enable zero-shot task adaptation of large language models on users’ specialized, private data. We train Bonito by fine-tunin…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗