Aaquib Syed

According to our database, Aaquib Syed authored at least 5 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization.

Phillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Refusal in Language Models Is Mediated by a Single Direction.

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Rimsky, Wes Gurnee, Neel Nanda

CoRR, 2024

Refusal in Language Models Is Mediated by a Single Direction.

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Attribution Patching Outperforms Automated Circuit Discovery.

Aaquib Syed, Can Rager, Arthur Conmy

CoRR, 2023

Prune and Tune: Improving Efficient Pruning Techniques for Massive Language Models.

Aaquib Syed, Phillip Guo, Vijaykaarti Sundarapandiyan

Proceedings of the First Tiny Papers Track at ICLR 2023, 2023