Bryan Kian Hsiang Low

MIT CSAIL

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Constitutional AI & AI Ethics (1)Red-Teaming & Adversarial Robustness (1)RLHF & Preference Learning (1)

Frequent co-authors

Thanh Q. Tran (1)Arun Verma (1)Kiwan Wong (1)Daniela Rus (1)

Papers (1)

Feb 23, 2026

MIT CSAIL2w ago·also NUS

BarrierSteer: LLM Safety via Learning Barrier Steering

LLMs can be made significantly safer by steering their latent space trajectories with Control Barrier Functions, preventing unsafe outputs without retraining.

Thanh Q. Tran, Arun Verma, Kiwan Wong +3

Constitutional AI & AI Ethics Red-Teaming & Adversarial Robustness RLHF & Preference Learning

Search

Bryan Kian Hsiang Low

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)